From 949250bbe9baecfb0731eb57e1e5b70f834d6552 Mon Sep 17 00:00:00 2001 From: dan Date: Mon, 12 Jan 2026 13:52:52 -0800 Subject: [PATCH] bd sync: 2026-01-12 13:52:52 --- .beads/issues.jsonl | 10 +++++----- .beads/last-touched | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/.beads/issues.jsonl b/.beads/issues.jsonl index 41b6ab0..7f5db14 100644 --- a/.beads/issues.jsonl +++ b/.beads/issues.jsonl @@ -15,12 +15,12 @@ {"id":"skills-1n3","title":"Set up agent skills for Gemini CLI","description":"The AI agent skills (worklog, web-search, etc.) configured in .skills are not currently working when using the Gemini CLI. \\n\\nObserved behavior:\\n- 'worklog' command not found even after 'direnv reload'.\\n- .envrc sources ~/proj/skills/bin/use-skills.sh, but skills are not accessible in the Gemini agent session.\\n\\nNeed to:\\n1. Investigate how Gemini CLI loads its environment compared to Claude Code.\\n2. Update 'use-skills.sh' or direnv configuration to support Gemini CLI.\\n3. Ensure skill symlinks/binaries are correctly in the PATH for Gemini.","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-22T17:39:28.106296919-05:00","updated_at":"2025-12-28T22:28:49.781533243-05:00","closed_at":"2025-12-28T22:28:49.781533243-05:00","close_reason":"No MCP/extensions. Gemini CLI lacks native skill support (feature request #11506 pending). Current workaround: GEMINI.md references skill paths for manual reading. Revisit when native support lands."} {"id":"skills-1qz","title":"Design: Token and cost budgets per agent","description":"Prevent token blowup footgun. Implement: hard budgets per agent and per run, limit context sizes, separate heavy/light agents, queueing with backpressure, retry with idempotency tokens. Plan-and-Execute pattern: expensive model plans, cheap models execute (90% cost reduction). From research synthesis.","status":"open","priority":3,"issue_type":"task","created_at":"2026-01-10T15:41:00.383262566-08:00","created_by":"dan","updated_at":"2026-01-10T15:41:00.383262566-08:00","dependencies":[{"issue_id":"skills-1qz","depends_on_id":"skills-s6y","type":"blocks","created_at":"2026-01-10T15:41:00.383903314-08:00","created_by":"dan"}]} {"id":"skills-20s","title":"Compare BOUNDARIES.md with upstream","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-03T20:15:53.585115099-08:00","updated_at":"2025-12-03T20:19:28.442646801-08:00","closed_at":"2025-12-03T20:19:28.442646801-08:00","dependencies":[{"issue_id":"skills-20s","depends_on_id":"skills-ebh","type":"discovered-from","created_at":"2025-12-03T20:15:53.586442134-08:00","created_by":"daemon","metadata":"{}"}]} -{"id":"skills-21ka","title":"Design HQ SKILL.md - orchestration instructions","description":"Write the core skill file that teaches agents to orchestrate.\n\nContents:\n- When to use HQ mode\n- How to read bd ready and pick work\n- How to spawn workers (Task tool? claude CLI?)\n- How to monitor progress (worker status, bd comments)\n- How to handle review cycles (approve/reject/iterate)\n- When to use orch for second opinions\n- Error handling and escalation\n\nOutput: skills/hq/SKILL.md","status":"open","priority":2,"issue_type":"task","created_at":"2026-01-11T21:06:34.882938854-08:00","created_by":"dan","updated_at":"2026-01-11T21:06:34.882938854-08:00"} +{"id":"skills-21ka","title":"Design HQ SKILL.md - orchestration instructions","description":"Write the core skill file that teaches agents to orchestrate.\n\nContents:\n- When to use HQ mode\n- How to read bd ready and pick work\n- How to spawn workers (Task tool? claude CLI?)\n- How to monitor progress (worker status, bd comments)\n- How to handle review cycles (approve/reject/iterate)\n- When to use orch for second opinions\n- Error handling and escalation\n\nOutput: skills/hq/SKILL.md","status":"closed","priority":2,"issue_type":"task","created_at":"2026-01-11T21:06:34.882938854-08:00","created_by":"dan","updated_at":"2026-01-12T10:30:43.412715295-08:00","closed_at":"2026-01-12T10:30:43.412715295-08:00","close_reason":"Completed - skills/hq/SKILL.md created with core loop, delegation boundaries, communication protocol, and open questions"} {"id":"skills-25l","title":"Create orch skill for multi-model consensus","description":"Build a skill that exposes orch CLI capabilities to agents for querying multiple AI models","status":"closed","priority":2,"issue_type":"feature","created_at":"2025-11-30T15:43:49.209528963-08:00","updated_at":"2025-11-30T15:47:36.608887453-08:00","closed_at":"2025-11-30T15:47:36.608887453-08:00"} {"id":"skills-266","title":"Add error context to date parsing in types.nim:111","description":"[ERROR] MED - Date parsing can fail on malformed JSON input with unhelpful error. parse() throws on invalid format, caller gets generic parse error. Wrap in try/except with context.","status":"closed","priority":2,"issue_type":"bug","created_at":"2026-01-10T18:50:53.753668466-08:00","created_by":"dan","updated_at":"2026-01-10T20:37:04.742536448-08:00","closed_at":"2026-01-10T20:37:04.742536448-08:00","close_reason":"Implemented consistent error handling strategy"} {"id":"skills-2hp","title":"Define agent autonomy policy for skills","description":"Disagreement in consensus:\n\nGPT: Stricter determinism to prevent 'agent drift'\nGemini: skill: should be a hint, agent can deviate if skill fails\n\nOptions:\n1. Constraint (must use skill, fail if broken)\n2. Heuristic (should use, can justify deviation)\n3. Configurable per-proto or per-step\n\nUX consideration: agents stuck in loops trying broken skills.