A local verification routine that runs a project's formatting, linting, type-checking, and test commands. It covers Python and frontend code and can also check generated documentation and other affected test suites.

Use it before commits or pull requests to check Ruff, ESLint, TypeScript, Prettier, Vitest, generated documentation, and relevant test suites.

It finds errors before a change is committed or sent for review. Running the same checks locally makes failures easier to diagnose than discovering them later in CI, the service that tests changes automatically.

How r0shi/harborclerk configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to r0shi/harborclerk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/r0shi/harborclerk/main/.claude/skills/verify/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/r0shi/harborclerk

Made for: Claude Code.

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/r0shi/harborclerk/verify/github.svg)](https://agentmods.dev/skills/r0shi/harborclerk/verify)

Your own site

<a href="https://agentmods.dev/skills/r0shi/harborclerk/verify"><img src="https://agentmods.dev/badge/skills/r0shi/harborclerk/verify/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/r0shi/harborclerk/verify"><img src="https://agentmods.dev/badge/skills/r0shi/harborclerk/verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 300 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	$0.00029	$0.00300
Opus 5.5	$0.00012	$0.00120
Sonnet 5.5	$0.00006	$0.00060
Haiku 4.5	$0.00003	$0.00030

Measured 1mo ago against content hash b3b0d44bb0fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify 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 1mo 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.

.claude/skills/verify/SKILL.md · 35 lines

What it actually says

Verify

Run the full local CI check suite and report results. All commands run from the repository root.

Steps

Run Python checks:

uv run ruff check . 2>&1 && uv run ruff format --check . 2>&1

Run frontend checks:

(cd frontend && npm run lint 2>&1 && npm run type-check 2>&1 && npm run format:check 2>&1 && npm test -- --run 2>&1)

Report a summary:
- Python lint: pass/fail (show errors if any)
- Python format: pass/fail
- ESLint: pass/fail (show errors, ignore warnings)
- TypeScript: pass/fail (show errors)
- Prettier: pass/fail (show files that need formatting)
- Vitest: pass/fail (show failing tests)
- Overall: PASS if all green, FAIL if any errors

CI additionally verifies generated docs (uv run python -m scripts.gen_docs --check) and runs the test suites; run those too when the change touches tools, routes, models, stages, compose services, or tested code.

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.

1mo ago First seen · 35 lines · 29 tokens per session scan A b3b0d44bb0fd

Subscribe to this mod's changes

verify is a skill published in the GitHub repository r0shi/harborclerk (3 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 300 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 2026-09-17.

CI and CD DevOps and cloud LLM Testing docker document-intelligence hybrid-search local-first macos

verify next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
verifyr0shi/harborclerk	Skill	3	2d ago	MIT	A	29	Claude Code
memobasemaximskorohod/memobase	Skill	22	17d ago	MIT	A	25	Claude Code, Codex
pulselinggen/skills	Skill	3	2d ago	Apache-2.0	A	132	Claude Code
shared-memorylinggen/skills	Skill	3	2d ago	Apache-2.0	A	64	Claude Code
djlinggen/skills	Skill	3	2d ago	Apache-2.0	A	101	Claude Code
healthlinggen/skills	Skill	3	2d ago	Apache-2.0	A	91	Claude Code
lingjinglinggen/skills	Skill	3	2d ago	Apache-2.0	A	65	Claude Code

harborclerk: Skill for Claude Code