Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mhylle/claude-skills-collectionnpx agentmods add skills/mhylle/claude-skills-collection/verification-loopWrote 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/mhylle/claude-skills-collection/verification-loop)<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/verification-loop"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/verification-loop/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/mhylle/claude-skills-collection/verification-loop"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/verification-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
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 →
- high Privilege Escalation · line 387 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Tool Misuse · line 239 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
- medium MCP Rug Pull · line 535 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 543 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- low Excessive Agency · line 506 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00067 | $0.04441 |
| Opus 5 | $0.00034 | $0.02220 |
| Sonnet 5 | $0.00013 | $0.00888 |
| Haiku 4.5 | $0.00007 | $0.00444 |
Grade A, and why
verification-loop 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 10d 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 — 557 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Loop
A systematic 6-check verification framework that validates implementation quality across multiple dimensions: build, types, lint, tests, security, and diff review. Catches issues early, ensures code compiles, type-checks, passes linting, runs tests, has no security issues, and contains no unintended changes.
Terminology: this skill uses "Checks" (Check 1–6). Don't confuse with "Phases" (plan phases) or "Steps" (implement-phase steps).
Design philosophy
Defense in depth — each check catches a different category of issue:
| Check | Catches | Why it matters |
|---|---|---|
| Build | Syntax errors, missing deps, bundling issues | Code must compile to run |
| Types | Type mismatches, null safety, interface violations | Type safety prevents runtime errors |
| Lint | Style violations, code smells, potential bugs | Consistent, maintainable code |
| Tests | Logic errors, regressions, broken contracts | Functional correctness |
| Security | Secrets, debug code, vulnerable patterns | Production safety |
| Diff | Unintended changes, scope creep, leftover code | Change discipline |
Fail fast — checks are ordered by detection speed. Build errors appear in seconds; security scans take longer. Fast checks first provide rapid feedback on common issues.
Project-agnostic — detect project type automatically, apply the matching tooling. Node.js, Python, Go, Rust, and mixed-language projects all work.
Idempotent — running the loop multiple times produces the same result. Each check passes or fails deterministically based on codebase state.
When to use
Automatically invoked by implement-phase as Step 2 (Exit Condition Verification), before integration testing, after implementation subagents complete.
Manually invoked for:
- Validating changes before committing
- Checking code quality after refactoring
- Pre-merge verification
- Reproducing CI/CD failures locally
Don't use for:
- Reading or analyzing code (no changes made)
- Running exploratory tests (use the test runner directly)
- Checking a single file (use individual tools)
What ships with it
4 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.
- 10d ago First seen · 557 lines · 67 tokens per session scan A 13bf14fb3d49
verification-loop is a skill published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 7d ago), licensed MIT. It adds 67 tokens to every session and 4,441 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 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.