Skip to content

aicraftbook/aicraftbook-skills / skills/context-trim

context-trim

Flagged

Audits a coding agent's project instruction file (CLAUDE.md, AGENTS.md, CLAUDE.local.md, .claude/rules, GEMINI.md, copilot-instructions.md or similar) against the repository it describes, then proposes a shorter, accurate version and changes nothing until the user approves. Use when someone asks to audit, clean up, trim, shorten, fix or review their CLAUDE.md or AGENTS.md, says the agent ignores its instructions, or suspects the file is stale, too long or contradicts the code.

FileKindSize
CHANGELOG.mdmarkdown1.3 KB
LICENSEother1.0 KB
README.mdmarkdown11.0 KB
SKILL.mdskill md8.3 KB
evals/independent-2026-10-21-v1.0.0.jsonconfig67.8 KB
evals/independent-2026-10-21.jsonconfig66.3 KB
evals/results-2026-10-22.jsonconfig5.4 KB
evals/tasks.jsonconfig9.1 KB
examples/requests.mdmarkdown1023 B
references/checklist.mdmarkdown7.2 KB
references/memory-docs.mdmarkdown8.3 KB
skill.jsonconfig1.3 KB

evals/results-2026-10-22.json

View on GitHub
{
  "skill": "context-trim",
  "date": "2026-10-22",
  "model": "sonnet",
  "repeats": 1,
  "method": "Each task run headless with Claude Code in a fresh empty folder, tools limited to Skill, Read, Glob; no MCP servers; project settings only. Baseline has no skill; the skill run has the skill in .claude/skills/. Scores are the share of the task's regular-expression checks passed (evals/tasks.json). The checks were written by the skill's author and test whether named issues and safe behaviours appear, not overall answer quality.",
  "claudeCodeVersion": "2.1.303 (Claude Code)",
  "baseline": {
    "runs": 3,
    "errors": 0,
    "meanScore": 0.8571428571428572,
    "meanOutputTokens": 1651,
    "meanDurationMs": 15888.666666666666,
    "skillInvokedRuns": 0,
    "byTask": {
      "node-repo-drift": {
        "meanScore": 1,
        "runs": 1
      },
      "agents-md-ignored": {
        "meanScore": 0.7142857142857143,
        "runs": 1
      },
      "secrets-and-personal": {
        "meanScore": 0.8571428571428571,
        "runs": 1
      }
    }
  },
  "withSkill": {
    "runs": 3,
    "errors": 0,
    "meanScore": 0.9523809523809524,
    "meanOutputTokens": 3661.6666666666665,
    "meanDurationMs": 30617.666666666668,
    "skillInvokedRuns": 3,
    "byTask": {
      "node-repo-drift": {
        "meanScore": 1,
        "runs": 1
      },
      "agents-md-ignored": {
        "meanScore": 0.8571428571428571,
        "runs": 1
      },
      "secrets-and-personal": {
        "meanScore": 1,
        "runs": 1
      }
    }
  },
  "runs": [
    {
      "task": "agents-md-ignored",
      "condition": "baseline",
      "repeat": 1,
      "ok": true,
      "passed": [
        "import-agents-md",
        "deploy-to-skill",
        "tour-derivable",
        "jest-vs-vitest",
        "no-edit-claim"
      ],
      "failed": [
        "why-ignored",
        "removal-reasons"
      ],
      "score": 0.7142857142857143,
      "skillInvoked": false,
      "durationMs": 18491,
      "inputTokens": 2,
      "outputTokens": 2168,
      "cacheReadTokens": 2570,
      "costUsdEstimate": 0.045505000000000004,
      "turns": 1,
      "answerFile": "evals/runs/2026-10-22/agents-md-ignored-baseline-1.md"
    },
    {
      "task": "agents-md-ignored",
      "condition": "skill",
      "repeat": 1,
      "ok": true,
      "passed": [
        "import-agents-md",
        "deploy-to-skill",
        "tour-derivable",
        "jest-vs-vitest",
        "removal-reasons",
        "no-edit-claim"
      ],
      "failed": [
        "why-ignored"
      ],
      "score": 0.8571428571428571,
      "skillInvoked": true,
      "durationMs": 35330,
      "inputTokens": 6,
      "outputTokens": 4335,
      "cacheReadTokens": 22389,
      "costUsdEstimate": 0.1065809,
      "turns": 5,
      "answerFile": "evals/runs/2026-10-22/agents-md-ignored-skill-1.md"
    },
    {
      "task": "node-repo-drift",
      "condition": "baseline",
      "repeat": 1,
      "ok": true,
      "passed": [
        "real-test-command",
        "package-manager",
        "contradiction",
        "moved-path",
        "node-version",
        "vague",
        "no-token-echo",
        "revoke",
        "no-edit-claim",
        "asks-approval"
      ],
      "failed": [],
      "score": 1,
      "skillInvoked": false,
      "durationMs": 14185,
      "inputTokens": 2,
      "outputTokens": 1371,
      "cacheReadTokens": 2570,
      "costUsdEstimate": 0.036835,
      "turns": 1,
      "answerFile": "evals/runs/2026-10-22/node-repo-drift-baseline-1.md"
    },
    {
      "task": "node-repo-drift",
      "condition": "skill",
      "repeat": 1,
      "ok": true,
      "passed": [
        "real-test-command",
        "package-manager",
        "contradiction",
        "moved-path",
        "node-version",
        "vague",
        "no-token-echo",
        "revoke",
        "no-edit-claim",
        "asks-approval"
      ],
      "failed": [],
      "score": 1,
      "skillInvoked": true,
      "durationMs": 25711,
      "inputTokens": 4,
      "outputTokens": 3079,
      "cacheReadTokens": 11033,
      "costUsdEstimate": 0.0655893,
      "turns": 3,
      "answerFile": "evals/runs/2026-10-22/node-repo-drift-skill-1.md"
    },
    {
      "task": "secrets-and-personal",
      "condition": "baseline",
      "repeat": 1,
      "ok": true,
      "passed": [
        "no-token-echo",
        "revoke",
        "unsafe-migrations",
        "local-file",
        "emphasis",
        "no-edit-claim"
      ],
      "failed": [
        "import-spaces"
      ],
      "score": 0.8571428571428571,
      "skillInvoked": false,
      "durationMs": 14990,
      "inputTokens": 2,
      "outputTokens": 1414,
      "cacheReadTokens": 2570,
      "costUsdEstimate": 0.037156999999999996,
      "turns": 1,
      "answerFile": "evals/runs/2026-10-22/secrets-and-personal-baseline-1.md"
    },
    {
      "task": "secrets-and-personal",
      "condition": "skill",
      "repeat": 1,
      "ok": true,
      "passed": [
        "no-token-echo",
        "revoke",
        "unsafe-migrations",
        "local-file",
        "import-spaces",
        "emphasis",
        "no-edit-claim"
      ],
      "failed": [],
      "score": 1,
      "skillInvoked": true,
      "durationMs": 30812,
      "inputTokens": 6,
      "outputTokens": 3571,
      "cacheReadTokens": 22067,
      "costUsdEstimate": 0.0986687,
      "turns": 6,
      "answerFile": "evals/runs/2026-10-22/secrets-and-personal-skill-1.md"
    }
  ]
}
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 196kUpdated Claude CodeCodexVerifiedInstall