\n\nNeeds decision before widespread adoption.","status":"closed","priority":4,"issue_type":"task","created_at":"2025-12-23T19:49:59.73500059-05:00","updated_at":"2025-12-29T14:37:35.335994418-05:00","closed_at":"2025-12-29T14:37:35.335994418-05:00","close_reason":"Parked: waiting on gastown (Steve Yegge's orchestration layer for beads). Revisit when gastown lands."} {"id":"skills-2k0","title":"Reframe elevation as scaffolding","description":"Elevation pipeline is over-optimistic. Auto-generation will produce garbage.\n\nReframe:\n- Rename to 'Pattern Extraction' or 'Skill Drafting'\n- Output is skeleton/scaffold, not complete skill\n- Require N\u003e=3 similar executions before suggesting\n- Generate promotion checklist:\n - Preconditions\n - Inputs/outputs contract\n - Failure modes observed\n - Determinism score\n- Generate tests as part of elevation\n\nHuman-in-the-loop is mandatory, not optional.\n\nFrom consensus: both models flagged as medium severity.","status":"closed","priority":3,"issue_type":"task","created_at":"2025-12-23T19:49:48.373417035-05:00","updated_at":"2025-12-29T13:55:35.820906687-05:00","closed_at":"2025-12-29T13:55:35.820906687-05:00","close_reason":"Parked with ADR-001: skills-molecules integration deferred. Current simpler approach (skills as standalone) works well. Revisit when complex orchestration needed."} -{"id":"skills-2l4e","title":"HQ: Orchestrator skill for multi-agent coordination","description":"**Status: Design/Exploration**\n\n## Vision\n\n`hq` is a skill that teaches any capable coding agent to act as an orchestrator - coordinating workers, managing tasks, and handling review cycles.\n\nNot a new binary. A skill that leverages existing tools:\n- `bd` - issue tracking\n- `worker` - lifecycle management \n- `review-gate` - quality enforcement\n- `orch` - multi-model consensus\n\n## Naming\n\n`hq` = headquarters. Short (2 chars), fits existing naming:\n- `bd` (2) - beads\n- `hq` (2) - headquarters\n- `orch` (4) - multi-model\n- `worker` (6) - lifecycle\n\n## Architecture\n\n```\nORCHESTRATOR = Agent + Tools + Skills + Context\n\nTools: bd, worker, review-gate, orch\nSkills: hq (how to orchestrate)\nContext: .beads/, .worker-state/, repo state\nAgent: Claude (or any capable LLM)\n```\n\nThe orchestrator IS the conversation. User talks to agent, agent has tools to spawn/manage workers.\n\n## Triggers (all supported)\n\n1. **bd issue** - `bd ready` shows work, orchestrator picks it up\n2. **Natural language** - User says \"implement feature X\"\n3. **Scheduled/ambient** - Future: cron-like \"check for work\"\n\n## How It Works\n\n```\nUser: \"Implement dark mode for settings page\"\n │\n ▼\nOrchestrator (Claude with hq skill):\n ├── Check bd for existing issue (or create one)\n ├── Decompose if needed (single task or multiple?)\n ├── worker spawn task-001\n ├── Invoke worker Claude (Task tool / claude CLI)\n ├── Monitor via worker status\n ├── Handle review (approve/request-changes)\n ├── worker merge on approval\n └── Report back to user\n```\n\n## Skill Structure\n\n```\nskills/hq/\n├── SKILL.md # Core orchestration instructions\n├── scripts/\n│ └── hq-status # Quick view: bd + worker + review state\n└── templates/\n └── worker-system.md # System prompt for spawned workers\n```\n\n## Key Decisions (TBD)\n\n1. **Worker invocation**: Task tool subagent? `claude` CLI? Manual?\n2. **Decomposition**: When to split into multiple workers?\n3. **Review policy**: Auto-approve simple tasks? Always human?\n4. **Failure handling**: Retry? Escalate? Reassign?\n\n## Related\n\n- Worker CLI: src/worker.nim (built, working)\n- Review-gate: skills/review-gate/ (built, needs deployment)\n- Benchmark harness: skills-qng9 (design phase)\n\n## Prior Art Considered\n\n- Strix (ambient AI assistant)\n- Helm (taken - K8s package manager)\n- Various agent frameworks (CrewAI, LangGraph, etc.)