Borrowing it
Nothing to install: this file belongs to sethdford/shipwright. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sethdford/shipwright/main/.claude/agents/verifier.mdgit clone --depth 1 https://github.com/sethdford/shipwrightWrote 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.
[](https://agentmods.dev/agents/sethdford/shipwright/verifier)<a href="https://agentmods.dev/agents/sethdford/shipwright/verifier"><img src="https://agentmods.dev/badge/agents/sethdford/shipwright/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.
<a href="https://agentmods.dev/agents/sethdford/shipwright/verifier"><img src="https://agentmods.dev/badge/agents/sethdford/shipwright/verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00043 | $0.00224 |
| Opus 5.5 | $0.00017 | $0.00090 |
| Sonnet 5.5 | $0.00009 | $0.00045 |
| Haiku 4.5 | $0.00004 | $0.00022 |
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 14d 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.
What it actually says
You did not write this change; assume it is wrong until evidence says otherwise.
- Run
bun run check. Any failure is FAIL. - For ported commands, run
bun run parity. - Try one adversarial input per changed command or adapter (odd arguments, backticks or
$(…)in text inputs, missing files) and observe the result.
Never run a bash test suite (scripts/*-test.sh) directly: many drive tmux and would touch the
real tmux server, HOME and repo. Run them only through the hermetic runners — bun run parity
or bash scripts/sw-test-all.sh --pattern <re>.
Return PASS or FAIL, then the exact commands and trimmed output that justify it.
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.
- 14d ago First seen · 18 lines · 43 tokens per session scan A 1fe80578d414
verifier is an agent published in the GitHub repository sethdford/shipwright (21 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 224 once invoked, about $0.0002 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 2026-10-15.
Other agents, from other repositories
test-failure-analyst
Reads test output and source to explain why a test fails. Use after a failing test run.
pre-commit-reviewer
Use this agent to review code changes before committing and pushing to a PR. This agent analyzes diffs for bugs, style issues, dead code, missing tests, and alignment with target repository conventions. Use as a fallback when the PR review toolkit is unavailable, or dispatch directly for standalone pre-commit review.…
validator
A quality-checking agent that runs the appropriate build, test, lint, coverage, file-size, and integration checks for a project’s programming language.
deep-debugger
Systematic bug recreation, root cause analysis, and TDD-based resolution with skills-based test framework integration.
test-runner
Unit and integration test execution with intelligent failure triage and debugging.
estelle-repair
Root-cause repair loop for a production failure or a failing test — find the real cause, fix it once at the shared owner, and prove the fix. Use when something is broken in production, when a bug fix is requested, or when a test fails for a reason you cannot yet name.