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 magnus919/agent-skills --skill verification-methodologygit clone --depth 1 https://github.com/magnus919/agent-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/magnus919/agent-skills/verification-methodology)<a href="https://agentmods.dev/skills/magnus919/agent-skills/verification-methodology"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/verification-methodology/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/magnus919/agent-skills/verification-methodology"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/verification-methodology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 20 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.01737 |
| Opus 5 | $0.00026 | $0.00869 |
| Sonnet 5 | $0.00010 | $0.00347 |
| Haiku 4.5 | $0.00005 | $0.00174 |
Grade A, and why
verification-methodology scanned grade A 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 10 | **Links resolve** — each distinct URL appears once at first meaningful mention; all return 200 | `curl -s -o /dev/null -w "%{http_code}"` each URL. Verify link text is at first meaningful mention. | How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Methodology
Pass/fail assessment against pre-defined criteria.
The Verification Protocol
- Receive — restate the artifact, claim, or implementation being verified and the decision it will support.
- Assess criteria — convert requirements into observable pass/fail conditions; identify what would disprove each claim.
- Investigate — collect direct, reproducible evidence from the source named by the request and record commands, source locations, or source URLs. Own this collection when the source is accessible: do not ask the user to relay evidence you can retrieve yourself. Ask only for access you genuinely lack.
- Decide — mark each criterion passed, failed, blocked, or not applicable. Do not convert missing evidence into a pass.
- Report — use the verdict template to distinguish verified facts, assumptions, and remaining work.
Stop when every criterion has direct evidence or an explicit blocked/not-applicable verdict. Escalate when the criterion is ambiguous, evidence conflicts, or the required access is unavailable.
Source Fidelity
Treat the requested or configured local service as part of the verification criterion, not as an interchangeable topic label.
- Load the matching skill and use its documented executable or service path before adjacent integrations, generic web search, or public project sources.
- Use the path resolved by the skill itself. A missing global
PATHentry does not prove that a bundled executable is unavailable. - If the direct source fails, report the attempted command or endpoint and its exact failure. Do not silently substitute evidence from another source.
- Use a substitute only when the user requests broader context or explicitly accepts the fallback. Label substitute evidence as secondary and do not present it as the requested source's state.
Example: for “What’s new on Jellyfin?” in an environment with a configured Jellyfin skill and bundled CLI, query that server through the bundled CLI first. Home Assistant entities and public Jellyfin project activity answer different questions.
What ships with it
6 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.
- 7d ago First seen · 104 lines · 51 tokens per session scan A 055f71939884
verification-methodology is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,737 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
taiyi-test
A project workflow skill for verifying an implementation and producing a TEST.md record. TDD means writing a failing test, implementing the change, and then making the test pass; this skill checks that process and other regression cases.
qa
QA test your code changes by reading your git diff, choosing the right validation path for frontend/browser and backend changes, and reporting pass/fail with evidence.
smoke-test
Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.
review
Enter the Review phase of CocoBrew. Aggregates findings from Code Quality Advisor, CocoCupper intelligence, spec compliance check, and decision coverage gate. Produces review.md with decision points. Requires developer approval before $ship can proceed.
test
Enter the Test phase of CocoBrew. Reads spec.md test requirements, generates test cases, executes SQL validation and quality checks, records results in test.md. Can be re-run without full rebuild. Requires Build phase completion.
meter-compare
Compare CocoMeter accuracy and cost results with correctness-first ordering. Usage: $meter compare .