\n\nOur approach: CLI tools + state files + skills (no daemons)","status":"open","priority":2,"issue_type":"feature","created_at":"2026-01-11T20:52:42.131018989-08:00","created_by":"dan","updated_at":"2026-01-11T20:52:42.131018989-08:00","dependencies":[{"issue_id":"skills-2l4e","depends_on_id":"skills-s6y","type":"blocks","created_at":"2026-01-11T20:58:56.699198314-08:00","created_by":"dan"},{"issue_id":"skills-2l4e","depends_on_id":"skills-21ka","type":"blocks","created_at":"2026-01-11T21:07:47.572946645-08:00","created_by":"dan"},{"issue_id":"skills-2l4e","depends_on_id":"skills-cg7c","type":"blocks","created_at":"2026-01-11T21:07:47.651118411-08:00","created_by":"dan"},{"issue_id":"skills-2l4e","depends_on_id":"skills-3j55","type":"blocks","created_at":"2026-01-11T21:07:47.745402558-08:00","created_by":"dan"},{"issue_id":"skills-2l4e","depends_on_id":"skills-iusu","type":"blocks","created_at":"2026-01-11T21:07:47.839898058-08:00","created_by":"dan"}],"comments":[{"id":1,"issue_id":"skills-2l4e","author":"dan","text":"Test comment from agent - exploring messaging","created_at":"2026-01-12T05:03:58Z"}]} +{"id":"skills-2l4e","title":"HQ: Orchestrator skill for multi-agent coordination","description":"**Status: Design/Exploration**\n\n## Vision\n\n`hq` is a skill that teaches any capable coding agent to act as an orchestrator - coordinating workers, managing tasks, and handling review cycles.\n\nNot a new binary. A skill that leverages existing tools:\n- `bd` - issue tracking\n- `worker` - lifecycle management \n- `review-gate` - quality enforcement\n- `orch` - multi-model consensus\n\n## Naming\n\n`hq` = headquarters. Short (2 chars), fits existing naming:\n- `bd` (2) - beads\n- `hq` (2) - headquarters\n- `orch` (4) - multi-model\n- `worker` (6) - lifecycle\n\n## Architecture\n\n```\nORCHESTRATOR = Agent + Tools + Skills + Context\n\nTools: bd, worker, review-gate, orch\nSkills: hq (how to orchestrate)\nContext: .beads/, .worker-state/, repo state\nAgent: Claude (or any capable LLM)\n```\n\nThe orchestrator IS the conversation. User talks to agent, agent has tools to spawn/manage workers.\n\n## Triggers (all supported)\n\n1. **bd issue** - `bd ready` shows work, orchestrator picks it up\n2. **Natural language** - User says \"implement feature X\"\n3. **Scheduled/ambient** - Future: cron-like \"check for work\"\n\n## How It Works\n\n```\nUser: \"Implement dark mode for settings page\"\n │\n ▼\nOrchestrator (Claude with hq skill):\n ├── Check bd for existing issue (or create one)\n ├── Decompose if needed (single task or multiple?)\n ├── worker spawn task-001\n ├── Invoke worker Claude (Task tool / claude CLI)\n ├── Monitor via worker status\n ├── Handle review (approve/request-changes)\n ├── worker merge on approval\n └── Report back to user\n```\n\n## Skill Structure\n\n```\nskills/hq/\n├── SKILL.md # Core orchestration instructions\n├── scripts/\n│ └── hq-status # Quick view: bd + worker + review state\n└── templates/\n └── worker-system.md # System prompt for spawned workers\n```\n\n## Key Decisions (TBD)\n\n1. **Worker invocation**: Task tool subagent? `claude` CLI? Manual?\n2. **Decomposition**: When to split into multiple workers?\n3. **Review policy**: Auto-approve simple tasks? Always human?\n4. **Failure handling**: Retry? Escalate? Reassign?\n\n## Related\n\n- Worker CLI: src/worker.nim (built, working)\n- Review-gate: skills/review-gate/ (built, needs deployment)\n- Benchmark harness: skills-qng9 (design phase)\n\n## Prior Art Considered\n\n- Strix (ambient AI assistant)\n- Helm (taken - K8s package manager)\n- Various agent frameworks (CrewAI, LangGraph, etc.)\n\nOur approach: CLI tools + state files + skills (no daemons)","status":"closed","priority":2,"issue_type":"feature","created_at":"2026-01-11T20:52:42.131018989-08:00","created_by":"dan","updated_at":"2026-01-12T10:49:31.53419315-08:00","closed_at":"2026-01-12T10:49:31.53419315-08:00","close_reason":"MVP complete: SKILL.md with orchestration loop, worker-system.md template, hq-status script. Ready for spike testing.","dependencies":[{"issue_id":"skills-2l4e","depends_on_id":"skills-s6y","type":"blocks","created_at":"2026-01-11T20:58:56.699198314-08:00","created_by":"dan"},{"issue_id":"skills-2l4e","depends_on_id":"skills-21ka","type":"blocks","created_at":"2026-01-11T21:07:47.572946645-08:00","created_by":"dan"},{"issue_id":"skills-2l4e","depends_on_id":"skills-cg7c","type":"blocks","created_at":"2026-01-11T21:07:47.651118411-08:00","created_by":"dan"},{"issue_id":"skills-2l4e","depends_on_id":"skills-3j55","type":"blocks","created_at":"2026-01-11T21:07:47.745402558-08:00","created_by":"dan"},{"issue_id":"skills-2l4e","depends_on_id":"skills-iusu","type":"blocks","created_at":"2026-01-11T21:07:47.839898058-08:00","created_by":"dan"}],"comments":[{"id":1,"issue_id":"skills-2l4e","author":"dan","text":"Test comment from agent - exploring messaging","created_at":"2026-01-12T05:03:58Z"}]} {"id":"skills-2wjp","title":"Log parseInt failures in getBranchStatus instead of silent discard","description":"[ERROR] LOW git.nim:139-143 - parseInt failures silently discarded. Return (0,0) explicitly with comment, or log the parse failure.","status":"closed","priority":4,"issue_type":"task","created_at":"2026-01-10T19:52:14.359878211-08:00","created_by":"dan","updated_at":"2026-01-10T20:37:04.762486765-08:00","closed_at":"2026-01-10T20:37:04.762486765-08:00","close_reason":"Implemented consistent error handling