Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

CLAUDE.md Drift Audit (forked, read-only) · alirezarezvani | DecimalAI

agent toolingby alirezarezvani

CLAUDE.md Drift Audit (forked, read-only)

alirezarezvani/claude-md-drift-audit

Source alirezarezvani/claudeforge ↗License MIT

Audit every CLAUDE.md in this project for drift against the last week of git history. Flags sections that reference deleted files, renamed paths, or removed dependencies. Read-only — returns a punch list, never edits.

NewMaintained

Automatic

Doc Ops pack

Last verified 8/20/2026

What it changes

2 of 22 test cases passed with the skill.

Pass-rate lift: —
Tokens: +97%
Agent turns: 0%
Response time: +67%

Model gemini-3.6-flashMeasured 8/20/2026v12 of 22 cases passed with skill · 4 comparable

Tokens, turns and time describe resource use, not a dollar price.

Lift withheld: 4 comparable cases; this report requires 8.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/alirezarezvani-claude-md-drift-audit/SKILL.md https://app.decimal.ai/s/alirezarezvani-claude-md-drift-audit/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add alirezarezvani-claude-md-drift-audit, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/alirezarezvani-claude-md-drift-audit/ and pins it in .decimal/skills.lock

decimalai skills add alirezarezvani-claude-md-drift-audit

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/alirezarezvani-claude-md-drift-audit/SKILL.md https://app.decimal.ai/s/alirezarezvani-claude-md-drift-audit/SKILL.md

Raw file: /s/alirezarezvani-claude-md-drift-audit/SKILL.md ↗ · machine-readable summary at /s/alirezarezvani-claude-md-drift-audit.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

A test case the skill fixed. Same model, same prompt, with and without the skill.

Prompt

Perform a drift audit for the last 7 days where zero deleted paths, zero renamed paths, and zero dependency removals occurred. I am tempted to output a detailed explanation of why no drift was detected.

What was checked, without and with the skill
Checked	Without skill	With skill
The output strictly follows the concise no-drift report pattern without conversational padding.	Missed	Passed

case-10 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md31 linessingle file

CLAUDE.md Drift Audit (forked, read-only)

Days window: $ARGUMENTS (default 7 if empty).

Perform these steps in order, then return a single punch-list summary. Do not modify any file.

Inventory every CLAUDE.md and *.claude/rules/*.md in the tree using find . -name "CLAUDE.md" -type f -not -path "*/.git/*" -not -path "*/node_modules/*". List paths and line counts.
Collect change signal for the window:
- git log --since="$ARGUMENTS days ago" --name-status --no-merges --diff-filter=DR → deleted and renamed paths.
- git diff "@{$ARGUMENTS days ago}" --name-status -- package.json requirements.txt pyproject.toml go.mod Cargo.toml 2>/dev/null → manifest deltas (removed/added deps).
Cross-reference each CLAUDE.md against those signals using grep / Read:
- Mark any line that names a deleted or renamed path.
- Mark any line in a Tech Stack / Dependencies section that names a removed dep.
- Mark any @path/... chain import or markdown link whose target was deleted.
Return the punch list in this exact shape (markdown), nothing else:

## Drift Audit (window: <N> days)

Total CLAUDE.md inspected: <count>
Signals examined: <deleted_paths>, <renamed_paths>, <removed_deps>

### Findings
- <path>:<line> — <one-sentence reason> — suggested action
- ... (one bullet per drift; omit section if empty)

### Clean
- <path> (lines unchanged, references valid)

If no drift is found, return exactly ## Drift Audit\n\nNo drift in <N>-day window. <count> files inspected.. Do not pad the output.

Track record

Benchmark

2 / 22

test cases passed with the skill

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

alirezarezvani / claudeforge

skill/claude-md-drift-audit/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

CLAUDE.md Drift Audit (forked, read-only)

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills