What is verification-loop?

A six-step verification routine for changes made on Windows that records either PASS or FAIL before a draft pull request. A pull request is a request for others to review and merge code.

Use it after a feature or refactor and before committing, pushing, or passing the work to another agent setup.

It creates a written check before work is committed, uploaded, or handed to another coding system.

verification-loop — Skill for Claude Code and Codex by frankxai

Install

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.

Any agent

npx skills add frankxai/claude-skills-library --skill verification-loop

Clone the repo

git clone --depth 1 https://github.com/frankxai/claude-skills-library

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/frankxai/claude-skills-library/verification-loop/github.svg)](https://agentmods.dev/skills/frankxai/claude-skills-library/verification-loop)

Your own site

<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/verification-loop"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/verification-loop"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/verification-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 751 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00049	$0.00751
Opus 5.5	$0.00020	$0.00300
Sonnet 5.5	$0.00010	$0.00150
Haiku 4.5	$0.00005	$0.00075

Measured 4d ago against content hash 4e7b85f2b571, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 4d 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.

absorbed/harness/verification-loop/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Estate verification loop

Run the checks in this order. Stop at the first hard failure. Record a result for every check you could not run. A missing tool is not a pass.

Install and build with the repo's package manager. Prefer pnpm when pnpm-lock.yaml is present. Prefer uv for Python. Do not switch the repo to npm because a snippet says npm run build.
Types. For TypeScript, pnpm exec tsc --noEmit from the package that owns the change. For Python, uv run pyright only when that project already uses it.
Lint with the formatter the repo already configured. Do not add a new linter config to make this step green.
Tests the change can affect. State the command, the pass count, and the fail count from the tool output.
Secret scan of the diff for private-key blocks, sk-ant, GitHub token prefixes, and Slack token prefixes. Reading a local env file during development is normal on this machine. Committing one is not.
git diff --stat against the branch you will push. Name the files. Confirm you did not sweep another agent's untracked work.

How to score

Build, types, and tests are hard gates when those tools exist for the files you changed.
A coverage number near 80 percent is a target for product code. It does not block a docs-only change or an ops handover.
console.log left in application code is a warning. It does not fail the build by itself.
If a check cannot run, write NOT RUN and the reason. Do not invent a pass.

Report

VERIFICATION
build:    PASS | FAIL | NOT RUN
types:    PASS | FAIL | NOT RUN
lint:     PASS | FAIL | NOT RUN
tests:    PASS | FAIL | NOT RUN
secrets:  PASS | FAIL | NOT RUN
diff:     <n files>
untracked: <n files>
ready:    YES | NO

Any untracked file makes ready NO. The runner also scans the text of those files. They belong to another session until someone names them in the change.

The person who writes this report does not sign the pull request. Open a draft. A different harness reviews the exact SHA.

Read the full file on GitHub · 52 lines

Files

What ships with it

1 file 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.

PROVENANCE.json 549 B

Changes

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.

4d ago Changed · +7 lines 4e7b85f2b571
5d ago First seen · 45 lines · 49 tokens per session scan A 4b8ddfce989d

Subscribe to this mod's changes

verification-loop is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 751 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 2026-10-11.

Claude Code Git and workflow Productivity Testing ai-tools anthropic prompt-engineering skills

ship

Commit, push, create PR(s), and auto-finalize — full automation pipeline. Handles uncommitted changes and recently created PRs.

dryvist/claude-code-plugins · 30 tokens

release-testing-workflow

Use this skill when you need release-phase QA workflow from T-14 planning to go/no-go and post-release monitoring; triggers include release testing workflow and go/no-go QA.

naodeng/awesome-qa-skills · 40 tokens

iterm2-layout

Configure iTerm2 workspace layouts with TOML. TRIGGERS - iTerm2 layout, workspace tabs, layout.toml, AutoLaunch.

terrylica/cc-skills · 35 tokens

alpha-forge-preship

Alpha Forge quality gates for PR review - RNG determinism, URL validation, parameter validation, manifest sync.

terrylica/cc-skills · 27 tokens

dev-ship

Fechamento de feature — verificação goal-backward antes de declarar pronto. Roda Must-Haves do PLAN.md, executa o demo script, revisa o diff completo procurando bugs e restos (debug logs, TODOs, código morto), passa lente de segurança nos arquivos tocados, escreve SUMMARY.md e arquiva o plano. Use quando o usuário…

calneymgp/solodev · 121 tokens

ai-prompt-regression-testing

Prompt engineering regression test matrix register: baseline outputs, semantic drift thresholds, judge evaluations, and golden dataset.

lingxling/awesome-skills-cn · 28 tokens