cf5c14ba29
fix: resolve moderate issues across config
...
- architect: restore effort: max to match orchestrate team roster
- orchestrate: remove researcher background annotation (blocks planning),
remove overly broad auditor trigger clause, risk-tag table is authoritative
- qa-checklist: add auditor hard rules (security_findings, build/test status)
- settings.json: simplify .env deny to single **/.env* glob per tool
- rules/01-session: clarify persistent context includes .claude/memory/
- memory: rename todo_inter_agent_schema.md → inter_agent_schema.md
2026-04-02 07:49:46 -04:00
341f500396
feat: add typed inter-agent communication schema
...
Replace freetext signals (RFR, LGTM, VERDICT: PASS) with YAML
frontmatter envelopes routed by a `signal` field. New message-schema
skill defines 12 message types covering worker submissions, review/audit
verdicts, triage/plan results, research results, and orchestrator
commands. All agents load the skill; qa-checklist enforces compliance;
orchestrate routes by envelope signal.
2026-04-02 07:38:02 -04:00
d2fdcbc731
refactor: modularize CLAUDE.md into ~/.claude/rules/ with agent-team content separation
...
- Split monolithic CLAUDE.md into 7 focused rule files in rules/
- Remove agent-team specific content from global rules (subagent cost,
model defaults, tier shortcuts) — already covered by orchestrate skill
- Add "prefer summaries over verbatim output" to orchestrate Step 8
- Update install.sh to symlink rules/ directory
- Trim CLAUDE.md to a minimal pointer since rules auto-load
2026-04-02 07:17:36 -04:00
53e3814ba8
feat(skills): add when_to_use frontmatter for skill discovery guidance
2026-04-02 07:09:40 -04:00
7699f67959
fix: correct stale agent names, false cost claims, and document permissionMode override
...
- Replace "Karen/Verification" with "reviewer/auditor" in worker-protocol
- Reframe parallel dispatch rationale from false "~10% token cost" (only
applies to fork agents with identical prefixes) to accurate wall-clock
latency savings
- Add Permission model section documenting that permissionMode is
overridden when parent runs in acceptEdits mode; disallowedTools is
the actual safety boundary
2026-04-02 07:05:43 -04:00
5f534cbc64
refactor: compress 14-agent team to 7 with wave-based parallelism
...
- Merge grunt + worker + senior-worker → worker (model scaled by orchestrator)
- Merge code-reviewer + karen → reviewer (quality + claim verification)
- Merge security-auditor + verification → auditor (security + runtime, background)
- Architect absorbs requirements-analyst + decomposer (two-phase: triage then plan)
- Rename docs-writer → documenter
- Remove review-coordinator (logic absorbed into orchestrate skill)
- Orchestrate skill: wave-based dispatch, parallelism as hard protocol requirement
with explicit cost rationale (~10% token cost for shared cached context)
2026-04-01 22:09:30 -04:00
71905bda32
fix: only mark plan step complete when all assigned workers receive LGTM
2026-04-01 17:20:25 -04:00
f7d3e1bd73
feat: orchestrator marks plan steps complete after LGTM
2026-04-01 17:19:38 -04:00
d3bc447563
feat: architect always writes plan file as master document, orchestrator reads from disk
2026-04-01 17:17:20 -04:00
22ae8ed516
fix: enforce parallel researcher dispatch in orchestrate skill
2026-04-01 17:07:44 -04:00
8366c09a27
refactor: rename plan agent to architect
2026-04-01 17:01:44 -04:00
e919c91258
refactor: migrate skills from flat .md files to directory structure
2026-04-01 16:56:58 -04:00
