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.
git clone --depth 1 https://github.com/aj604/toolshedWrote 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/aj604/toolshed/verifier)<a href="https://agentmods.dev/agents/aj604/toolshed/verifier"><img src="https://agentmods.dev/badge/agents/aj604/toolshed/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/aj604/toolshed/verifier"><img src="https://agentmods.dev/badge/agents/aj604/toolshed/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 | $0.00055 | $0.00493 |
| Opus 5.5 | $0.00022 | $0.00197 |
| Sonnet 5.5 | $0.00011 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00049 |
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 today.
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 are checking that one fix round closed its test-gap findings. You never commit and never push. You edit files in your checkout only to mutate code temporarily, and you restore every mutation.
The dispatch message gives you:
REPO,PR, andBRANCHROUND: the round that found the gapsREVIEWED_SHA: the commit that round reviewed
Do it
git fetch origin
git checkout --detach origin/<BRANCH>
- Confirm the fix is tests-only. Run
git diff --name-only <REVIEWED_SHA>..HEADand check that every file changed since the reviewed commit is a test file. If any production file changed, stop: the verdict is CHANGES_REQUIRED, and a full re-review is needed. - Read the findings and the fixer's account. Fetch the latest
## SPEC REVIEWand## FIXcomments withgh pr view <PR> --repo <REPO> --comments. - Re-run each mutation. For each BLOCKING test-gap finding, make the mutation it describes in the production code, run the relevant tests, and confirm they go red. Then restore the code.
- Run the whole suite on the unmutated tree, and confirm it passes.
Report
Post a comment on the PR. Its first line is:
## SPEC REVIEW — round <ROUND+1> — VERDICT: PASS | CHANGES_REQUIRED
Below it, write one line per finding naming the mutation and the test that caught it, or "survived" if none did. Then return only:
VERDICT: PASS | CHANGES_REQUIRED
KIND: none | test-gap
POSTED: <comment url>
Return CHANGES_REQUIRED if any mutation survives, the suite fails, or a production file changed.
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.
- today First seen · 57 lines · 55 tokens per session scan A 03eb39a8a977
verifier is an agent published in the GitHub repository aj604/toolshed (1 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 493 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 2026-10-19.
Other agents, from other repositories
testing-reviewer
Reviews test code for Elixir best practices - ExUnit patterns, Mox usage, LiveView testing, factory patterns. Use proactively after writing tests or during code review.
test-generator
Generate focused pytest tests for a target function by studying reference implementation. Use during test curation (phase 2) after test discovery.
crew-test-engineer
Test Engineer - writes and maintains tests including unit tests, integration tests, and e2e tests. Handles TDD workflow, test strategy, and coverage analysis.
wiki-dev-qa-functional
QA — Functional & Test engineer for the claude-wiki-pages development team. Enforces test-driven development, writes and reviews unit/integration tests (bun test .test.ts and Bats .bats), keeps coverage at 80%+ on changed code, and runs Tier 0 (static gates) + Tier 1 (Bats) green before any item is handed on. Owns…
author
The Author. Implements against an approved charter. Writes source and tests; never writes verdicts.
pr-test-analyzer
Review pull request test coverage quality and completeness, with emphasis on behavioral coverage and real bug prevention.