strategy"} {"id":"skills-2xc","title":"Extract date format constant in types.nim","description":"[SMELL] LOW - Date format 'yyyy-MM-dd HH:mm:sszzz' hardcoded in toJson/fromJson. Extract to const DateFormat* or use times.IsoDateTimeFormat.","status":"closed","priority":3,"issue_type":"task","created_at":"2026-01-10T18:50:53.896053988-08:00","created_by":"dan","updated_at":"2026-01-10T20:53:25.756173382-08:00","closed_at":"2026-01-10T20:53:25.756173382-08:00","close_reason":"ContextDateFormat already extracted in error handling refactor"} {"id":"skills-2xo","title":"Add README.md for web-search skill","description":"web-search skill has SKILL.md and scripts but no README.md. AGENTS.md says README.md is for humans, contains installation instructions, usage examples, prerequisites.","status":"closed","priority":2,"issue_type":"task","created_at":"2025-11-30T11:58:14.26066025-08:00","updated_at":"2025-12-28T22:37:48.324822157-05:00","closed_at":"2025-12-28T22:37:48.324822157-05:00","close_reason":"Added README.md with prerequisites, usage examples, and cross-references","dependencies":[{"issue_id":"skills-2xo","depends_on_id":"skills-vb5","type":"blocks","created_at":"2025-11-30T12:01:30.240439018-08:00","created_by":"daemon","metadata":"{}"}]} @@ -32,7 +32,7 @@ {"id":"skills-3gk","title":"Research: Cross-agent hook alternatives","description":"Claude Code has hooks (Stop, SessionStart, etc.) for mechanical enforcement. Other agents don't.\n\nResearch alternatives for cross-agent quality gates:\n\n1. **External wrapper** - Script that launches agent, monitors output, gates exit\n2. **Protocol-based** - Agent follows instructions in AGENTS.md, posts to state store\n3. **Orchestrator pattern** - Meta-agent spawns worker + reviewer, enforces gate\n4. **Hybrid** - Hooks where available, protocol elsewhere\n\nEvaluate:\n- Enforcement strength (mechanical vs cooperative)\n- Implementation complexity\n- Agent compatibility\n- Failure modes\n\nOutput: Comparison doc with recommendation","status":"closed","priority":2,"issue_type":"task","created_at":"2026-01-09T17:14:20.433319252-08:00","created_by":"dan","updated_at":"2026-01-09T19:33:36.683960774-08:00","closed_at":"2026-01-09T19:33:36.683960774-08:00","close_reason":"Consolidated into skills-8sj"} {"id":"skills-3hri","title":"HQ SKILL.md design gaps from orch consensus","description":"Orch consensus review of HQ SKILL.md (flash-or, gemini, gpt @ temp 1.2) identified multiple design gaps.\n\nSession: 01KESKA3TVWYVW2PTS0XRBR1Q7\n\n## Architectural Decision\n\nHQ should be a **thin orchestration layer** making decisions, not a monolith handling everything.\n\nIssues have been reclassified to proper layers:\n- **HQ**: WIP limits, DoD, templates, core loop, dependency scoping\n- **worker CLI**: Launch, rebase, salvage, retry counts\n- **review-gate**: CI gates, post-merge verification\n- **bd**: Context pruning, message format\n- **infrastructure**: Security, disk space\n\n2 issues closed as duplicates:\n- skills-gyvt → merged into skills-vdup (retry limits)\n- skills-8umb → merged into skills-8hyz (context pruning)\n\nSee epic comments for full architectural rationale.","status":"open","priority":2,"issue_type":"epic","created_at":"2026-01-12T09:19:33.047763881-08:00","created_by":"dan","updated_at":"2026-01-12T09:59:21.172216773-08:00","dependencies":[{"issue_id":"skills-3hri","depends_on_id":"skills-8umb","type":"blocks","created_at":"2026-01-12T09:20:37.67133727-08:00","created_by":"dan"},{"issue_id":"skills-3hri","depends_on_id":"skills-q8i0","type":"blocks","created_at":"2026-01-12T09:26:17.249825798-08:00","created_by":"dan"},{"issue_id":"skills-3hri","depends_on_id":"skills-qqaa","type":"blocks","created_at":"2026-01-12T09:26:17.300419697-08:00","created_by":"dan"},{"issue_id":"skills-3hri","depends_on_id":"skills-lr29","type":"blocks","created_at":"2026-01-12T09:26:17.353360648-08:00","created_by":"dan"},{"issue_id":"skills-3hri","depends_on_id":"skills-gyvt","type":"blocks","created_at":"2026-01-12T09:26:17.420475584-08:00","created_by":"dan"},{"issue_id":"skills-3hri","depends_on_id":"skills-365b","type":"blocks","created_at":"2026-01-12T09:26:17.479320404-08:00","created_by":"dan"},{"issue_id":"skills-3hri","depends_on_id":"skills-9mhk","type":"blocks","created_at":"2026-01-12T09:26:17.532630668-08:00","created_by":"dan"},{"issue_id":"skills-3hri","depends_on_id":"skills-4dnt","type":"blocks","created_at":"2026-01-12T09:26:17.591580206-08:00","created_by":"dan"},{"issue_id":"skills-3hri","depends_on_id":"skills-du0a","type":"blocks","created_at":"2026-01-12T09:26:17.640412141-08:00","created_by":"dan"},{"issue_id":"skills-3hri","depends_on_id":"skills-n8ck","type":"blocks","created_at":"2026-01-12T09:26:17.70105987-08:00","created_by":"dan"},{"issue_id":"skills-3hri","depends_on_id":"skills-8l92","type":"blocks","created_at":"2026-01-12T09:26:17.755417151-08:00","created_by":"dan"},{"issue_id":"skills-3hri","depends_on_id":"skills-a50w","type":"blocks","created_at":"2026-01-12T09:26:17.810308166-08:00","created_by":"dan"},{"issue_id":"skills-3hri","depends_on_id":"skills-6ppz","type":"blocks","created_at":"2026-01-12T09:26:17.865598387-08:00","created_by":"dan"},{"issue_id":"skills-3hri","depends_on_id":"skills-ya3n","type":"blocks","created_at":"2026-01-12T09:26:17.912357881-08:00","created_by":"dan"}],"comments":[{"id":3,"issue_id":"skills-3hri","author":"dan","text":"[HQ:arch:2026-01-12T09:35:58-08:00] Architectural