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 vlad-ryzhkov/ai-context-engineering-for-qa --skill agents-checker-skillgit clone --depth 1 https://github.com/vlad-ryzhkov/ai-context-engineering-for-qaWrote 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/vlad-ryzhkov/ai-context-engineering-for-qa/agents-checker-skill)<a href="https://agentmods.dev/skills/vlad-ryzhkov/ai-context-engineering-for-qa/agents-checker-skill"><img src="https://agentmods.dev/badge/skills/vlad-ryzhkov/ai-context-engineering-for-qa/agents-checker-skill/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/vlad-ryzhkov/ai-context-engineering-for-qa/agents-checker-skill"><img src="https://agentmods.dev/badge/skills/vlad-ryzhkov/ai-context-engineering-for-qa/agents-checker-skill.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 | $0.00051 | $0.02988 |
| Opus 5 | $0.00026 | $0.01494 |
| Sonnet 5 | $0.00010 | $0.00598 |
| Haiku 4.5 | $0.00005 | $0.00299 |
Grade A, and why
agents-checker 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 yesterday.
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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/agents-checker — AI Agent Setup Validator
SILENT MODE: Execute all validation phases silently. Do not output intermediate findings or progress per file. Only the final audit report and SKILL COMPLETE block go to chat.
Status Reporting: After Phase 2 (qa_agent.md checks) and Phase 3 (each agent file), emit a single-line JSON progress:
{"phase": N, "files_scanned": N, "issues_found": N}
Type: Audit Utility Category: QA Setup / Compliance
Checks that the project's Claude agent files comply with the standards produced by /init-agent. Validates structure, required sections, cross-references, and absence of stale placeholders.
When to Use
- After manually editing
qa_agent.mdor any file in.claude/agents/ - After adding a new agent
- Before running
/update-ai-setup - As a pre-flight check in the QA pipeline
Scope
| Target | Path |
|---|---|
| QA Lead profile | .claude/qa_agent.md |
| Agent files | .claude/agents/*.md |
| Skill cross-refs | .claude/skills/*/SKILL.md frontmatter |
Input Parameters
| Parameter | Required | Default | Description |
|---|---|---|---|
auto_fix |
No | true |
When true, auto-repairs safe deterministic issues after full audit and logs each change with rationale. Unsafe issues (missing files, role-specific content) are always flagged only. |
Workflow
Phase 1: File Existence
Check each required file is present:
.claude/qa_agent.md.claude/agents/auditor.md.claude/agents/sdet.md
If any file is missing → 🔴 CRITICAL. Stop and report. Do not proceed to Phase 2.
Phase 2: qa_agent.md Structure
Load .claude/skills/init-agent/references/qa-agent-template.md as the reference standard.
Verify qa_agent.md contains all required sections:
| Check | Rule | Severity |
|---|---|---|
## Core Mindset present |
Must have 3–5 principles listed | 🔴 CRITICAL |
## Anti-Patterns (BANNED) present |
Table with ≥ 5 rows | 🔴 CRITICAL |
## Quality Gates present |
Must contain Before Commit + Before PR sections | 🟠 MAJOR |
## Cross-Skill Protocol present |
Must reference /spec-audit → /api-isolated-tests → /api-tests |
🟠 MAJOR |
| No placeholders | Grep for [xxx] pattern — none allowed |
🟠 MAJOR |
| Anti-patterns match role | qa_agent.md is an Orchestrator — anti-patterns must cover orchestration failures (e.g. micro-management, blind approval, silent looping). Universal code-level patterns (Thread.sleep, assertEquals) belong in agent files, NOT here. | 🟡 MINOR |
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.
- yesterday First seen · 253 lines · 51 tokens per session scan A 1a07bf9b356d
agents-checker is a skill published in the GitHub repository vlad-ryzhkov/ai-context-engineering-for-qa (6 stars, last pushed yesterday), licensed Unlicense. It adds 51 tokens to every session and 2,988 once invoked, about $0.0003 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 2026-09-09.
Other skills, from other repositories
detecting-broken-object-property-level-authorization
Detect and test for OWASP API3:2023 Broken Object Property Level Authorization vulnerabilities including excessive data exposure and mass assignment attacks.
Phone Use
MUST Load this skill for ANY task that involves GUI interaction or device control — opening apps, tapping, typing, scrolling, swiping, Back/Home/Recents, reading the screen, or any workflow that touches on-screen content. Load this even when the user does not explicitly mention the device — if the task implies a GUI…
release-new-version
Use when the user wants to release a new Zafiro version — drafting bilingual release notes, deciding the next version number, bumping app/build.gradle.kts, tagging, and publishing to GitHub (main repo, optionally the Xposed repo).
audit-brand
Audits and evolves brand positioning, voice consistency, and messaging for an existing brand. Works across personal brands and DTC/ecommerce store brands. Runs a structured audit across positioning, voice, visual direction, and content pillars, then produces a scorecard with specific fix recommendations. Also develops…
compliance-check
Assesses US regulatory compliance likelihood for any consumer product before listing for US sale. Accepts a CJ product PID/URL, Amazon ASIN, or product name/description as input. Classifies the product into a regulatory category (children's toys, electronics, cosmetics, supplements, pet products, apparel…
stress-test
Three-phase strategic decision analysis combining verbalized sampling (Stanford arXiv 2510.01171), customizable analytical lenses, and a structured decision brief. Surfaces tail-distribution insights — the non-obvious, suppressed analyses that mode-collapsed prompting misses. Adapted from @alexprompter's Model Council…