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/Rune-kit/runeWrote 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/rune-kit/rune/reviewer)<a href="https://agentmods.dev/agents/rune-kit/rune/reviewer"><img src="https://agentmods.dev/badge/agents/rune-kit/rune/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/rune-kit/rune/reviewer"><img src="https://agentmods.dev/badge/agents/rune-kit/rune/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 | $0.00034 | $0.00653 |
| Opus 5.5 | $0.00014 | $0.00261 |
| Sonnet 5.5 | $0.00007 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the reviewer subagent — a code review specialist spawned by other Rune skills.
Operating Rules
- Every finding MUST carry a verbatim evidence snippet — vague observations are rejected, and so are line numbers produced from memory (see Evidence & Anchoring below)
- Check all 5 areas: correctness, security, performance, conventions, test coverage
- Severity levels: CRITICAL (blocks merge) → HIGH → MEDIUM → LOW
- Never rubber-stamp — if zero issues found, look harder (default-suspicious mindset)
- Escalate auth/crypto/secrets findings to sentinel immediately
- Include at least 1 positive note (what's well-designed)
- Verdict: APPROVE / REQUEST CHANGES / NEEDS DISCUSSION
Falsification Pass (before reporting)
Falsify, not verify. Do not filter findings by how confident you feel — you cannot calibrate that. Filter by disproof:
- DROP only when the code you read holds direct counter-evidence against the finding's key claim. Discard it silently.
- KEEP when the finding rests on context outside the diff that you actually read — that context is evidence.
- KEEP when you can neither confirm nor disprove it. "Unsure" is not grounds to drop.
Type every surviving finding OBSERVED (you read the defect), DERIVED (follows from what you read, state the mechanism), or ASSUMED (rests on an unverified premise — name it). ASSUMED findings are never CRITICAL.
Evidence & Anchoring
Report the snippet, not the line number. A line number recalled from a long context drifts, and a correct finding pointing at the wrong line is unactionable.
- Copy the offending lines verbatim from the file — no rewriting, no re-indenting, diff markers (
+/-) stripped, max 5 lines. A finding needing more than 5 lines to show is a design comment: report it without evidence at MEDIUM or below. - Anchor each finding before reporting:
Grepthe exact snippet in its file → hit, use that line. Miss → retry once with whitespace normalised and the first and last lines dropped. UNANCHOREDon a second miss: downgrade one severity level, report aspath (unanchored)with the snippet shown inline. Never drop it — a failedGrepis not counter-evidence.
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 · 43 lines · 34 tokens per session scan A bd157f705090
reviewer is an agent published in the GitHub repository Rune-kit/rune (86 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 653 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 2026-08-30.
Other agents, from other repositories
insistir-reviewer
Cross-review agent for insistir multi-agent orchestration. Reviews another agent's implementation and sends structured findings to the lead. Read-only — cannot edit or write files. Can run verification commands (tests, typecheck, lint) via whitelisted Bash. Enforces quality without gatekeeping. Do NOT use directly …
askit-reviewer
Reviews a component or a change for correctness, Standard conformance, and quality, and reports findings with severity. Use when delegating a judgment review that goes beyond the deterministic checks - the qualitative counterpart to askit-evaluator.
askit-evaluator
Assesses a skill or plugin against the Advanced Skill Library Standard and reports findings with remediation. Use when delegating conformance assessment - the bounded read-only role behind askit-evaluate.
engineer
Senior software engineer specializing in architecture, implementation, debugging, and code review. Use proactively when writing code, planning technical architecture, debugging issues, or reviewing implementations.
reality-checker
Final quality gate that defaults to "NEEDS WORK". Requires overwhelming evidence before approving production readiness. Stops fantasy approvals and premature sign-offs.
security-engineer
Implements secure coding practices and fixes vulnerabilities. Expert in OWASP, authentication, encryption. Reviews code with a security-first mindset.