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 ShipBook/shipbook-mcp --skill audit-logsgit clone --depth 1 https://github.com/ShipBook/shipbook-mcpWrote 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/shipbook/shipbook-mcp/audit-logs)<a href="https://agentmods.dev/skills/shipbook/shipbook-mcp/audit-logs"><img src="https://agentmods.dev/badge/skills/shipbook/shipbook-mcp/audit-logs/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/shipbook/shipbook-mcp/audit-logs"><img src="https://agentmods.dev/badge/skills/shipbook/shipbook-mcp/audit-logs.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 | $0.00045 | $0.01163 |
| Opus 5 | $0.00023 | $0.00581 |
| Sonnet 5 | $0.00009 | $0.00233 |
| Haiku 4.5 | $0.00005 | $0.00116 |
Grade A, and why
audit-logs 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 9d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Logs
Scan the codebase for logging issues — PII exposure, secrets, and sensitive data leaks.
Important: This skill is read-only. It reports findings but does NOT make changes automatically. Always present the report first and ask the user what they want to fix.
Steps
1. Find all log statements
Scan the project for all logging calls. Look for:
- Shipbook:
log.e(),log.w(),log.i(),log.d(),log.v(),Log.e(),Log.w(), etc. - Standard:
console.log,console.error,console.warn,print(),NSLog(),android.util.Log - Framework loggers:
logger.info(),logger.error(),Timber.d(), etc.
2. Check for secrets and sensitive data (high priority)
These must never appear in logs. Flag immediately:
- Passwords and secrets — variable names like
password,secret,token,apiKey,accessToken,refreshToken,authorization - Full credit card numbers — patterns like
\d{4}[-\s]?\d{4}[-\s]?\d{4}[-\s]?\d{4}. Logging the last 4 digits is acceptable (e.g.,**** **** **** 1234), but the full number must never be logged. - SSN, national ID, and passport numbers — variable names like
ssn,socialSecurity,nationalId,idNumber,passportNumber,passport. These are government-issued identifiers used for identity theft and are protected under GDPR, CCPA, and most privacy laws. They must never appear in logs.
These are non-negotiable — present them as critical findings that need immediate attention.
3. Check for personal identifiers (ask user)
These are suggestions — the user may have valid reasons to log them. Present as recommendations and ask before changing:
- Email addresses logged directly — suggest using userId or hashed identifier instead
- Phone numbers — variable names like
phone,phoneNumber,mobile - Physical addresses —
address,street,zipCode,postalCode - Full names —
fullName,firstName,lastNamelogged directly in message strings
Recommendation example:
// Consider replacing direct PII with internal identifiers:
log.i(`User logged in: ${user.email}`)
// Could be:
log.i(`User logged in: ${user.id}`)
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.
- 9d ago First seen · 91 lines · 45 tokens per session scan A 10022419e3a7
audit-logs is a skill published in the GitHub repository ShipBook/shipbook-mcp (2 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 1,163 once invoked, about $0.0002 per session on Opus 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…