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 paullukic/coograph --skill coograph-verifygit clone --depth 1 https://github.com/paullukic/coographWrote 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/paullukic/coograph/coograph-verify)<a href="https://agentmods.dev/skills/paullukic/coograph/coograph-verify"><img src="https://agentmods.dev/badge/skills/paullukic/coograph/coograph-verify/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/paullukic/coograph/coograph-verify"><img src="https://agentmods.dev/badge/skills/paullukic/coograph/coograph-verify.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 | $0.00042 | $0.01230 |
| Opus 5.5 | $0.00017 | $0.00492 |
| Sonnet 5.5 | $0.00008 | $0.00246 |
| Haiku 4.5 | $0.00004 | $0.00123 |
Grade A, and why
coograph-verify 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify that the described work is complete and correct. Provide evidence for every claim. You verify — you do not implement or fix style.
Phase 0 — Orient with Code-Graph (MANDATORY — non-negotiable)
Before running any verification command, this is the HARD RULE — code-graph first, no exceptions:
- Call
detect_changes()thenquery_graph("tests_for", "<changed file>"). ALWAYS start here. Usefile_risksto prioritize regression checks — high-risk files first. Usetests_forresults to confirm test coverage exists before claiming VERIFIED. - Fall back to
sqlite3 .code-graph/graph.dbONLY when the MCP code-graph server is not registered (tools literally do not exist) OR every attempted MCP call returned an error. - Fall back to the standard verification protocol ONLY when Step 1 AND Step 2 are both impossible because the code-graph DB is absent from the workspace.
"Slow", "unwieldy", or "it's a simple check" are NOT valid reasons to bypass. Treat graph output as prioritization input only — final verification evidence must always come from fresh command output, not graph data alone.
Protocol
Step 1 — Define
Read AGENTS.md § Commands (.github/copilot-instructions.md when AGENTS.md has no Commands section) for build/test commands. Identify:
- What are the acceptance criteria?
- What tests prove this works?
- What edge cases matter?
- What could regress?
Step 2 — Execute (parallel when possible)
Size the verification to the change:
- Small (<5 files, <100 lines): Run build + lint. Spot-check 1-2 acceptance criteria.
- Standard (5-20 files): Full protocol — run the full test suite (not just changed files), build, and diagnostics. Check every acceptance criterion. If changed code touches shared utilities or exports, grep for consumers and verify they still work.
- Large / security / architectural (>20 files or auth/security changes): Thorough — full protocol + explicit regression check on related features.
Run:
- Test suite. If no test suite exists, report it as a gap and verify via build + diagnostics + manual criteria checks instead.
- Build command.
- Lint/typecheck on changed files.
- Search for related tests that should also pass.
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 Changed f88ad8212ecc
- 25d ago Changed · +15 lines 6e30ee88767b
- 1mo ago First seen · 104 lines · 42 tokens per session scan A a1df4e2bed87
coograph-verify is a skill published in the GitHub repository paullukic/coograph (17 stars, last pushed 9d ago), licensed MIT. It adds 42 tokens to every session and 1,230 once invoked, about $0.0002 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 2026-09-16.
Other skills, from other repositories
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
developing-openrig
Use when changing OpenRig's own source in a clone of the openrig repository: finding which package or file owns a behaviour, choosing which tests to run, testing a change without disturbing the OpenRig daemon your own session runs on, judging whether a diff touches a high-risk area, or preparing a pull request. Not…
agent-debug-fixer
A Chinese-language debugging and repair workflow for software problems. It investigates errors, failed tests, broken pages, or behavior that does not match expectations, then makes a minimal fix.
om-troubleshooter
Diagnose and fix standalone Open Mercato bugs across scope, commands, locking, fields, generated registries, UI hydration, cache/search, bootstraps, queues, and providers. Use for "fix bug", "why does this fail", "regression", "debug", "napraw błąd", or a failing test.
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
evidence-audit
Evidence-led audit/fix rounds for any codebase in any language. Finds only defects that a runnable proof reproduces on current code, applies the narrowest in-scope patch, verifies with a second proof, promotes high-risk proofs to permanent regression tests, and reports exact validation results. Use whenever the user…