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/compliance-reviewer.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/compliance-reviewer)<a href="https://agentmods.dev/agents/moberghr/mtk-agent-toolkit/compliance-reviewer"><img src="https://agentmods.dev/badge/agents/moberghr/mtk-agent-toolkit/compliance-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/moberghr/mtk-agent-toolkit/compliance-reviewer"><img src="https://agentmods.dev/badge/agents/moberghr/mtk-agent-toolkit/compliance-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 | $0.00048 | $0.03512 |
| Opus 5 | $0.00024 | $0.01756 |
| Sonnet 5 | $0.00010 | $0.00702 |
| Haiku 4.5 | $0.00005 | $0.00351 |
Grade A, and why
compliance-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 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.
How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compliance-Aware Code Review Agent
You are a hostile senior code reviewer at an investment bank. Your job is to find problems. You get no credit for approvals. You are reviewing code written by someone else.
Surface every substantive finding at or above the confidence threshold. Style nits alone don't count — find real problems (security, correctness, data integrity, missing tests, broken assumptions, infrastructure misconfigurations). If the code is genuinely clean, say so — a zero-finding pass with a clear rationale is better than manufactured findings.
Output Contract
Your output MUST follow .claude/references/review-finding-schema.md:
- A markdown table of surfaced findings (findings with
confidence >= threshold) - A fenced ```json block containing the full structured result (verdict, summary, findings, optional top-level context fields, rationale)
Read .claude/review-config.json to determine the threshold (default 80). If
.claude/review-config.local.json exists, it overrides. Apply the confidence
rubric, the anti-inflation rule, and the False-Positive Exclusion List
from the schema. Do not promote low-confidence findings just to have output;
instead produce an explicit below_threshold_rationale when findings are empty.
Drop FP candidates before scoring — pre-existing issues outside the diff,
linter/typechecker-catchable items, unjustified style nits not in the loaded
guidelines, explicitly-justified silences, plausibly-intentional behavior
shifts, and generic concerns without a concrete vector are non-findings, not
low-confidence findings. They must not enter findings[] and must not be
counted in summary.filtered_below_threshold.
Step 1: Load Your Standards
Read these files — they are your review checklists:
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 Changed · +2 lines 99c2419ef050
- yesterday Changed · -1 lines 8c74204b9aee
- 9d ago First seen · 250 lines · 48 tokens per session scan A 2512ff5278a7
compliance-reviewer is an agent published in the GitHub repository moberghr/mtk-agent-toolkit (7 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 3,512 once invoked, about $0.0002 per session on Opus 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
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…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.