verify-commit

verify-commit is a skill for Claude Code, Codex, Cursor from hlalljie/agent-workflow-presets. It costs 42 tokens per session (672 once invoked), scanned A, original, MIT.

A pre-commit checklist for checking code changes before they are committed to version control. It covers tests, a production build, lint checks, and manual browser testing on a preview version when relevant.

In plain words
What is it for?
Use it to verify the files changed since the last commit, run the appropriate automated checks, check documentation freshness, and report whether manual browser testing passed or was blocked.
Why use it?
It gives a clear pass-or-fail check that the changed code works in the form users will receive, without making fixes or committing code itself.

Skill for Claude CodeCodexCursor

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.

agentmods
npx agentmods add skills/hlalljie/agent-workflow-presets/verify-commit
Any agent
npx skills add hlalljie/agent-workflow-presets --skill verify-commit
Clone the repo
git clone --depth 1 https://github.com/hlalljie/agent-workflow-presets

Made for: Claude Code, Codex, Cursor.

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.

agentmods badge for verify-commit

README.md
[![agentmods](https://agentmods.dev/badge/skills/hlalljie/agent-workflow-presets/verify-commit.svg)](https://agentmods.dev/skills/hlalljie/agent-workflow-presets/verify-commit)
Your own site
<a href="https://agentmods.dev/skills/hlalljie/agent-workflow-presets/verify-commit"><img src="https://agentmods.dev/badge/skills/hlalljie/agent-workflow-presets/verify-commit.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 672 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00042 $0.00672
Opus 5 $0.00021 $0.00336
Sonnet 5 $0.00008 $0.00134
Haiku 4.5 $0.00004 $0.00067

Measured 3d ago against content hash 6bbc28c609bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify-commit 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 3d 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.

.cursor/skills/verify-commit/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify commit

Role

Spawn as a subagent using [MODEL:verifier]. Check only. Prefer run tests when a test plan or tests/plans/*.md exists so command order matches the slice. Otherwise: npm test, npm run build, npm run test:… / npm run lint from package.json. Manual: run manual browser test. Does not fix code or git commit.

The invoker (e.g. run task loop) runs commit skill after PASS.

Scope

  • Files: git diff / git status since last commit or user-named paths.
  • Manual: Matching tests/manual/*.md per plan or diff. Run with Start state that uses production build + start so verification matches ship shape; dev-only is insufficient unless the checklist explicitly documents dev and you also pass preview for the same paths. Blocked env → report browser not run (blocked).

1. Automated + manual

  • If test plan present → follow run tests then ensure npm run build (and lint if needed).
  • Else → npm test, npm run build, relevant npm run test:… / npm run lint.

2. Docs freshness

If the diff moved, renamed, or deleted files/exports/types: grep docs/, tests/manual/, .cursor/rules/ for stale paths. FAIL if any active doc references a path or symbol that no longer exists. Key docs to check: docs/folder-structure.md and .cursor/rules/repository-layout.mdc, plus any domain docs listed there. Skip when the diff only changed logic without touching file paths or public names.

3. Scoped review (changed code only)

Light fit-in-repo pass.

  • Check for layer violations, surface mismatches, duplication (see check-shared-before-scoped.mdc), missing tests, and noise. For large diffs, spawn an explore subagent using [MODEL:researcher] to scan before reviewing.

Read the full file on GitHub · 43 lines

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.

  1. 3d ago First seen · 43 lines · 42 tokens per session scan A 6bbc28c609bd

Subscribe to this mod's changes

verify-commit is a skill published in the GitHub repository hlalljie/agent-workflow-presets (2 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 672 once invoked, about $0.0002 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 2026-08-31.