review: HQ should be thin orchestration layer. Reclassifying issues to proper layers:\n\nLAYER ASSIGNMENTS:\n- HQ: Orchestration decisions (what to work on, approve/reject, WIP limits)\n- review-gate: Quality enforcement (CI gates, test verification, evidence)\n- worker CLI: Lifecycle \u0026 isolation (state machine, retry counts, rebase, launch)\n- bd: Issue tracking \u0026 messaging (context pruning, message format)\n- infrastructure: Runtime concerns (sandboxing, disk space)\n\nISSUES BEING RECLASSIFIED:\n- CI/test gates → review-gate\n- Retry counting → worker CLI (merge with skills-vdup)\n- Context bloat → bd (merge with skills-8hyz)\n- Rebase handling → worker CLI\n- Security/sandbox → infrastructure\n- Resource exhaustion → infrastructure\n- Worker launch → worker CLI\n- Post-merge verification → review-gate\n- Stale salvage → worker CLI\n\nISSUES STAYING IN HQ:\n- WIP limits, DoD checklist, communication templates, core loop, dependency scoping","created_at":"2026-01-12T17:35:58Z"}]} {"id":"skills-3ib6","title":"Create initial scenario suite (easy/medium/hard)","description":"Write 6-9 scenarios across difficulty levels:\n\nEasy (clear spec, single file):\n- Add factorial function\n- Fix typo in config\n- Add CLI flag\n\nMedium (requires understanding context):\n- Refactor function to use new pattern\n- Add caching to existing endpoint\n- Write tests for existing code\n\nHard (ambiguous, multi-file, debugging):\n- Fix race condition\n- Migrate to new library version\n- Resolve conflicting requirements","status":"closed","priority":3,"issue_type":"task","created_at":"2026-01-11T16:19:46.322151154-08:00","created_by":"dan","updated_at":"2026-01-11T16:38:26.581305762-08:00","closed_at":"2026-01-11T16:38:26.581305762-08:00","close_reason":"Pausing - need to validate approach with simpler spike first","dependencies":[{"issue_id":"skills-3ib6","depends_on_id":"skills-ig7w","type":"blocks","created_at":"2026-01-11T16:20:20.771085983-08:00","created_by":"dan"}]} -{"id":"skills-3j55","title":"Create hq-status script","description":"Unified status view across all coordination layers.\n\nShows:\n- bd ready (available work)\n- worker status (active workers)\n- review-gate status (pending reviews)\n- Recent bd comments (coordination messages)\n\nUsage: hq-status [--json]\n\nOutput: skills/hq/scripts/hq-status","status":"open","priority":3,"issue_type":"task","created_at":"2026-01-11T21:06:34.998651979-08:00","created_by":"dan","updated_at":"2026-01-11T21:06:34.998651979-08:00"} +{"id":"skills-3j55","title":"Create hq-status script","description":"Unified status view across all coordination layers.\n\nShows:\n- bd ready (available work)\n- worker status (active workers)\n- review-gate status (pending reviews)\n- Recent bd comments (coordination messages)\n\nUsage: hq-status [--json]\n\nOutput: skills/hq/scripts/hq-status","status":"closed","priority":3,"issue_type":"task","created_at":"2026-01-11T21:06:34.998651979-08:00","created_by":"dan","updated_at":"2026-01-12T10:47:40.367540818-08:00","closed_at":"2026-01-12T10:47:40.367540818-08:00","close_reason":"Completed - skills/hq/scripts/hq-status created"} {"id":"skills-3ja","title":"Design: Cross-agent quality gate architecture","description":"Design a quality gate pattern that works regardless of agent.\n\nRequirements:\n- Worker agent can be Claude, Gemini, OpenCode, etc.\n- Reviewer agent can be any capable model\n- Gate blocks completion until reviewer approves\n- Circuit breakers prevent infinite loops\n- Works in autonomous/unattended scenarios\n\nBuilding on alice/idle research (docs/research/idle-alice-quality-gate.md):\n- alice uses Claude hooks + jwz state\n- We need agent-agnostic equivalent\n\nConsiderations:\n- State management: jwz vs beads vs simple files\n- Enforcement: mechanical vs protocol-based\n- Reviewer selection: orch consensus vs single model\n- Activation: opt-in prefix vs context-based\n\nOutput: Architecture doc with component design","status":"closed","priority":2,"issue_type":"task","created_at":"2026-01-09T17:14:20.657906484-08:00","created_by":"dan","updated_at":"2026-01-09T19:33:36.694607649-08:00","closed_at":"2026-01-09T19:33:36.694607649-08:00","close_reason":"Consolidated into skills-8sj"} {"id":"skills-3o7","title":"Fix ai-skills.nix missing sha256 hash","description":"modules/ai-skills.nix:16 has empty sha256 placeholder for opencode-skills npm package. Either get actual hash or remove/comment out