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/bitqs/slime/claude-mdgit clone --depth 1 https://github.com/bitqs/SlimeWhat 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 | $0.01164 | $0.01164 |
| Opus 5 | $0.00582 | $0.00582 |
| Sonnet 5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
Slime 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 yesterday.
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
Slime — a Claude Code plugin that renders your real work as a turn-based RPG: hooks observe every tool call and write battle events; a statusline HUD, a tmux pane, and a PixiJS web arena visualize them. Published as marketplace bitqs/slime; users run it straight from the git clone — no build step, no npm install, zero runtime dependencies (devDependencies are fine; the browser arena uses a vendored public/vendor/pixi.min.js, never a CDN).
Commands
node --test test/ # full suite
node --test test/hud.test.js # one file
npm run typecheck # tsc --checkJs strict (needs `npm install` once for devDeps)
# Eyeball the arena without a real session:
SLIME_ROOT=/tmp/slime-demo node scripts/demo-feed.js &
SLIME_ROOT=/tmp/slime-demo SLIME_PORT=4118 node scripts/serve.js
# open http://127.0.0.1:4118 (?calm=1 = flash-free)
# Public demo worker (Cloudflare):
cd demo && npx wrangler deploy # → slime-arena-demo.shuangqu.workers.dev
Architecture
Everything flows through one state directory, SLIME_ROOT (default ~/.claude/slime, overridable via env — tests rely on this):
hooks (hooks/hooks.json → scripts/hook-*.js) WRITERS, fire on every prompt/tool call
└→ sessions/<id>.jsonl append-only SlimeEvent stream (cast/resolve/encounter/turn_end/
sessions/<id>.json live Snapshot boss_down/choice_open/choice_made/
profile.json, usage.json, boss state per-project plan_scroll/plan_approved/potion…)
consumers READERS, never write game state
├ scripts/statusline.js one-line HUD (core/hud.js), runs on every keystroke
├ scripts/watch.js tmux top-pane live monitor
└ scripts/serve.js local HTTP: / (public/index.html) + /state + /events (SSE tail
of the jsonl) + exact-match static whitelist (arena.js,
sequencer.js, minions.js, vendor/pixi.min.js — never
path-derived fs reads)
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.
- yesterday First seen · 61 lines · 1,164 tokens per session scan A 7f7c78aa6479
Slime CLAUDE.md is an instructions file published in the GitHub repository bitqs/Slime (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,164 tokens to every session, about $0.0058 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
Claude CLAUDE.md
Claude Code instructions for johanolofsson72/Claude, covering claude.md, critical rules (read first), execution mode, autonomous mode (non-interactive) and anti-stall rule.
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
agentoscope AGENTS.md
Instructions for rafaelcg/agentoscope, covering agentoscope — agent instructions, what this is, layout, commands and conventions.