444060c3eb
- Introduced `critic`, an independent adversarial reviewer for security and correctness. - Added `fable-orchestrator` to manage task routing and verification. - Implemented `gauntlet-critic` for fresh-context evaluation of gauntlet rounds. - Created `planner` for generating executable implementation plans with dependencies. - Developed `security-auditor` for application security reviews and audits. - Established `system-steward` to improve agent prompts and skills based on verified failures. - Added `dev-loop` skill for autonomous development loops over repositories. - Implemented `gauntlet-loop` skill for iterative quality benchmarking against reference standards. - Updated project settings to utilize the new orchestrator agent. - Created documentation for `GAUNTLET.md`, `PROGRESS.md`, and `REFERENCE_BAR.md` to track project status and quality benchmarks. - Added detailed prompting style guide to enhance understanding of prompt patterns and agentic loops.
1.9 KiB
1.9 KiB
name, description, allowed-tools
| name | description | allowed-tools |
|---|---|---|
| self-model-audit | Compare what the harness believes about the operator and project (docs/SELF_MODEL.md, CLAUDE.md, role memory) against what recent work and corrections actually reveal, and propose edits that close the gap. Use periodically or after repeated "that's not what I meant" signals. | Read Grep Glob |
Find where the harness is modeling a stale, aspirational, or simply wrong version of the operator or the project — then propose the smallest edits that make the model match reality. Read-only: propose changes, don't apply them without approval.
- Read the belief set.
docs/SELF_MODEL.md,docs/PROJECT_BRIEF.md, the operator/project instructions inCLAUDE.md, active## Lessons, and relevant role memory. Note every claim the system holds about who the operator is, what they want, and how they work. - Read the evidence. Recent handoffs (
docs/HANDOFF.md), recorded decisions (docs/DECISIONS.md), corrections captured inLESSONS_LEARNED.md, and the shape of recent tasks. Infer what the operator's actual behavior and choices reveal. - Find the gaps. Flag each place the stated model conflicts with revealed behavior: preferences that changed, aspirational goals the system optimizes for but recent work contradicts, assumptions never re-confirmed, and voice/style drift. Distinguish "genuinely stale" from "reasonable disagreement" — do not pathologize a deliberate choice.
- Propose edits. For each gap, give the exact
SELF_MODEL.md(orCLAUDE.mdinstruction) change that closes it, tied to the evidence that justifies it. Prefer removing an over-specific belief over adding more. - Return the gap list (belief → contradicting evidence → proposed edit), and route any accepted change through the operator or
system-steward. Never infer a sensitive attribute, and never store credentials, financial/health data, or anything the operator hasn't agreed to persist.