the incomplete fetchFromNpm approach.","status":"closed","priority":2,"issue_type":"bug","created_at":"2025-11-30T11:58:24.404929863-08:00","updated_at":"2025-11-30T12:12:39.372107348-08:00","closed_at":"2025-11-30T12:12:39.372107348-08:00"} {"id":"skills-3uv9","title":"Consider logging cleanup failures in removeWorktree/removeBranch","description":"[ERROR] LOW git.nim:55,60,62 - Cleanup operations ignore failures. May leave orphaned resources. Consider logging failures for debugging.","status":"closed","priority":4,"issue_type":"task","created_at":"2026-01-10T19:52:14.792134512-08:00","created_by":"dan","updated_at":"2026-01-10T20:37:04.764769727-08:00","closed_at":"2026-01-10T20:37:04.764769727-08:00","close_reason":"Implemented consistent error handling strategy"} @@ -124,7 +124,7 @@ {"id":"skills-bww","title":"Benchmark AT-SPI overhead and coverage","description":"## Goal\nMeasure AT-SPI's runtime overhead and coverage across apps.\n\n## Prerequisites\n- Enable `services.gnome.at-spi2-core.enable = true` in NixOS\n- Set `QT_LINUX_ACCESSIBILITY_ALWAYS_ON=1` for Qt apps\n- Rebuild and re-login\n\n## Overhead benchmarks\n1. **Startup time**: App launch with/without AT-SPI\n2. **Memory**: RSS delta with AT-SPI enabled\n3. **CPU**: Idle CPU with AT-SPI bus running\n4. **UI latency**: Input-to-paint latency (if measurable)\n\n## Coverage audit\nFor each app, document:\n- Does it expose accessibility tree?\n- How complete is the tree? (all elements vs partial)\n- Are coordinates accurate?\n- Are element types/roles correct?\n\n### Apps to test\n- [ ] Firefox\n- [ ] Ghostty terminal\n- [ ] Nautilus/file manager\n- [ ] VS Code / Electron app\n- [ ] A Qt app (if any installed)\n\n## Query benchmarks\n- Time to enumerate all elements in a window\n- Time to find element by role/name\n- Memory overhead of pyatspi queries\n\n## Depends on\n- skills-pdg (Enable AT-SPI for UI tree access)","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-17T14:13:21.599259773-08:00","updated_at":"2025-12-17T14:13:21.599259773-08:00","dependencies":[{"issue_id":"skills-bww","depends_on_id":"skills-pdg","type":"blocks","created_at":"2025-12-17T14:13:41.633210539-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"skills-byq","title":"Integrate: review-gate with worker primitives","description":"Connect existing review-gate CLI with new worker system.\n\n## Current state\nreview-gate CLI exists with:\n- check/enable/approve/reject\n- Circuit breaker (3 strikes)\n- Stop hook integration (for Claude)\n\n## Integration needed\n- worker spawn enables review-gate automatically\n- worker status shows review state\n- worker approve/reject wraps review-gate\n- Evidence artifacts feed into review-gate\n\n## File coordination\n.worker-state/X.json includes:\n - review_session_id (links to .review-state/)\n - needs_review: true/false\n - review_status: pending/approved/rejected","notes":"MVP Tier 1: Wire review-gate to worker state machine","status":"closed","priority":1,"issue_type":"task","created_at":"2026-01-10T12:15:04.625083755-08:00","created_by":"dan","updated_at":"2026-01-10T23:24:21.172713875-08:00","closed_at":"2026-01-10T23:24:21.172713875-08:00","close_reason":"Integrated review-gate with worker: spawn enables review, status/show display review state, approve/reject update review-gate, cancel/merge clean up review state","dependencies":[{"issue_id":"skills-byq","depends_on_id":"skills-s6y","type":"blocks","created_at":"2026-01-10T12:15:10.376067847-08:00","created_by":"dan"}]} {"id":"skills-cc0","title":"spec-review: Add anti-hallucination constraints to prompts","description":"Models may paraphrase and present as quotes, or invent requirements/risks not in the doc.\n\nAdd:\n- 'Quotes must be verbatim'\n- 'Do not assume technologies/constraints not stated'\n- 'If missing info, list as open questions rather than speculating'","status":"closed","priority":3,"issue_type":"task","created_at":"2025-12-15T00:23:26.045478292-08:00","updated_at":"2025-12-15T14:07:19.556888057-08:00","closed_at":"2025-12-15T14:07:19.556888057-08:00"} -{"id":"skills-cg7c","title":"Design worker system prompt template","description":"Create the system prompt/context that spawned workers receive.\n\nContents:\n- Role definition (you are a worker agent)\n- Task context (from bd issue or description)\n- Available tools (worker start/done/heartbeat, bd comments)\n- Completion criteria\n- How to signal blockers/questions\n- How to hand off for review\n\nOutput: skills/hq/templates/worker-system.md","status":"open","priority":2,"issue_type":"task","created_at":"2026-01-11T21:06:34.943983399-08:00","created_by":"dan","updated_at":"2026-01-11T21:06:34.943983399-08:00"} +{"id":"skills-cg7c","title":"Design worker system prompt template","description":"Create the system prompt/context that spawned workers receive.