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 agentmods add skills/cloudnative-co/claude-code-starter-kit/verification-loopnpx skills add cloudnative-co/claude-code-starter-kit --skill verification-loopgit clone --depth 1 https://github.com/cloudnative-co/claude-code-starter-kitWhat 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 | $0.00019 | $0.00688 |
| Opus 5 | $0.00010 | $0.00344 |
| Sonnet 5 | $0.00004 | $0.00138 |
| Haiku 4.5 | $0.00002 | $0.00069 |
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 2d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification Loop Skill
A comprehensive verification system for Claude Code sessions.
When to Use
Invoke this skill:
- After completing a feature or significant code change
- Before creating a PR
- When you want to ensure quality gates pass
- After refactoring
Verification Phases
Pick the right command for each phase from the project's own configuration (package.json scripts, Makefile, CI workflow, etc.). The commands below are examples, not prescriptions. Summarize long output instead of pasting it verbatim.
Phase 1: Build Verification
Check that the project builds. Examples: npm run build, cargo check, go build ./..., shellcheck -S warning *.sh.
If the build fails, STOP and fix before continuing.
Phase 2: Type Check
Run the project's type checker if it has one. Examples: npx tsc --noEmit (TypeScript), pyright . or mypy . (Python).
Report all type errors. Fix critical ones before continuing.
Phase 3: Lint Check
Run the project's linter. Examples: npm run lint, ruff check ., shellcheck.
Phase 4: Test Suite
Run the project's test suite, with coverage if available. Examples: npm test -- --coverage, pytest --cov, bash tests/run-unit-tests.sh.
Report:
- Total tests: X
- Passed: X
- Failed: X
- Coverage: X% (against the project's target)
Phase 5: Security Scan
Check for leaked secrets in the changes:
- If a dedicated scanner is available (gitleaks, trufflehog), use it.
- Otherwise, follow the bundled security-review skill.
- At minimum, review the added lines of
git difffor credentials, tokens, and keys. Do not report PASS based on a repository-wide grep.
Also check for leftover debug output (e.g., console.log, print) in the changed files.
Phase 6: Diff Review
# Show what changed
git diff --stat
git diff HEAD~1 --name-only
Review each changed file for:
- Unintended changes
- Missing error handling
- Potential edge cases
Output Format
After running all phases, produce a verification report:
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.
- 2d ago First seen · 92 lines · 19 tokens per session scan A 18009036f966
verification-loop is a skill published in the GitHub repository cloudnative-co/claude-code-starter-kit (147 stars, last pushed 8d ago), licensed MIT. It adds 19 tokens to every session and 688 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…