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 agentmods add instructions/kbatsu/chrysippus/claude-mdgit 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/instructions/kbatsu/chrysippus/claude-md)<a href="https://agentmods.dev/instructions/kbatsu/chrysippus/claude-md"><img src="https://agentmods.dev/badge/instructions/kbatsu/chrysippus/claude-md.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 | $0.01372 | $0.01372 |
| Opus 5 | $0.00686 | $0.00686 |
| Sonnet 5 | $0.00274 | $0.00274 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
chrysippus CLAUDE.md 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 5d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project: chrysippus
This repo ships portable Claude Code skills that change the register of
assistant prose: shakespeare (Early Modern English), pirate (Treasure
Island / Pirates-of-the-Caribbean register), gen-alpha (internet-native
ironic Gen-Alpha slang), toronto-mans (Toronto / MTE caricature with
Patois + AAVE borrows), and ontario-bud (rural-Ontario / Letterkenny-inspired
caricature). See README.md for what they do and how to install
them in other repos. The canonical source for each skill lives in
rules/<persona>/; the .claude/skills/<persona>/ files are generated by
scripts/render.py and verified by scripts/render.py --check.
Communication style
This repo uses the shakespeare skill at .claude/skills/shakespeare/SKILL.md.
Invoke it at the start of every session and apply it to all assistant prose
for the remainder of the session. Read
.claude/skills/shakespeare/shakespeare.config to determine the active flavor
and preservation toggles. Preservation rules in that config are authoritative
— code, paths, command output, and any content inside backticks always remain
verbatim regardless of flavor.
The pirate, gen-alpha, and toronto-mans skills also live in this
repo but are trigger-only: they do not auto-activate. Summon them when
the user says one of their trigger phrases:
- Pirate: "talk like a pirate", "pirate mode", "ahoy matey",
"arrr",
/pirate. - Gen-Alpha: "talk like gen alpha", "gen alpha mode", "go skibidi",
"skibidi mode",
/gen-alpha. - Toronto-mans: "talk like a toronto mans", "toronto mans mode",
"toronto mode", "the six mode",
/toronto-mans. Note: thesafety_warningspreservation toggle is hard-locked on for this skill and cannot be disabled. - Ontario-bud: "ontario bud", "letterkenny mode", "pitter patter",
"talk like wayne",
/ontario-bud.
Precedence between skills
If more than one persona skill is activated in the same session, the most recently invoked one wins. Tell the user once which is now active; do not fuse or blend the registers. "End mode" / "stop " fully deactivates the named skill for the session.
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.
- 5d ago First seen · 102 lines · 1,372 tokens per session scan A 7916ed16495e
chrysippus CLAUDE.md is an instructions file published in the GitHub repository kbatsu/chrysippus (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,372 tokens to every session, about $0.0069 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 instructions, from other repositories
Arcgentic CLAUDE.md
Claude Code instructions for Arch1eSUN/Arcgentic, covering arcgentic v0.2.0 — dev session handoff, 1. identity, 2. not-this (boundary), 3. where you are (state as of handoff) and files to be created (v0.2.0 p0 scope, per spec § 18).
deep-init copilot-instructions.md
Instructions for deepfusionlabs/deep-init, covering repository instructions (copilot projection), kemal — agent context, architecture, components (7) and critical to know (non-obvious, load-bearing).
hotwire-codex-skills AGENTS.md
Instructions for davidteren/hotwire-codex-skills, covering agents.md — hotwire-codex-skills, what this is, how a skill is structured, conventions for adding/editing skills and the built skills.
hotwire-codex-skills CLAUDE.md
Instructions for davidteren/hotwire-codex-skills: See AGENTS.md and README.md for the suite guide and skill catalog.
gen-alpha-output-style CLAUDE.md
Instructions for sjnims/gen-alpha-output-style, covering claude.md, project overview, repository structure, architecture and development commands.
auto-pilot AGENTS.md
AGENTS.md instructions for IronRookieCoder/auto-pilot, covering 项目概况 and 同步更新规则.