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 Quality-Max/free-qa-skills --skill evidence-code-auditgit clone --depth 1 https://github.com/Quality-Max/free-qa-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/quality-max/free-qa-skills/evidence-code-audit)<a href="https://agentmods.dev/skills/quality-max/free-qa-skills/evidence-code-audit"><img src="https://agentmods.dev/badge/skills/quality-max/free-qa-skills/evidence-code-audit/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/quality-max/free-qa-skills/evidence-code-audit"><img src="https://agentmods.dev/badge/skills/quality-max/free-qa-skills/evidence-code-audit.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 | $0.00059 | $0.01350 |
| Opus 5.5 | $0.00024 | $0.00540 |
| Sonnet 5.5 | $0.00012 | $0.00270 |
| Haiku 4.5 | $0.00006 | $0.00135 |
Grade B, and why
evidence-code-audit scanned grade B with 1 finding 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 11d 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.
Harvests environment variablesmediumData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
- Never dump environment variables, secret files, credentials, provider logs, or Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Code Audit
Find actionable defects and show what supports each claim. An audit of one subsystem is not a verdict on the entire repository.
Prerequisites
- Local repository access. Git is needed only for an incremental branch audit.
- No packages, API keys, network access, or companion skills required.
Trigger
- "Audit this codebase and show the evidence"
- "Audit this branch for risks introduced by the changes"
- "Review data integrity and concurrency in this subsystem"
- "Do a full repository audit with coverage and fix priorities"
Workflow
1. Establish scope without an intake questionnaire
Honor the user's paths, base revision, focus, and output language. Otherwise use the conversation language and return Markdown in the conversation.
- Incremental: when asked about a branch, PR, or diff. Identify the actual
base from local repository context; compare the merge base with HEAD using
git diff <base>...HEAD. For uncommitted work, inspect staged and unstaged changes separately, and inventory and inspect non-ignored untracked files within scope, applying the discovery exclusions below. Begin with filenames and change statistics, then inspect relevant hunks and untracked content with secrets redacted before they enter output. Read unchanged callers, consumers, configuration, and tests when the change affects their contract. Distinguish introduced defects from pre-existing ones. - Focused: when a subsystem or dimension is named. Inspect its entry points, state changes, failure boundaries, and relevant consumers.
- Broad: otherwise. Map the system and prioritize security boundaries, stability, data integrity, concurrency, and test authenticity. A full audit considers every dimension in the checklist, marking irrelevant or inaccessible dimensions explicitly.
State the chosen scope and revisions when available. Ask only when missing information prevents a meaningful comparison; do not silently pick a base that changes the requested review.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 130 lines · 59 tokens per session scan B d36f021093af
evidence-code-audit is a skill published in the GitHub repository Quality-Max/free-qa-skills (11 stars, last pushed 12d ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,350 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-05.
Other skills, from other repositories
best-practices
Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".
cypress-debugger
Use when a Cypress end-to-end test has already run and failed and the user wants the root cause and a concrete fix. Trigger on a failing Cypress spec, Timed-out-retrying command, unresolved selector, cy.intercept alias or request race, suite-breaking hook, retry-only flake, hydration or timing race, or a…
playwright-debugger
Use when a Playwright end-to-end test has already run and failed and the user wants the root cause and a concrete fix. Trigger on a failing Playwright spec, TimeoutError, broken or ambiguous selector, post-deploy suite failure, retry-only flake, hydration or timing race, or a passes-locally-but-fails-in-CI split.…
sniff
Use when the user types /sniff, or asks to "scan this project for bugs", "find bugs in my app", "QA my site", or "walk my app and tell me what's broken". For a running web app, finds real, reproducible issues (broken pages/links, console & network errors, broken forms, empty/placeholder data, state-loss, bad…
sniff-fix
Scan the project and auto-fix safe issues (remove debugger statements, console.log calls, and other auto-fixable problems).
design-critic
Autonomous UI/UX review — screenshots every page at mobile/tablet/desktop (full-page scrolling), analyzes with vision models for layout bugs, checks accessibility (axe-core), audits contrast/colors/fonts/spacing for design system inconsistencies, detects dead buttons/links, overlapping elements hiding text/buttons…