Borrowing it
Nothing to install: this file belongs to sandydasari/openacme. 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/sandydasari/openacme/main/CLAUDE.mdgit clone --depth 1 https://github.com/sandydasari/openacmeWrote 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/sandydasari/openacme/claude-md)<a href="https://agentmods.dev/instructions/sandydasari/openacme/claude-md"><img src="https://agentmods.dev/badge/instructions/sandydasari/openacme/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 5.1 | $0.13009 | $0.13009 |
| Opus 5 | $0.06504 | $0.06504 |
| Sonnet 5 | $0.02602 | $0.02602 |
| Haiku 4.5 | $0.01301 | $0.01301 |
Grade A, and why
openacme 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 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 — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAcme — Claude Code guide
TypeScript agent platform. Multi-provider LLM with streaming tool-calls, SQLite-backed sessions, MCP integration, OAuth (ChatGPT / Claude subscriptions), an Ink-based CLI TUI, and a Vite + TanStack Router web UI served by the Hono server.
Design lens. This is an AI workforce platform — a structured set of role-specialized agents working for a small human team — not a single-agent assistant. Each agent carries a name, a role (third-person paragraph for coworkers), and a persona (second-person system prompt), and owns its own config, model, tools, skills, MCP servers, sessions, tasks, memory, workspace, and resources. When designing new state or behavior, the question is "does this hold for N agents working in parallel under different roles?" — not "does this work for the agent." Anywhere you'd reach for a global table or a singleton, default to scoping by agent_id instead. Cross-agent work — one agent assigning a task to another, one agent looking up coworkers via agent_list — is a first-class primitive, so anything you add should be addressable by agent.
Workspace layout
Turborepo + pnpm 9. Workspace globs: apps/*, packages/*. Published packages are @openacme/*; internal tooling is @repo/*.
apps/
cli/ # `openacme` binary — Commander + Ink TUI + Clack setup
web/ # Vite + TanStack Router SPA (chat/agents/skills UI); static-built into packages/server/web
docs/ # Next.js docs site (placeholder)
packages/
agent-core/ # Agent class — agentic loop, streaming, history reconstruction
server/ # Hono HTTP server + AgentManager (multi-agent orchestration)
cli (apps) # see above
llm-provider/ # getModel() — OpenAI / Anthropic / Google / OpenRouter / Ollama / custom
mcp-client/ # MCP stdio + HTTP/SSE transports; tool discovery into registry
tools/ # ToolRegistry + built-ins (shell, read_file, write_file, edit,
# apply_patch, list_files, search_files, session_search, skill_view,
# web_search, web_extract, execute_code, process, memory, task_*,
# agent_list, browser_*)
browser/ # Per-agent browser sessions via pluggable provider (local Chrome / Browserbase / Browser-Use / Firecrawl)
db/ # better-sqlite3 + Drizzle; sessions/messages/user_profiles +
# task_comments/task_events + FTS5 (agents are filesystem-backed
# under <dataDir>/agents/, not in the DB)
memory/ # Per-agent persistent MEMORY.md store (Anthropic memory_20250818 +
# Claude Code index/topic-file convention)
tasks/ # Workforce task store (filesystem; isolation by assignee)
config/ # Zod schema + YAML/JSON loader (~/.openacme/config.yaml)
auth/ # OAuth (ChatGPT subscription, Claude Pro), token store, body/response
# transforms, refresh
skills/ # SKILL.md discovery, progressive disclosure + multi-source hub
# (GitHub, marketplaces, URL, well-known, local, builtin) under hub/;
# bundled skills live at packages/skills/builtin/<name>/
agent-catalog/# Bundled agent templates (Software Engineer, …) — Importable via web or CLI
ui/ # Shared React components (minimal)
eslint-config, typescript-config # @repo/* internal
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 · 499 lines · 13,009 tokens per session scan A 58b8fa64f469
openacme CLAUDE.md is an instructions file published in the GitHub repository sandydasari/openacme (85 stars, last pushed 1mo ago), licensed MIT. It adds 13,009 tokens to every session, about $0.0650 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 2026-08-30.
Other instructions, from other repositories
agentforge-py copilot-instructions.md
Copilot instructions for Scaffoldic/agentforge-py: See AGENTS.md for project conventions. AGENTS.md is the canonical source for AI-assistant instructions. This file exists so GitHub Copilot's native .github/copilot-instructions.md discovery keeps working.
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.