Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mostafa-drz/claude-skills --skill audit-skillsgit clone --depth 1 https://github.com/mostafa-drz/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mostafa-drz/claude-skills/audit-skills)<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/audit-skills"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/audit-skills/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/audit-skills"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/audit-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.02279 |
| Opus 5.5 | $0.00023 | $0.00912 |
| Sonnet 5.5 | $0.00012 | $0.00456 |
| Haiku 4.5 | $0.00006 | $0.00228 |
Grade A, and why
audit-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Skills
Audit personal Claude skills for consistency, best practices, and up-to-date standards.
Command routing
Check $ARGUMENTS:
help→ display help then stop--fix [skill-name]→ auto-fix issues (see Fix mode)--verbose [skill-name]→ show full details for every check (not just failures)<skill-name>→ audit a single skill- empty → audit all skills
Help
Doctor — Audit personal Claude skills for health and consistency
Usage:
/audit-skills Audit all personal skills
/audit-skills <skill-name> Audit a single skill
/audit-skills --fix Auto-fix all skills
/audit-skills --fix <skill-name> Auto-fix a specific skill
/audit-skills --verbose Full detail for every check
/audit-skills help This help
Checks performed:
Manifest Does the skill follow SKILLS_GUIDE.md conventions?
Frontmatter Are all required/recommended fields present and correct?
Content Is the skill under 500 lines? Are references bundled?
Tools Are allowed-tools minimal? Any duplicates? Any contradictions?
UX Does it have help/config/reset? First-time detection? Memory?
Docs Is the description third-person with trigger keywords?
Security Does disable-model-invocation match the side-effect profile?
Upstream Does it follow latest official Claude skills documentation?
Output:
[PASS] Check passed
[WARN] Non-critical suggestion
[FAIL] Violates manifest or best practice
[INFO] Informational note
Example output:
/slack-to-ticket
[PASS] Third-person description
[PASS] disable-model-invocation: true (has side effects)
[WARN] SKILL.md is 120 lines — fine, but has inline examples that could be bundled
[FAIL] Missing help subcommand
[PASS] Preferences memory pattern present
Step 1: Load references
Local manifest
Read ~/.claude/skills/SKILLS_GUIDE.md — this is the source of truth for local conventions.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +7 lines · +58 tokens per session d914b20a9050
- 1mo ago First seen · 261 lines · 0 tokens per session scan A 9711d7fbcef4
audit-skills is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 2,279 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
rudder-data-graphs
Produces Data Graph YAML from RETL sources for Audiences. Use when designing Data Graphs, mapping RETL to entities/events, or assessing customer fit for Audiences.
rudder-typer-workflow
Generates type-safe SDKs (Swift/Kotlin) from tracking plans with compile-time validation. Use when generating type-safe event tracking code from tracking plans using RudderTyper.
rudder-instrumentation-planning
Designs event taxonomies and instrumentation strategies from business requirements. Use when designing event taxonomy from scratch or restructuring existing instrumentation strategy.
rudder-instrumentation-debugging
Diagnoses and fixes validation errors, schema issues, and instrumentation problems. Use when debugging validation errors, schema issues, or instrumentation problems.
rudder-ai-events-verify
Verifies RudderStack AI events locally: captures what an instrumented app or MCP server sends, validates it against the AI events v0.3 schema, and checks joins, counts, identity and content. Use when testing AI events, or when AI or MCP events look wrong or missing.