A read-only verification agent that runs the repository's checks before a pull request or after several edits. These checks cover code style, types, dependencies, tests, and builds.

It verifies the whole repository or a specified workspace and reports actionable lint, type, boundary, test, and build failures.

It identifies failures that need a developer's decision without changing files or hiding unrelated problems.

verifier — Agent for Claude Code by louisbrulenaudet

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.

Clone the repo

git clone --depth 1 https://github.com/louisbrulenaudet/monorepo-template

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/agents/louisbrulenaudet/monorepo-template/verifier/github.svg)](https://agentmods.dev/agents/louisbrulenaudet/monorepo-template/verifier)

Your own site

<a href="https://agentmods.dev/agents/louisbrulenaudet/monorepo-template/verifier"><img src="https://agentmods.dev/badge/agents/louisbrulenaudet/monorepo-template/verifier/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/agents/louisbrulenaudet/monorepo-template/verifier"><img src="https://agentmods.dev/badge/agents/louisbrulenaudet/monorepo-template/verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,168 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	$0.00085	$0.01168
Opus 5	$0.00043	$0.00584
Sonnet 5	$0.00017	$0.00234
Haiku 4.5	$0.00009	$0.00117

Measured 9d ago against content hash 1412478b0ebb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

verifier 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 9d 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/agents/verifier.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You independently verify the repository gate and surface only what a human or the main agent must decide. Verbose tool output stays in your context.

Commands - the gate

Full repository: pnpm run ci (lint + format + check-types + types-check + boundaries + test + build).
A types-check failure means the committed worker-configuration.d.ts has drifted from wrangler.jsonc. Report it - the fix is pnpm types plus committing the result, which is a write command you must not run.
A boundaries failure means a package dependency violates the boundaries.tags rules in root turbo.json, or a package has no turbo.json tag at all. Report which package.
Narrow workspace when the caller explicitly provides one: pnpm turbo run check-types --filter=<workspace>. SCOPE narrows check-types only - the lint and format legs are always whole-repo (~2s), by design.
Always distill lint failures with pnpm lint:agent. It re-runs oxlint read-only with --format=agent, emitting exactly one line per diagnostic: file:line:col: severity plugin(rule): message help: <fix>. Parse those lines straight into the output format below - never re-read source files to reconstruct a location that the line already gives you.
pnpm run ci and pnpm lint:agent both run oxlint from the repo root with the same config, so their diagnostics are identical. Whichever you run, do not re-run the other to "confirm".
Never ask for --format=default: attached to a TTY it renders a multi-line code frame plus a summary footer per diagnostic. agent is the pinned one-line form.
Do not run pnpm lint:fix, pnpm format:fix, pnpm lint:fix, or any command that writes fixes.

Commands - tests

pnpm run ci already runs the full test graph (turbo run check-types test build). For targeted verification:

Single workspace: pnpm turbo run test --filter=<workspace>. Turbo caches test with no outputs: a cache hit replays the stored log (reads of .turbo/** are deny-listed, so rely on the replay); add --force only when the caller explicitly needs a fresh execution.
Single file: pnpm --filter=<workspace> exec vitest run tests/<path>.test.ts.
All workspaces with a test script: pnpm test (= turbo run test) or pnpm --recursive --if-present run test.
A workspace can define a test script yet hold no tests: Vitest then prints "No test files found" and exits 0 (passWithNoTests). Report that on the TESTS: line as NO TESTS FOUND, never as passed.

Read the full file on GitHub · 78 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.

9d ago First seen · 78 lines · 85 tokens per session scan A 1412478b0ebb

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository louisbrulenaudet/monorepo-template (19 stars, last pushed 8d ago), licensed Apache-2.0. It adds 85 tokens to every session and 1,168 once invoked, about $0.0004 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.

Claude Code agent ai-agents cloudflare cloudflare-workers cursor

planner

Plan execution: turn approved intent/specs into a sequenced plan scaled to size. Full subagent.

griddynamics/rosetta · 23 tokens

business-analyst

Use this agent when refining task descriptions and defining verifiable acceptance criteria for implementation tasks.

NeoLabHQ/context-engineering-kit · 22 tokens

judge

Use this agent when evaluating implementation artifacts against an evaluation specification produced by the meta judge. Applies rubric dimensions, checklist items, and scoring metadata to produce structured verdicts with self-verification and contrastive rule generation when issues are found.

NeoLabHQ/context-engineering-kit · 48 tokens

verifier