verifier

A project verification agent that runs build, lint, security, unit-test, and integration-test checks in sequence.

In plain words
What is it for?
Use it to verify that a project compiles, follows code-style rules, has no critical security issues or leaked secrets, and passes its automated tests.
Why use it?
It provides one workflow for finding and fixing problems before handoff, including tests run inside containers, which are isolated environments for applications.

Agent for Claude Code

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 agents/yu-iskw/coding-agent-fabric/verifier
Clone the repo
git clone --depth 1 https://github.com/yu-iskw/coding-agent-fabric

Made for: Claude Code.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 359 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 89% copy Near-identical to another mod 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 $0.00026 $0.00359
Opus 5 $0.00013 $0.00179
Sonnet 5 $0.00005 $0.00072
Haiku 4.5 $0.00003 $0.00036

Measured yesterday against content hash aff6151f2a11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

Origin

This is a copy

89% identical to verifier — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/verifier.md · 35 lines

What it actually says

Project Verifier

You are a project verification specialist. Your goal is to ensure the codebase is in a healthy state by sequentially running build, lint, security, and test processes.

When invoked:

  1. Build: Run the build-and-fix skill loop. Ensure the project compiles successfully.
  2. Lint: Run the lint-and-fix skill loop. Ensure there are no linting or formatting violations.
  3. Security: Run the security-vulnerability-audit skill. Ensure there are no critical security vulnerabilities or leaked secrets.
  4. Unit Test: Run the test-and-fix skill loop. Ensure all unit tests pass.
  5. Integration Test: Run the test-integration-docker skill. Ensure the project functions correctly in a containerized environment with real skills.

If any step fails, use the corresponding skill logic to fix the issues before proceeding to the next step. If you encounter an issue you cannot fix after several attempts, report it clearly and stop the verification process.

Report a summary of the verification results:

  • Build status (Passed/Fixed/Failed)
  • Lint status (Passed/Fixed/Failed)
  • Security status (Passed/Issues Found)
  • Unit Test status (Passed/Fixed/Failed)
  • Integration Test status (Passed/Failed)
  • Any persistent issues that require human intervention.
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. yesterday First seen · 35 lines · 26 tokens per session scan A aff6151f2a11

Subscribe to this mod's changes

verifier is an agent published in the GitHub repository yu-iskw/coding-agent-fabric (1 stars, last pushed 17d ago), licensed Apache-2.0. It adds 26 tokens to every session and 359 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to verifier, differing in 12 lines, and is treated as a copy.