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/johnny-xuan/treework/agents-mdgit clone --depth 1 https://github.com/Johnny-xuan/TreeWorkWrote 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/johnny-xuan/treework/agents-md)<a href="https://agentmods.dev/instructions/johnny-xuan/treework/agents-md"><img src="https://agentmods.dev/badge/instructions/johnny-xuan/treework/agents-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 | $0.00375 | $0.00375 |
| Opus 5 | $0.00187 | $0.00187 |
| Sonnet 5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
TreeWork 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 3d 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.
What it actually says
TreeWork Repository Guidance
This repository contains two independently installable TreeWork editions and the source used to maintain them.
Read Before Editing
- Workflow behavior: read the relevant file under
plugins/treework/skills/treework/references/. - Build Tree runtime: read
docs/architecture/build-tree-runtime.md. - Transaction, event, checkpoint, or projection behavior: read
docs/architecture/transaction-projection.md. - Project Map product behavior: read
docs/product/project-map.md. - Development and release commands: read
docs/development.mdanddocs/releasing.md.
Repository Boundaries
plugins/treework/is the installable Coding Agents edition. Keep it free of project history, UI source, prototypes, and maintainer-only documents.skills/treework-manual/is the independently installable Manual edition. Keep its complete working contract in one self-containedSKILL.md.- Agent references explain how to use TreeWork. Do not put Rust modules, API internals, migration plans, or frontend architecture there.
project-map-ui/is source;plugins/treework/assets/graph-panel/is generated output..TreeWork/is user-project state created by TreeWork and must never be bundled into the installable plugin.
Change Discipline
- Preserve the three-stage workflow: Pre-Tree Alignment, Build Tree, Work Tree.
- Keep the Agent-facing command surface small.
- Do not add Team, Runner, assignment, or provider-session state.
- Project Map remains a read-only projection.
- Machine-owned accepted state changes only through transactions.
- Add or update tests for public behavior.
- Run
make testandmake validatebefore declaring a change complete.
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.
- 3d ago First seen · 40 lines · 375 tokens per session scan A 0cec79e3fbd9
TreeWork AGENTS.md is an instructions file published in the GitHub repository Johnny-xuan/TreeWork (24 stars, last pushed 21d ago), licensed MIT. It adds 375 tokens to every session, about $0.0019 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
vibe-coding-repository-standard AGENTS.md
Instructions for cz1993/vibe-coding-repository-standard, covering vcrs repository instructions, purpose, communication, change discipline and privacy and safety.
memi CLAUDE.md
Claude Code instructions for memi-design/memi, covering mémoire — guidelines for claude, prime directives, what is mémoire, widget v2 operating model and architecture.
memi AGENTS.md
AGENTS.md instructions for memi-design/memi, covering mémoire — guidelines for codex, prime directives, what is mémoire, architecture and atomic design levels.
simple-man AGENTS.md
Instructions for Maksim-Burtsev/simple-man, a project described as: Cut the chatter. Keep the work. A measured communication policy for coding agents: −32% output tokens, zero lost facts.
zimster AGENTS.md
Instructions for wazimmerman/zimster, a project described as: One development workflow for coding agents, without the agent sprawl.
apex-workflow AGENTS.md
AGENTS.md instructions for 0xCozart/apex-workflow, covering apex workflow agent instructions, install flow and guardrails.