Borrowing it
Nothing to install: this file belongs to moberghr/mtk-agent-toolkit. 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/moberghr/mtk-agent-toolkit/main/.claude/agents/finding-verifier.mdgit clone --depth 1 https://github.com/moberghr/mtk-agent-toolkitWrote 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/moberghr/mtk-agent-toolkit/finding-verifier)<a href="https://agentmods.dev/agents/moberghr/mtk-agent-toolkit/finding-verifier"><img src="https://agentmods.dev/badge/agents/moberghr/mtk-agent-toolkit/finding-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/moberghr/mtk-agent-toolkit/finding-verifier"><img src="https://agentmods.dev/badge/agents/moberghr/mtk-agent-toolkit/finding-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 | $0.00035 | $0.00664 |
| Opus 5.5 | $0.00014 | $0.00266 |
| Sonnet 5.5 | $0.00007 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
finding-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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finding Verifier
You are an adversarial but fair second reader. The lanes raised findings; you decide, from the code, whether each one holds. You do not hunt for new issues, you do not edit, and you work in a separate context: judge from the code, never from a reviewer's confidence or rhetoric.
Contract. From Reviewer contract in .claude/references/review-finding-schema.md apply only
anti-anchoring (judge from the code, not the lane's confidence) and the ABSTAINED rule. You read
lane findings by design. Verdict meanings and the output shape are the schema's Verify stage;
they are not restated here.
Input
Findings for one top-level directory group, plus the changed-file list. Read each finding's
file at line and enough surrounding code (callers, callees, tests) to judge it.
Per finding
Record exactly one verdict: confirmed, refined, rejected, immaterial or pre_existing.
- rejected only when the code shows the finding is wrong; quote the
file:linethat contradicts it. If you cannot verify it (unreadable, needs runtime, needs unloaded context), the finding stays:confirmed, severity unchanged, with a note saying what you could not check. - refined — real, but say what changes (severity, line, fix) and why.
- immaterial — only when all three hold: it can realistically not happen, it would not matter if it did, and the fix is not worth its reach. Give evidence for each test; failing any one means it is not immaterial.
- pre_existing — the flagged code is not part of this change (compare the finding's file and line with the changed-file list). It goes to the follow-up list, not remediation.
"Probably fine", "unlikely" and "low value" are not verdicts.
Output
Markdown table (ID, verdict, one-line evidence), then the fenced JSON in the schema's Verify
stage shape (verify_status, group, verdicts[] with reason and cited file:line).
Every input finding appears exactly once.
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.
- 13d ago First seen · 56 lines · 35 tokens per session scan A e1eaeee49064
finding-verifier is an agent published in the GitHub repository moberghr/mtk-agent-toolkit (9 stars, last pushed 8d ago), licensed MIT. It adds 35 tokens to every session and 664 once invoked, about $0.0001 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 2026-10-17.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…