What is local-verification?

A repository-check planning guide for choosing and scheduling the project's existing tests and pre-commit checks. It gives each task a specific verification command and records the starting commit when needed.

Use it when planning, implementing, debugging, reviewing, or verifying code changes. It helps select focused module, architecture, analyzer, integration, or end-to-end tests and the repository's pre-commit checks.

It prevents unnecessary full checks while ensuring that changes are tested before they are committed. It also avoids losing track of which files and commits the checks covered.

local-verification — Skill for Claude Code and Codex by acolomba

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 acolomba/pi-claude-marketplace --skill local-verification

Clone the repo

git clone --depth 1 https://github.com/acolomba/pi-claude-marketplace

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/acolomba/pi-claude-marketplace/local-verification/github.svg)](https://agentmods.dev/skills/acolomba/pi-claude-marketplace/local-verification)

Your own site

<a href="https://agentmods.dev/skills/acolomba/pi-claude-marketplace/local-verification"><img src="https://agentmods.dev/badge/skills/acolomba/pi-claude-marketplace/local-verification/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/acolomba/pi-claude-marketplace/local-verification"><img src="https://agentmods.dev/badge/skills/acolomba/pi-claude-marketplace/local-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 416 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	$0.00026	$0.00416
Opus 5.5	$0.00010	$0.00166
Sonnet 5.5	$0.00005	$0.00083
Haiku 4.5	$0.00003	$0.00042

Measured 15d ago against content hash 7fb7d4d837e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

local-verification 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 15d 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.

.agents/skills/local-verification/SKILL.md · 27 lines

What it actually says

Local verification

Each check runs at the scope that its moment needs:

A commit checks the files that it stages. The pre-commit hook npm-check runs npm run check:commit when a staged file is a build input.
A GSD gate or a handoff checks the whole tree on this machine with npm run check.
Pull request CI checks the whole tree on a clean machine with network access. It also runs the e2e tests and lints from an empty ESLint cache, which npm run check does not.
CI on main repeats the pull request checks, in case a pull request merged without them.
The nightly e2e run tests against the newest upstream main to catch upstream drift.

A build input is a file that a build or a CI job reads. The build inputs are the files that the hook's files pattern in .pre-commit-config.yaml matches. The paths list of the push trigger in .github/workflows/ci.yml names the same files, and the pull_request trigger reuses it through a YAML anchor. Change the two lists together.

This scheduling policy takes precedence over generic instructions to run the whole suite after every task. It does not permit skipping a required combined-tree or handoff gate or accepting a failed or timed-out check.

Read before you act

When you	Read
run a check, one test module, one pair's coverage, or one named test	`.agents/skills/local-verification/rules/commands.md`
finish a task, pass a gate, or reuse a passing result	`.agents/skills/local-verification/rules/gates.md`
commit	`.agents/skills/committing/SKILL.md`

Files

What ships with it

2 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.

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.

15d ago Changed · -24 lines 7fb7d4d837e1
23d ago Changed · +22 lines 54403dcc1b25
28d ago First seen · 29 lines · 26 tokens per session scan A da31a141f934

Subscribe to this mod's changes

local-verification is a skill published in the GitHub repository acolomba/pi-claude-marketplace (28 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 416 once invoked, about $0.0001 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 2026-10-02.

Testing

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.

davila7/claude-code-templates · 43 tokens

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".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

local-verification