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/longyangxi/openoffice/claude-mdgit clone --depth 1 https://github.com/longyangxi/OpenOfficeWrote 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/longyangxi/openoffice/claude-md)<a href="https://agentmods.dev/instructions/longyangxi/openoffice/claude-md"><img src="https://agentmods.dev/badge/instructions/longyangxi/openoffice/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 | $0.00582 | $0.00582 |
| Opus 5 | $0.00291 | $0.00291 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
OpenOffice 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 4d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Office
Project Structure
apps/web- Next.js 15 PWA (Vercel deployment)apps/gateway- Mac daemon (Node.js + multi-channel + AI CLI control)packages/shared- Shared event protocol (Zod schemas)packages/orchestrator- Multi-agent engine (worktree, delegation, phases)packages/memory- Persistent agent memory (sessions, facts, shared knowledge)
Git
- All git commit messages MUST be in English.
Key Commands
pnpm dev:web- Start web dev serverpnpm dev:gateway- Start gateway
Architecture
- Channels: WebSocket (always), Ably (optional), Telegram (optional)
- UI: PixiJS v8 pixel office + Key Node Mode agent cards
Data Directory
- Dev:
~/.open-office-dev/, Release:~/.open-office/ config.json— global configdata/instances/<id>/— per-gateway state (logs, sessions, memory)data/agents.json— agent definitionsprojects/— default agent workspace (team projects created here)worktrees/<repo-hash>/<agentId>/— centralized worktree isolation
Worktree Isolation
- One agent = one worktree = one branch (keyed by agentId, not taskId)
- Worktrees stored outside repo at
~/.open-office[-dev]/worktrees/to prevent path traversal - On task:done: auto-merge to main (default), with per-agent toggle + undo merge
- Before each task: auto-rebase onto latest main, conflicts auto-resolved
- Cleanup: on fire agent only (no startup GC)
- Full docs:
packages/orchestrator/README.md→ "Worktree Isolation"
Key Node Mode
Only 4 key events shown in UI: TASK_STARTED, APPROVAL_NEEDED, TASK_DONE, TASK_FAILED. Agent states: idle, working, waiting_approval, done, error. TASK_DONE includes structured result (changedFiles, diffStat, testResult).
Team Execution Flow
Phases: CREATE → DESIGN → EXECUTE → COMPLETE → (loop or END). Execute: Leader → Dev (build+self-fix) → Reviewer (VERDICT) → Fix loop (max 3 reviews). Roles: Developer (ENTRY_FILE or PREVIEW_CMD+PORT), Code Reviewer (VERDICT PASS/FAIL), Team Lead (delegates only). Preview: static HTML (npx serve:9100), build output (dist/index.html), or command (PREVIEW_CMD on PREVIEW_PORT). Project dir: unique per session, all members share it. Created on APPROVE_PLAN.
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.
- 4d ago First seen · 48 lines · 582 tokens per session scan A 92943bfb9b26
OpenOffice CLAUDE.md is an instructions file published in the GitHub repository longyangxi/OpenOffice (250 stars, last pushed 1mo ago), licensed MIT. It adds 582 tokens to every session, about $0.0029 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.