Slime AGENTS.md

A project instruction guide for Slime, a plugin that turns coding sessions into a turn-based role-playing game. It explains the project, rules, file layout, and safe ways for coding agents to work on it.

In plain words
What is it for?
Onboarding agents, explaining project structure, and documenting rules such as keeping the real coding session unchanged.
Why use it?
It gives an agent the context and constraints needed to change Slime without breaking its behavior.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/bitqs/slime/agents-md
Clone the repo
git clone --depth 1 https://github.com/bitqs/Slime

Made for: Codex, OpenCode.

Per session 2,038 This file is loaded in full into every session.
When invoked 2,038 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02038 $0.02038
Opus 5 $0.01019 $0.01019
Sonnet 5 $0.00408 $0.00408
Haiku 4.5 $0.00204 $0.00204

Measured yesterday against content hash 14d679a6ae58, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Slime AGENTS.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.

AGENTS.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — read this first, then you can ship

The single onboarding doc for any coding agent or vibe-coder working on Slime. Read it top to bottom and you can collaborate without breaking anything. It is harness-neutral; CLAUDE.md is the Claude-Code-specific companion, and docs/STRUCTURE.md is the full file-by-file map.

What Slime is

A zero-dependency, zero-build plugin that renders a real coding session as a turn-based RPG. Hooks observe every prompt and tool call and append battle events to an append-only stream; three read-only consumers visualize them — a statusline HUD, a tmux pane, and a PixiJS browser arena. Your work goals are the bosses; your plugins are your gear.

The prime directive (never violate)

Observer principle. The plugin must never change the real session. With Slime installed, the agent's behavior must be byte-identical to without it. Therefore:

  • Hooks are fail-soft: whole body in try/catch, always process.exit(0), never block, no LLM calls in the hot path (the heuristic core/estimate.js exists precisely to avoid one).
  • Consumers (statusline.js, watch.js, serve.js) are read-only w.r.t. game state. The sole exception: serve.js writes the lang preference to config.json on an explicit user click (POST /set-lang, 127.0.0.1-only, validated) — a UI preference, not game state, and it never touches Claude's session, so the observer principle still holds. Nothing else under SLIME_ROOT is written by a consumer.

The other hard rules

  • Zero runtime deps, zero build. No npm install to run; no bundler; no .ts source. TypeScript is dev-only via JSDoc + tsc --checkJs. The browser arena vendors public/vendor/pixi.min.js — never a CDN. devDependencies are fine.
  • Statusline safety. Anything rendered to the terminal goes through hud.sanitize (strips control chars / ANSI — state files are untrusted input replayed every keystroke). Arena DOM uses textContent/escHtml, never innerHTML.
  • Flash safety. Arena flashes are capped ≤3/sec by the sequencer governor; ?calm=1 and prefers-reduced-motion must keep degrading new effects.
  • Determinism / replay-stability. State is replayed from the event stream and polled every keystroke. Do not use Math.random() in render or hook hot paths — derive "randomness" from an event index/hash (see mapper's hash) so output is stable across replays. Money/XP/unlocks are persisted once, never re-derived.
  • i18n. User-facing strings live in data/locales/{en,zh}.json (flat key→string; locale.t falls back to en). Add both languages for every new key. Player resource is Token (boss HP keeps "HP").
  • Test isolation. Every test sets process.env.SLIME_ROOT to a tmpdir before requiring libs (ROOT is captured at require time) and cleans up after.

Read the full file on GitHub · 141 lines

Changes

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.

  1. yesterday First seen · 141 lines · 2,038 tokens per session scan A 14d679a6ae58

Subscribe to this mod's changes

Slime AGENTS.md is an instructions file published in the GitHub repository bitqs/Slime (1 stars, last pushed 2mo ago), licensed MIT. It adds 2,038 tokens to every session, about $0.0102 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.