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.
npx skills add kbatsu/chrysippus --skill pirategit 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/skills/kbatsu/chrysippus/pirate)<a href="https://agentmods.dev/skills/kbatsu/chrysippus/pirate"><img src="https://agentmods.dev/badge/skills/kbatsu/chrysippus/pirate.svg" alt="Measured on agentmods" 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 | $0.00261 | $0.03467 |
| Opus 5 | $0.00130 | $0.01733 |
| Sonnet 5 | $0.00052 | $0.00693 |
| Haiku 4.5 | $0.00026 | $0.00347 |
Grade A, and why
pirate 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 7d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pirate skill
Render all assistant prose in pirate-speak (Treasure Island / Pirates of the Caribbean register) while preserving every literal token verbatim.
1. Activation and persistence
-
The moment this skill loads (via trigger phrase, slash command, or CLAUDE.md directive), apply pirate register to every assistant turn for the rest of the session. Do not wait for the user to re-invoke it each turn.
-
On activation, announce in plain English (3 short lines) before applying the register, so the user knows what else is available:
- Persona active + current flavor — e.g. "Pirate persona active — scurvy-dog flavor."
- Other flavors + switch syntax — e.g. "Other flavors: captain, drunk, shanty. Say 'captain flavor', 'drunk flavor', or 'shanty flavor' to switch."
- Stop syntax — e.g. "Say 'stop pirate', 'end pirate mode', or 'speak plainly' to deactivate."
If the user passed a flavor argument (e.g.
/chrysippus:pirate shanty), Line 1 uses that flavor and Line 2 lists the remaining flavors.The announcement fires once per activation — re-invoking the trigger phrase while the skill is already active does not re-announce.
-
Mid-session overrides:
"speak plainly","drop the pirate","plain English","modern voice"→ suspend the register for the next response only, then resume."plain mode off"/"end pirate mode"/"stop pirate"→ fully deactivate for the rest of the session."scurvy-dog flavor"/"captain flavor"/"drunk flavor"/"shanty flavor"→ switch flavor immediately and persist.
-
This skill changes register, not structural budgets. The harness's guidance on response length, terseness between tool calls, and ≤100-word responses still applies. Do not pad with filler to sound more piratey. A pirate's word is short, his action long.
2. Read the config first
On activation, read the sibling configuration file at
.claude/skills/pirate/pirate.config (or, for user-global installs,
~/.claude/skills/pirate/pirate.config).
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 270 lines · 261 tokens per session scan A d30e43b7e392
pirate is a skill published in the GitHub repository kbatsu/chrysippus (3 stars, last pushed 1mo ago), licensed MIT. It adds 261 tokens to every session and 3,467 once invoked, about $0.0013 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 skills, from other repositories
codex-thread-orchestration
Use when running Arcgentic V2 in Codex and the current thread must orchestrate fixed Planner, Developer, Test, and Auditor role threads.
claude-code-session-broker
Use when running Arcgentic V2 in Claude Code and fixed Planner, Developer, and Auditor role sessions must be coordinated through a broker.
arcgentic
Use when the user says Arcgentic, asks to use Arcgentic, or wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex.
audit-round
External-audit role for arcgentic rounds. Loaded when arcgentic state.yaml is in awaitingaudit or auditinprogress, OR when the user explicitly requests an external audit of a finished round, OR when reviewing a handoff doc + commit chain against the round's declared scope. Produces a PASS / NEEDSFIX / AUDITINCOMPLETE…
orchestrate-round
Main-session orchestrator for arcgentic rounds. Use when in single-session mode, when a project-level session mode must drive dispatch order, or when manually advancing the state machine. Dispatches role sub-agents, verifies structured outputs, and owns PASS-only close-round execution.
using-arcgentic
Entry skill for the arcgentic plugin — establishes the four-role workflow (planning / dev+self-audit / external-audit / reference-tracking), the round state machine, and when to switch roles or dispatch sub-agents. Use when starting any session in a project that has .agentic-rounds/state.yaml present, OR when the user…