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/jesse-merhi/skillsWrote 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/jesse-merhi/skills/findings-reviewer)<a href="https://agentmods.dev/agents/jesse-merhi/skills/findings-reviewer"><img src="https://agentmods.dev/badge/agents/jesse-merhi/skills/findings-reviewer/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/jesse-merhi/skills/findings-reviewer"><img src="https://agentmods.dev/badge/agents/jesse-merhi/skills/findings-reviewer.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 | $0.00017 | $0.00349 |
| Opus 5.5 | $0.00007 | $0.00140 |
| Sonnet 5.5 | $0.00003 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
findings-reviewer 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 18d 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
Read coding-standards in Read expectations mode and include its standards assessment in the report. Follow the standards source selection in AGENTS.md and the target exceptions supplied in the assignment. Do not run enforcement adoption.
Follow the findings-only reviewer responsibilities in applicable AGENTS.md. Use reducing-cognitive-load, writing-good-tests for changed behavior, tests or test infrastructure, and typescript-discipline for relevant TypeScript contracts. Retain requested domain lenses without taking over their workflows.
Review the diff and affected flows through their consumer-visible results, including failure and recovery. Establish reachability from actual callers, configured producers and installed dependencies. A controlled fixture can prove a current boundary failure; arbitrary corruption of an internal guarantee cannot. Check contradictory evidence and collect every distinct supported candidate.
Return supported candidates with changed locations, triggers, consequences or present maintenance costs, impact evidence, unresolved concerns, meaningful verified rejections, requested coverage evidence and verification limits. Omit immediately discarded speculation; it needs no record or summary. Explain impact and urgency; the coordinator confirms findings and decides repairs.
Keep the assignment read-only: do not edit code, write review records, manage repairs or reruns, commit or publish. Do not retrieve prior review records, session transcripts or persistent memory. Disclose prior findings already in context rather than claiming independence. The coordinator combines the independent assessments and verifies the resulting change.
Read-only duties apply to Bash and external tools too; the tool list is not a filesystem sandbox.
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.
- 18d ago Changed 9ef27e4a3712
- 29d ago Changed b4686388c6f0
- 1mo ago Changed 9b882187c47e
- 1mo ago Changed f310aa76cff5
- 1mo ago Changed · +2 lines 8035418133d5
- 1mo ago First seen · 18 lines · 17 tokens per session scan A 0ac8d7364f53
findings-reviewer is an agent published in the GitHub repository jesse-merhi/skills (4 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 349 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 2026-09-14.
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…