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.
git clone --depth 1 https://github.com/vlad-ryzhkov/AI-QA-workshop-feb19Wrote 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/rules/vlad-ryzhkov/ai-qa-workshop-feb19/12-skill-repo-scout)<a href="https://agentmods.dev/rules/vlad-ryzhkov/ai-qa-workshop-feb19/12-skill-repo-scout"><img src="https://agentmods.dev/badge/rules/vlad-ryzhkov/ai-qa-workshop-feb19/12-skill-repo-scout/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/rules/vlad-ryzhkov/ai-qa-workshop-feb19/12-skill-repo-scout"><img src="https://agentmods.dev/badge/rules/vlad-ryzhkov/ai-qa-workshop-feb19/12-skill-repo-scout.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 | $0.00000 | $0.00134 |
| Opus 5 | $0.00000 | $0.00067 |
| Sonnet 5 | $0.00000 | $0.00027 |
| Haiku 4.5 | $0.00000 | $0.00013 |
Grade A, and why
12-skill-repo-scout 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 12d 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.
What it actually says
SKILL: REPO SCOUT
TRIGGER
Use this when entering a new backend repository (Go) before writing tests to catalog API surface, infrastructure and test coverage.
LOGIC SOURCE
EXECUTE the instruction set defined in: .claude/skills/repo-scout/SKILL.md
@.claude/skills/repo-scout/SKILL.md
KEY CONSTRAINT
- Do NOT use for QA projects — use /init-project for those.
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.
- 12d ago First seen · 18 lines · 134 tokens per session scan A 2bc45cad8afb
12-skill-repo-scout is a cursor rule published in the GitHub repository vlad-ryzhkov/AI-QA-workshop-feb19 (25 stars, last pushed 6mo ago), licensed Unlicense. It costs nothing until one of its globs matches a file; then it loads 134 tokens. 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 cursor rules, from other repositories
cursor-rule-example
SKILL: Generate Ktor/JUnit API Tests (use for /api-tests).
validate-contracts
Assert data shape consistency across system boundaries — live API responses against JSON Schema, key-set comparison across layers, data shape validation for migrations and exports. Catches silent data corruption before deploy.
manual-review.backend
The obligations, predicates, evidence schema, failure handling, and review timing in this source are shared. Concrete browser, dispatch, question, filesystem, and command mechanics are target-native and MUST come from the selected runtime fragment at the matching adapter path. A fragment declares only the capability…
websockets
Real-time over WebSockets end to end, SocketRouter and wsEmit on the backend, socketSdk with useListener and useEmitter on the client, auth on upgrade, testing.
testing
Testing with @iobroker/testing and Mocha.
api-design
API design guidelines — REST principles, GraphQL patterns, versioning, pagination, error handling, documentation, security, caching, and testing. Applied when designing or reviewing API endpoints.