\n\nContents:\n- Role definition (you are a worker agent)\n- Task context (from bd issue or description)\n- Available tools (worker start/done/heartbeat, bd comments)\n- Completion criteria\n- How to signal blockers/questions\n- How to hand off for review\n\nOutput: skills/hq/templates/worker-system.md","status":"closed","priority":2,"issue_type":"task","created_at":"2026-01-11T21:06:34.943983399-08:00","created_by":"dan","updated_at":"2026-01-12T10:41:56.919305275-08:00","closed_at":"2026-01-12T10:41:56.919305275-08:00","close_reason":"Completed - skills/hq/templates/worker-system.md created with role definition, available commands, communication protocol, and completion criteria"} {"id":"skills-cjx","title":"Create spec-review skill for orch + spec-kit integration","description":"A new skill that integrates orch multi-model consensus with spec-kit workflows.\n\n**Purpose**: Use different models/temps/stances to review spec-kit artifacts before phase transitions.\n\n**Proposed commands**:\n- /spec-review.spec - Critique current spec for completeness, ambiguity, gaps\n- /spec-review.plan - Evaluate architecture decisions in plan\n- /spec-review.gate - Go/no-go consensus before phase transition\n\n**Structure**:\n```\nskills/spec-review/\n├── SKILL.md\n├── commands/\n│ ├── spec.md\n│ ├── plan.md\n│ └── gate.md\n└── prompts/\n └── ...\n```\n\n**Key design points**:\n- Finds spec/plan files from current branch or specs/ directory\n- Invokes orch with appropriate prompt, models, stances\n- Presents consensus/critique results\n- AI reviewing AI is valuable redundancy (different models/temps/stances)\n\n**Dependencies**:\n- orch CLI must be available (blocked on dotfiles-3to)\n- spec-kit project structure conventions","status":"closed","priority":2,"issue_type":"feature","created_at":"2025-12-14T17:50:13.22879874-08:00","updated_at":"2025-12-15T00:10:23.122342449-08:00","closed_at":"2025-12-15T00:10:23.122342449-08:00"} {"id":"skills-cnc","title":"Add direnv helper for per-repo skill deployment","description":"Create sourceable helper script and documentation for the standard per-repo skill deployment pattern using direnv + nix build.","status":"closed","priority":2,"issue_type":"feature","created_at":"2025-11-30T12:19:20.71056749-08:00","updated_at":"2025-11-30T12:37:47.22638278-08:00","closed_at":"2025-11-30T12:37:47.22638278-08:00"} {"id":"skills-czz","title":"Research OpenCode agents for skill integration","description":"DEPLOYMENT.md:218 has TODO to research OpenCode agents. Need to understand how Build/Plan/custom agents work and whether skills need agent-specific handling.","status":"closed","priority":2,"issue_type":"task","created_at":"2025-11-30T11:58:24.855701141-08:00","updated_at":"2025-12-28T20:48:58.373191479-05:00","closed_at":"2025-12-28T20:48:58.373191479-05:00","close_reason":"Researched OpenCode agents - documented in DEPLOYMENT.md. Skills deploy globally, permissions control per-agent access."} @@ -230,7 +230,7 @@ {"id":"skills-ty7","title":"Define trace levels (audit vs debug)","description":"Two trace levels to manage noise vs utility:\n\n1. Audit trace (minimal, safe, always on):\n - skill id/ref, start/end\n - high-level checkpoints\n - artifact hashes/paths\n - exit status\n\n2. Debug trace (opt-in, verbose):\n - tool calls with args\n - stdout/stderr snippets\n - expanded inputs\n - timing details\n\nConsider OpenTelemetry span model as reference.\nGPT proposed this; Gemini focused on rotation/caps instead.","status":"closed","priority":3,"issue_type":"task","created_at":"2025-12-23T19:49:48.514684945-05:00","updated_at":"2025-12-29T13:55:35.838961236-05:00","closed_at":"2025-12-29T13:55:35.838961236-05:00","close_reason":"Parked with ADR-001: skills-molecules integration deferred. Current simpler approach (skills as standalone) works well. Revisit when complex orchestration needed."} {"id":"skills-u3d","title":"Define skill trigger conditions","description":"How does an agent know WHEN to apply a skill/checklist?\n\nOptions:\n- frontmatter triggers: field with patterns\n- File-based detection\n- Agent judgment from description\n- Beads hooks on state transitions\n- LLM-based pattern detection","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-23T17:59:09.69468767-05:00","updated_at":"2025-12-28T22:25:38.579989006-05:00","closed_at":"2025-12-28T22:25:38.579989006-05:00","close_reason":"Resolved: agent judgment from description is the standard. Good descriptions + 'When to Use' sections are sufficient. No new trigger mechanism needed - would add complexity without clear benefit."} {"id":"skills-uan","title":"worklog: merge Guidelines and Remember sections","description":"Guidelines (8 points) and Remember (6 points) sections overlap significantly - both emphasize comprehensiveness, future context, semantic compression. Consolidate into single principles list. Found by bloat lens review.","status":"closed","priority":3,"issue_type":"task","created_at":"2025-12-25T02:03:16.148596791-05:00","updated_at":"2025-12-27T10:05:51.527595332-05:00","closed_at":"2025-12-27T10:05:51.527595332-05:00","close_reason":"Closed"} -{"id":"skills-udu","title":"Design: Cross-agent compatibility layer","description":"Make primitives work with Claude, Gemini, Codex, etc.