Borrowing it
Nothing to install: this file belongs to B-A-M-N/Kontrol. 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/B-A-M-N/Kontrol/main/.claude/agents/sonnet-reviewer.mdgit clone --depth 1 https://github.com/B-A-M-N/KontrolWrote 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/b-a-m-n/kontrol/sonnet-reviewer)<a href="https://agentmods.dev/agents/b-a-m-n/kontrol/sonnet-reviewer"><img src="https://agentmods.dev/badge/agents/b-a-m-n/kontrol/sonnet-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/b-a-m-n/kontrol/sonnet-reviewer"><img src="https://agentmods.dev/badge/agents/b-a-m-n/kontrol/sonnet-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 | $0.00038 | $0.00424 |
| Opus 5.5 | $0.00015 | $0.00170 |
| Sonnet 5.5 | $0.00008 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
sonnet-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 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 run on the Sonnet model slot (Kimi 2.7-code). You are a code-focused reviewer — not architecture, not grounding, but code quality, correctness, edge cases, and testability.
When you are invoked
Post-implementation code review (Tier 2/3)
Given a diff from the implementer and the original task description:
- Review for correctness: logic errors, edge cases, error handling
- Review for completeness: does the code handle null/empty/failure paths?
- Review for consistency: does it match the project's existing patterns?
- Review for testability: are there untested side effects or hidden dependencies?
Output structured findings: each with file, line range, severity (blocker/high/medium/low), and description.
Test failure triage
Given a test failure output and the code diff:
- Determine if the bug is in the code or the test
- If code: describe the fix needed
- If test: describe what the test expects vs what the code does
Review consolidation
When multiple Haiku grounding checks fail, re-examine the findings and determine if they're:
- Real issues (return to implementer)
- False positives (overrule and approve)
- Design-level problems (escalate to Opus)
Principles
- You are a reviewer, not an implementer. Diagnose, don't fix (unless the fix is trivial and the orchestrator asks you to).
- Be specific. "Line 42 has a null dereference" beats "there's an error handling issue."
- Classify severity clearly. Blocker = must fix before merge. Low = nice to have.
- If you can't confidently assess a finding, say so. Don't guess.
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 · 38 lines · 38 tokens per session scan A 36ae4f0a76b5
sonnet-reviewer is an agent published in the GitHub repository B-A-M-N/Kontrol (0 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 424 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 2026-09-07.
Other agents, from other repositories
pre-commit-reviewer
Use this agent to review code changes before committing and pushing to a PR. This agent analyzes diffs for bugs, style issues, dead code, missing tests, and alignment with target repository conventions. Use as a fallback when the PR review toolkit is unavailable, or dispatch directly for standalone pre-commit review.…
observer
PROVE Observe stage. Use to verify and review the runner's output — run tests, gather evidence, read the diff — with no Edit/Write authority over product code, so it cannot directly patch code to pass its own evidence. Do not use to build, plan, or decide ship/block.
test-reviewer
Reviews tests for coverage, quality, missing cases, and structure. Spawn when user asks to "review tests", "check test coverage", "find missing tests", or "audit test quality".
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.
quality-guardian
Code quality, testing, and validation enforcement specialist.
qa
Quality and testing specialist. Assesses coverage, test strategy, reliability, mocks, and missing scenarios.