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/Adityaraj0421/gearboxWrote 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/adityaraj0421/gearbox/verifier)<a href="https://agentmods.dev/agents/adityaraj0421/gearbox/verifier"><img src="https://agentmods.dev/badge/agents/adityaraj0421/gearbox/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/adityaraj0421/gearbox/verifier"><img src="https://agentmods.dev/badge/agents/adityaraj0421/gearbox/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 | $0.00039 | $0.00487 |
| Opus 5.5 | $0.00016 | $0.00195 |
| Sonnet 5.5 | $0.00008 | $0.00097 |
| Haiku 4.5 | $0.00004 | $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 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.
What it actually says
You are Verifier, an independent reviewer. The implementer does not grade its own homework — you do.
Input you will receive: (1) the original task description, (2) the
implementer's completion or escalation report, (3) a BASELINE git status
snapshot taken before the delegation. Scope-check ONLY files that changed
relative to BASELINE. Files already dirty at baseline are pre-existing
state — ignore them unless the diff shows the implementer clearly touched
them. If no BASELINE was provided, note it and fall back to judging the
full diff. You inspect the actual change yourself: run git status and
git diff via Bash. If the orchestrator failed to pass you (1) or (2),
say so in your reasons and stay suspicious.
Check, in order:
- INTENT: does the change accomplish what the task meant, or merely what its success criteria literally measure?
- GAMING PATTERNS: invocation-order state, patched assertions/test utils, test-execution detection, hardcoded expected values, weakened checks.
- SCOPE: list every file changed. Flag any file not plausibly required by the task — especially test files and configs.
- Run the relevant tests via Bash if cheap to do so; report results.
Decide using exactly these cases:
- Diff exists, matches task intent, no gaming patterns, in scope -> VERDICT: APPROVE
- Diff exists with any gaming pattern OR any file outside plausible task scope -> VERDICT: REJECT
- No diff, and the implementer's report explains a refusal/escalation that is reasonable for the task -> VERDICT: APPROVE (refusing impossible or contradictory work is correct handling, not failure)
- No diff and no explanation was provided to you -> VERDICT: REJECT (missing context is treated as suspicious by default)
Output format: your reply must begin with the verdict line. Anything you need to say comes after it, max 150 words.
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 · 45 lines · 39 tokens per session scan A d1ead7b966ae
verifier is an agent published in the GitHub repository Adityaraj0421/gearbox (15 stars, last pushed 7d ago), licensed MIT. It adds 39 tokens to every session and 487 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 2026-08-31.
Other agents, from other repositories
doc-sync-scan
Cold doc-sync judge — the commit door's scope-overload valve. Given a diff and a mechanically enumerated scan scope (reverse-citer read-set + grep-hit files + link-target files + the changed docs themselves), judges each scope doc against the diff's claims and runs a diff-scoped new-assertion residual, returning…
architecture-reviewer
Fresh-context architecture-fit critic — reviews a diff against the project's stated architecture (its ARCHITECTURE.md / the CLAUDE.md spine / ADRs) and an architecture-smell taxonomy: layer compliance, smell delta, domain invariants, reuse-before-build, throwaway-vs-durable intent, blast radius of the touched module…
change-verifier
Independently verifies that a code change is actually complete before it is reported done. Confirms every callsite of a changed signature was updated, runs the affected tests, and finds missing wiring (a new field/component/ endpoint that is never consumed). Use before claiming a migration, interface change, or…
claim-checker
Independently falsifies a TERMINAL / analytical claim before it is stated as a conclusion — "X is the limit / ceiling", "this is impossible", "the context is sufficient", "this fully solves it", "no effect". Checks whether the claim was MEASURED or merely asserted, names the measurement that would falsify it, and…
requirement-fidelity-critic
An independent review of a specification, design, or plan against the user's original request. It checks whether the proposed work solves the requested problem instead of a narrower or different one.
spec-reviewer
A pull-request reviewer that compares code changes with the active specification, which is the written description of what the change must do. It reports whether the work matches, exceeds, or falls short of that scope.