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 SZoloth/skill-pack --skill qagit clone --depth 1 https://github.com/SZoloth/skill-packWrote 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/szoloth/skill-pack/qa)<a href="https://agentmods.dev/skills/szoloth/skill-pack/qa"><img src="https://agentmods.dev/badge/skills/szoloth/skill-pack/qa/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/szoloth/skill-pack/qa"><img src="https://agentmods.dev/badge/skills/szoloth/skill-pack/qa.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 | $0.00066 | $0.01720 |
| Opus 5.5 | $0.00026 | $0.00688 |
| Sonnet 5.5 | $0.00013 | $0.00344 |
| Haiku 4.5 | $0.00007 | $0.00172 |
Grade A, and why
qa 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA — Codex-Powered Change Review
Thorough QA on all changes in the current working tree using Codex as a second pair of eyes. Detects what changed, sends it to Codex for deep review, and presents actionable findings.
When to Use
- After completing implementation work, before committing
- User says "QA", "full QA", "QA my changes", "review with codex"
- Any time you want a second opinion on everything you just built
Process
Step 1: Gather All Changes
# Get the full picture
git status --porcelain
git diff --stat
git diff --cached --stat
# Capture the actual diff (staged + unstaged)
git diff HEAD > /tmp/qa-full-diff.patch
If changes span many files, also get a summary:
git diff HEAD --name-only
Step 2: Build Context
Before sending to Codex, gather context about what was being built:
- What task/feature was being implemented?
- What files were touched and why?
- Any known areas of concern?
Summarize this in 2-3 sentences to give Codex context.
Step 3: Codex Review (diff-based)
Run Codex with the full diff and context. Use -C to point at the repo so Codex can read surrounding code.
cat <<'PROMPT' | codex exec --full-auto -C "$(git rev-parse --show-toplevel)" -o /tmp/qa-codex-review.md -
You are doing a thorough QA review of the following changes. Be critical — find real bugs, not style nits.
## Context
[2-3 sentence summary of what was built]
## Your Review Checklist
1. **Correctness**: Logic errors, off-by-ones, wrong conditions, missing edge cases
2. **Runtime errors**: Null/undefined access, type mismatches, missing imports
3. **Security**: Injection, XSS, secrets in code, unsafe operations
4. **Data integrity**: Race conditions, stale state, missing validation
5. **Integration**: Does this work with the rest of the codebase? Missing wiring?
6. **Regressions**: Could these changes break existing functionality?
7. **Missing pieces**: Anything obviously incomplete or TODO'd?
## Changes to Review
$(git diff HEAD)
For each issue found, report:
- **File:line** — exact location
- **Severity** — P1 (bug/security), P2 (likely problem), P3 (minor concern)
- **Issue** — what's wrong
- **Fix** — how to fix it
If the changes look solid, say so — don't manufacture issues.
PROMPT
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 First seen · 210 lines · 66 tokens per session scan A 8fffd2297f64
qa is a skill published in the GitHub repository SZoloth/skill-pack (14 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,720 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
code-review-checklist
Genera un checklist de revisión de código personalizado para cualquier pull request basado en el lenguaje, tipo de cambio y nivel de riesgo. Úsalo cuando te pidan revisar código, verificar un PR, revisar un pull request o generar un checklist de revisión de código. Produce un checklist enfocado con verificaciones…
pr-description-writer
Redacta una descripción de pull request clara y estructurada a partir de un diff de git, resumen de rama o lista de commits. Úsalo cuando te pidan escribir una descripción de PR, redactar una solicitud de cambios o documentar cambios de código. Produce una descripción con resumen, motivación, cambios realizados, pasos…
resolve-pr-comments
Evaluate, fix, answer, and reply to GitHub pull request review comments and conversation comments. Handles both change requests (fix or skip) and reviewer questions (explain using the rationale recalled from past Claude Code transcripts). Use when the user asks to "resolve PR comments", "fix review comments", "address…
review-code
Review code for bugs, security vulnerabilities, API misuse, consistency issues, simplicity problems, or test coverage gaps and low-value tests by running internal reviews and a peer review in parallel and returning combined findings. Single-concern with a type argument, or full review with no argument. Use when the…
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".
assess-technical-debt
Assess project-wide structural technical debt: complexity hotspots, deprecated API usage, duplication clusters, architecture rot, and low-value tests. Ranks findings by impact and refactor effort into a report at .turbo/technical-debt.md. Use when the user asks to "assess technical debt", "find technical debt"…