Agent
Shared rules for session-developer / session-tester / session manager to ensure bugs and improvements found during work are never silently swallowed but recorded as new handoff tasks.
0 3d ago A 0 tokens
original MIT
0Stars on the repository
27Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Agent
Research director. Opus-level coordinator that evaluates coverage, identifies gaps, and gates transitions between research phases. Makes PASS/REINVESTIGATE/APPROVE/REVISE decisions.
0 3d ago A 43 tokens
original MIT
Agent
Research drafter. Synthesizes verified findings into a structured specification or document. Sonnet base.
0 3d ago A 25 tokens
original MIT
Agent
Research investigator. Explores assigned facets through web search, doc reading, and code analysis. Returns structured findings with evidence and confidence ratings. Sonnet base.
0 3d ago A 35 tokens
original MIT
Agent
Research verifier. Adversarially cross-checks another investigator's findings. Attempts to refute claims, verify sources, and identify logical gaps. Sonnet base.
0 3d ago A 37 tokens
original MIT
Agent
Session developer. Implements assigned tasks via strict TDD and returns a structured report. Sonnet base (session manager can override model via args).
0 3d ago A 32 tokens
original MIT
Agent
Session doc reconciler. Detects and applies documentation updates triggered by code changes. Two modes - audit (read-only) and apply (single writer). Sonnet base.
0 3d ago A 40 tokens
original MIT
Agent
Session integration tester. Runs the whole-project test suite and E2E once, and judges whether the session's work is actually wired into the system. Sonnet base.
0 3d ago A 40 tokens
original MIT
Agent
Session repairer. Fixes a specific finding with targeted verification. Sonnet base.
0 3d ago A 22 tokens
original MIT
Agent
Session reviewer. Validates test report sufficiency, reviews spec/architecture quality, and provides macro-level assessment. Opus base.
0 3d ago A 30 tokens
original MIT
Agent
Session tester. Adversarially verifies the assigned tasks within their own scope — whether the tests mean anything, and what they fail to guarantee. Sonnet base.
0 3d ago A 37 tokens
original MIT