Borrowing it
Nothing to install: this file belongs to skeggsguy/adventure-party. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/skeggsguy/adventure-party/main/CLAUDE.mdgit clone --depth 1 https://github.com/skeggsguy/adventure-partyWrote 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/skeggsguy/adventure-party/claude-md)<a href="https://agentmods.dev/instructions/skeggsguy/adventure-party/claude-md"><img src="https://agentmods.dev/badge/instructions/skeggsguy/adventure-party/claude-md/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/instructions/skeggsguy/adventure-party/claude-md"><img src="https://agentmods.dev/badge/instructions/skeggsguy/adventure-party/claude-md.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 | $0.01355 | $0.01355 |
| Opus 5.5 | $0.00542 | $0.00542 |
| Sonnet 5.5 | $0.00271 | $0.00271 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
adventure-party 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 1mo 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This is the source repo for Adventure Party (party plugin) — a
fantasy-flavored agent-party and experience-system framework for Claude
Code, aimed at smart, driven users who weren't full-stack devs before
2024. Everything shipped is markdown (agents, skills, one hook payload)
plus a one-command hooks/hooks.json — no runtime code, no build. The repo
doubles as its own marketplace (.claude-plugin/marketplace.json).
Dogfooding this repo loads the shipped instructions through the plugin's
own SessionStart hook, so the party protocol arrives that way rather than
from this file. This project's .claude/ experience files are NOT loaded
by anything — read gotchas.md before your first edit, architecture.md
before planning or changing how parts fit, decisions.md before choosing
between approaches.
Commands
- Validate manifests (stdlib only — no
jq, which is absent on stock macOS/Linux/WSL):python3 -m json.tool .claude-plugin/plugin.json,python3 -m json.tool .claude-plugin/marketplace.jsonandpython3 -m json.tool hooks/hooks.json - Validate frontmatter (agents + skills; silence means valid, and a
broken description silently unloads the file; needs PyYAML —
pip install pyyaml, not bundled with python3 on Debian/Ubuntu):python3 -c "import re,glob,yaml;[yaml.safe_load(re.match(r'^---\n(.*?)\n---\n',open(p,encoding='utf-8').read(),re.S).group(1)) for p in glob.glob('agents/*.md')+glob.glob('skills/*/SKILL.md')]" - Check the hook payload against the 9,000 soft budget and the 10,000
character hard cap (past the cap the whole entry is silently relocated
to disk; counts code points, so
wc -cis wrong here):python3 -c "import sys;n=len(open('hooks/instructions.md',encoding='utf-8').read());print('FAIL' if n>10000 else 'WARN' if n>9000 else 'OK',n,'chars');sys.exit(n>10000)" - Hook smoke test (the sentinel phrase is
the lantern is lit, inhooks/instructions.md; anything else means the hook didn't inject):claude --plugin-dir . -p 'Quote the sentence containing "lantern" from your instructions, or say NONE.' - Dogfood locally:
claude --plugin-dir .(agentsparty:fighter/cleric/wizard, skills/party:session-zeroand/party:long-restshould list)
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.
- 1mo ago Changed · -2 lines · -43 tokens per session ed0866f35119
- 2mo ago First seen · 87 lines · 1,398 tokens per session scan A 521de9a6db09
adventure-party CLAUDE.md is an instructions file published in the GitHub repository skeggsguy/adventure-party (6 stars, last pushed 19d ago), licensed MIT. It adds 1,355 tokens to every session, about $0.0054 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.