stale-brain
VerifiedAudit AI agent memory and instruction files: CLAUDE.md, AGENTS.md, .cursorrules, GEMINI.md, copilot-instructions.md and every other major agent's memory files (13 agents, 18+ file locations) against the live repository. Use when the user runs /stale-brain or asks to audit, verify, refresh, lint, or fix agent memory, rules, or instruction files; when they complain the agent "ignores rules", "keeps getting it wrong", or that instructions "feel outdated"; and mid-task, whenever an instruction in a loaded memory file contradicts observed reality (a referenced path is missing, a named script doesn't exist, the stated package manager doesn't match the lockfile). Extracts checkable claims, verifies each with cited evidence, ages the rest with half-lives, meters token cost, and proposes approve-only fixes.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.6 KB |
| assets/demo.svg | other | 4.4 KB |
| assets/hero.svg | other | 1.1 KB |
| assets/pulse.svg | other | 3.9 KB |
| references/claim-types.md | markdown | 7.9 KB |
| references/memory-sources.md | markdown | 3.9 KB |
| references/output-format.md | markdown | 15.0 KB |
assets/pulse.svg
View on GitHub<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 880 440" role="img" aria-label="Pulse: the ticker, the graphs, the trend">
<rect width="880" height="440" rx="16" fill="#F8F1E3"/>
<g font-family="'Helvetica Neue', Helvetica, Arial, 'Segoe UI', sans-serif" font-size="12" font-weight="700" fill="#E63A0C" letter-spacing="2.5">
<text x="32" y="44">THE TICKER</text>
<text x="32" y="168">THE GRAPHS</text>
<text x="32" y="292">THE TREND</text>
</g>
<!-- Band 1: ticker, the audit's tail -f -->
<g font-family="ui-monospace, 'Cascadia Code', Menlo, Consolas, monospace" font-size="14" xml:space="preserve">
<text x="32" y="74"><tspan fill="#E63A0C">[stale-brain]</tspan><tspan fill="#5C5142"> inventory · 7 files (4 always-loaded ~4.8k + 3 on-demand ~2.2k)</tspan></text>
<text x="32" y="98"><tspan fill="#E63A0C">[stale-brain]</tspan><tspan fill="#5C5142"> verifying 20/39 · </tspan><tspan fill="#C42B08">●6</tspan><tspan fill="#5C5142"> </tspan><tspan fill="#D9930D">●4</tspan><tspan fill="#5C5142"> </tspan><tspan fill="#A79B87">●2</tspan><tspan fill="#5C5142"> </tspan><tspan fill="#2F9E44">●8</tspan></text>
<text x="32" y="122"><tspan fill="#E63A0C">[stale-brain]</tspan><tspan fill="#5C5142"> verifying 39/39 · </tspan><tspan fill="#C42B08">●13</tspan><tspan fill="#5C5142"> </tspan><tspan fill="#D9930D">●10</tspan><tspan fill="#5C5142"> </tspan><tspan fill="#A79B87">●4</tspan><tspan fill="#5C5142"> </tspan><tspan fill="#2F9E44">●12</tspan></text>
</g>
<!-- Band 2: health bar + token meter -->
<g>
<rect x="32" y="186" width="42" height="20" rx="6" fill="#C42B08"/>
<rect x="80" y="186" width="42" height="20" rx="6" fill="#C42B08"/>
<rect x="128" y="186" width="42" height="20" rx="6" fill="#C42B08"/>
<rect x="176" y="186" width="42" height="20" rx="6" fill="#D9930D"/>
<rect x="224" y="186" width="42" height="20" rx="6" fill="#D9930D"/>
<rect x="272" y="186" width="42" height="20" rx="6" fill="#2F9E44"/>
<rect x="320" y="186" width="42" height="20" rx="6" fill="#2F9E44"/>
<rect x="368" y="186" width="42" height="20" rx="6" fill="#2F9E44"/>
<rect x="416" y="186" width="42" height="20" rx="6" fill="#2F9E44"/>
<rect x="464" y="186" width="42" height="20" rx="6" fill="#2F9E44"/>
<text x="526" y="202" font-family="ui-monospace, Menlo, Consolas, monospace" font-size="16" font-weight="700" fill="#33291F">health 58/100</text>
</g>
<g font-family="ui-monospace, 'Cascadia Code', Menlo, Consolas, monospace" font-size="14" xml:space="preserve">
<text x="32" y="238"><tspan fill="#5C5142">misleading </tspan><tspan fill="#D9930D">▓▓▓</tspan><tspan fill="#CBBFA9">░░░░░░░</tspan><tspan fill="#33291F"> ~1.4k of 4.8k always-loaded tokens (29%) carry stale or false claims</tspan></text>
</g>
<!-- Band 3: trend across audits -->
<g font-family="ui-monospace, 'Cascadia Code', Menlo, Consolas, monospace" font-size="14">
<text x="32" y="322" fill="#5C5142">2026-05-02</text>
<rect x="150" y="308" width="123" height="16" rx="5" fill="#E63A0C" opacity="0.45"/>
<text x="286" y="322" fill="#5C5142">health 41</text>
<text x="32" y="352" fill="#5C5142">2026-06-18</text>
<rect x="150" y="338" width="165" height="16" rx="5" fill="#E63A0C" opacity="0.7"/>
<text x="328" y="352" fill="#5C5142">health 55</text>
<text x="32" y="382" fill="#5C5142">2026-07-31</text>
<rect x="150" y="368" width="174" height="16" rx="5" fill="#2F9E44"/>
<text x="337" y="382" fill="#33291F" font-weight="700">health 58 <tspan fill="#2F9E44">▲ +3</tspan></text>
</g>
<text x="32" y="420" font-family="'Helvetica Neue', Helvetica, Arial, 'Segoe UI', sans-serif" font-size="13" fill="#A79B87">plain Unicode · zero dependencies · ASCII fallback · spec in references/output-format.md</text>
</svg>
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |