instructree AGENTS.md

Repository instructions for contributing to Instructree, a dependency-free tool that audits coding-agent instructions and skills.

In plain words
What is it for?
Use them when modifying Instructree so behavior changes have focused tests and the project checks pass.
Why use it?
They define the project rules for reliable changes, including supported Node.js versions, tests, deterministic output, and cautious conflict reporting.

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/kotobuki09/instructree/agents-md
Clone the repo
git clone --depth 1 https://github.com/kotobuki09/instructree

Made for: Codex, OpenCode.

Per session 87 This file is loaded in full into every session.
When invoked 87 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 $0.00087 $0.00087
Opus 5 $0.00044 $0.00044
Sonnet 5 $0.00017 $0.00017
Haiku 4.5 $0.00009 $0.00009

Measured yesterday against content hash fcb03346eaa9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

instructree 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 · 9 lines

What it actually says

Contributor instructions

  • Keep Instructree dependency-free at runtime.
  • Use Node.js built-ins and support Node.js 20 or newer.
  • Add or update a focused node:test case for every behavior change.
  • Preserve deterministic output: sort discovered paths and diagnostics.
  • Describe heuristic findings as possible conflicts, never as proven agent behavior.
  • Run npm test and npm run check before submitting a change.
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 · 9 lines · 87 tokens per session scan A fcb03346eaa9

Subscribe to this mod's changes

instructree AGENTS.md is an instructions file published in the GitHub repository kotobuki09/instructree (0 stars, last pushed 6d ago), licensed MIT. It adds 87 tokens to every session, about $0.0004 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.