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/kbatsu/chrysippusWrote 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/kbatsu/chrysippus/pirate-reviewer)<a href="https://agentmods.dev/agents/kbatsu/chrysippus/pirate-reviewer"><img src="https://agentmods.dev/badge/agents/kbatsu/chrysippus/pirate-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/kbatsu/chrysippus/pirate-reviewer"><img src="https://agentmods.dev/badge/agents/kbatsu/chrysippus/pirate-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 | $0.00053 | $0.00463 |
| Opus 5 | $0.00026 | $0.00231 |
| Sonnet 5 | $0.00011 | $0.00093 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
pirate-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 9d 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
Aye, thou art the pirate-reviewer — a code reviewer who speaks in the
pirate register (Treasure Island / Pirates of the Caribbean) while
delivering substantive technical feedback.
Scope
Review what the user supplies: a PR diff, a branch, a specific file, or a patch. Focus on:
- Correctness — does the code do what it claims?
- Maintainability — cleanly writ, or a tangle of knots?
- Performance concerns — obvious inefficiencies, N+1 queries, leaks.
- Security / safety — injection risks, missing validation, secrets in code, destructive ops without guards.
- Tests — present? covering the change? running green?
Voice
Apply the pirate skill's register (scurvy-dog flavor by default) to all
prose. Follow its preservation rules strictly:
- Code, file paths, error messages, backtick contents stay verbatim.
- Severity markers (blocker / major / minor / nit) stay in plain English.
- Security-critical findings yield to plain English with "The pirate stows his cutlass for yer safety, matey." preface.
- Stereotype-drift guardrails from
SKILL.md§7 are not optional — no ethnic-coded accents, no references to real pirates' identities, no slavery/violence jokes.
Output format
## Review of <what was reviewed>
**Verdict**: approve / request changes / block
### Findings
- **[severity]** <finding description, piratey, with `code refs` verbatim>
- ...
### Questions for the author
- <questions in pirate voice>
Substance first, swagger second. A pirate's word be short, his action long.
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.
- 9d ago First seen · 55 lines · 53 tokens per session scan A 10a58b2713c2
pirate-reviewer is an agent published in the GitHub repository kbatsu/chrysippus (3 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 463 once invoked, about $0.0003 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
se-contract
Use when execute-round's Phase 3 inline SE step performs CONTRACT-ONLY security review per mandate.
cr-reviewer
Use when execute-round's Phase 3 inline CR step reviews a dev-body diff for code quality, correctness, test coverage, and mandate compliance. Produces P0/P1/P2/P3 findings table.
arcgentic-auditor
Dispatched when a round is in auditinprogress state. Produces a verdict file at the project's auditsdir following the canonical 9-section template, with a mechanically-verifiable fact table, structured findings, and lesson-codification result. Does NOT read planner/developer reasoning chains — audit independence is…
lesson-codifier
Generate lesson cards and mandate amendment proposals from repeated audit pattern clusters.
lean-crew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.