\n\n## Challenge\nDifferent agents have different:\n- CLI interfaces (claude -p, gemini, codex)\n- Permission models\n- Hook support (Claude has Stop hooks, others don't)\n\n## Approach\nworker spawn abstracts the agent:\n worker spawn --agent=claude \"task\"\n worker spawn --agent=gemini \"task\"\n worker spawn --agent=codex \"task\"\n\nEach agent adapter handles:\n- Command-line invocation\n- Output capture\n- Permission prompt detection\n- Completion detection\n\n## File-based coordination\nAll agents can read/write files.\n.worker-state/ is the universal interface.\nNo agent-specific hooks required for coordination.\n\n## Hook-enhanced (optional)\nClaude: Stop hook for hard gating\nOthers: Orchestrator polling for soft gating","status":"open","priority":2,"issue_type":"task","created_at":"2026-01-10T12:14:51.639787315-08:00","created_by":"dan","updated_at":"2026-01-10T12:14:51.639787315-08:00","dependencies":[{"issue_id":"skills-udu","depends_on_id":"skills-s6y","type":"blocks","created_at":"2026-01-10T12:15:10.2649542-08:00","created_by":"dan"}]} +{"id":"skills-udu","title":"Design: Cross-agent compatibility layer","description":"Make primitives work with Claude, Gemini, Codex, etc.\n\n## Challenge\nDifferent agents have different:\n- CLI interfaces (claude -p, gemini, codex)\n- Permission models\n- Hook support (Claude has Stop hooks, others don't)\n\n## Approach\nworker spawn abstracts the agent:\n worker spawn --agent=claude \"task\"\n worker spawn --agent=gemini \"task\"\n worker spawn --agent=codex \"task\"\n\nEach agent adapter handles:\n- Command-line invocation\n- Output capture\n- Permission prompt detection\n- Completion detection\n\n## File-based coordination\nAll agents can read/write files.\n.worker-state/ is the universal interface.\nNo agent-specific hooks required for coordination.\n\n## Hook-enhanced (optional)\nClaude: Stop hook for hard gating\nOthers: Orchestrator polling for soft gating","status":"open","priority":2,"issue_type":"task","created_at":"2026-01-10T12:14:51.639787315-08:00","created_by":"dan","updated_at":"2026-01-10T12:14:51.639787315-08:00","dependencies":[{"issue_id":"skills-udu","depends_on_id":"skills-s6y","type":"blocks","created_at":"2026-01-10T12:15:10.2649542-08:00","created_by":"dan"}],"comments":[{"id":16,"issue_id":"skills-udu","author":"dan","text":"[HQ:status:2026-01-12T13:52:39-08:00] Decided against --agent flag. Cross-agent instructions added directly to HQ SKILL.md instead. Simpler approach - HQ just runs bash commands per agent type. See 'Cross-Agent Compatibility' and 'Launch by Agent Type' sections.","created_at":"2026-01-12T21:52:39Z"}]} {"id":"skills-ut4","title":"Investigate: Sandbox for research-only subagents","description":"Can we ensure research/explore subagents run in a restricted sandbox?\n\n## Context\nWhen spawning subagents for research tasks (codebase exploration, web search, reading files), they should be read-only and sandboxed - no writes, no destructive commands.\n\n## Questions to Answer\n1. Does Claude Code Task tool support sandbox restrictions for subagents?\n2. Can we pass sandbox mode to Gemini CLI subagents?\n3. How does OpenCode's permission system work for subagents?\n4. Can Codex subagents inherit sandbox restrictions?\n\n## Desired Behavior\n- Research subagent can: Read, Grep, Glob, WebFetch, WebSearch\n- Research subagent cannot: Write, Edit, Bash (destructive), delete\n\n## Security Benefit\nPrevents research tasks from accidentally (or maliciously) modifying files or running destructive commands.\n\nRelated: Cross-agent quality gate architecture (skills-3ja)","status":"open","priority":2,"issue_type":"task","created_at":"2026-01-09T17:31:05.49739394-08:00","created_by":"dan","updated_at":"2026-01-09T17:31:05.49739394-08:00"} {"id":"skills-uz4","title":"Compare RESUMABILITY.md with upstream","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-03T20:15:54.897754095-08:00","updated_at":"2025-12-03T20:19:29.384645842-08:00","closed_at":"2025-12-03T20:19:29.384645842-08:00","dependencies":[{"issue_id":"skills-uz4","depends_on_id":"skills-ebh","type":"discovered-from","created_at":"2025-12-03T20:15:54.899671178-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"skills-v6p","title":"Move Message type from db.nim to types.nim","description":"[COUPLING] LOW db.nim:130-141 - Message type defined in db.nim but other types are in types.nim. Move for consistency.","status":"open","priority":4,"issue_type":"task","created_at":"2026-01-10T18:52:41.927231152-08:00","created_by":"dan","updated_at":"2026-01-10T18:52:41.927231152-08:00"} diff --git a/.beads/last-touched b/.beads/last-touched index a098e44..af6017d 100644 --- a/.beads/last-touched +++ b/.beads/last-touched @@ -1 +1 @@ -skills-vz05 +skills-hf1