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/goondocks-co/open-agent-kit/agents-mdgit clone --depth 1 https://github.com/goondocks-co/open-agent-kitWrote 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/goondocks-co/open-agent-kit/agents-md)<a href="https://agentmods.dev/instructions/goondocks-co/open-agent-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/goondocks-co/open-agent-kit/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 | $0.00854 | $0.00854 |
| Opus 5 | $0.00427 | $0.00427 |
| Sonnet 5 | $0.00171 | $0.00171 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
open-agent-kit 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.
This is a copy
84% identical to open-agent-kit copilot-instructions.md — 24 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions for AI Contributors
You are an AI coding agent working in this repository.
Source of truth (hard rules)
Read and follow oak/constitution.md. It is the authoritative specification for architecture, conventions, golden paths, and quality gates.
- If anything conflicts with
oak/constitution.md,oak/constitution.mdwins. - If you are unsure how to apply a rule, stop and ask rather than guessing.
- The canonical Anchor Index lives in
oak/constitution.md.
Required workflow
- Read
oak/constitution.md(especially the golden paths + hard rules + DoD). - Search first: find the closest existing implementation and mirror it (use the Top Anchors below).
- Implement the change following the constitution.
- Run the quality gate:
make check(must pass). - Update docs to prevent drift:
- Review/update
READMEif behavior/workflows changed. - Update the relevant feature docs (or create them) when touching feature behavior.
- Review/update
- If a better pattern is needed:
- Record the decision (RFC for formal, doc for informal) and update rules/docs so the new pattern becomes standard.
Non-negotiables
- No magic strings or numbers anywhere (including tests).
- Prefer proper engineering over shortcuts; fix root causes, not symptoms.
- Commands should be idempotent by default.
- Templates shipped by OAK are managed by OAK and overwritten on upgrade (no user overrides).
- Narrow lanes for deviation; when unclear, ask.
Editable install (MUST preserve)
MUST NOT run uv tool install or uv pip install without the -e flag. Always use make setup or make sync instead of ad-hoc install commands. See §7.3 of oak/constitution.md for the full rule, rationale, and verification command.
Top Anchors (shorthand)
These are the first places to look. The full Anchor Index is in oak/constitution.md.
Add a New Feature (vertical slice exemplar)
src/open_agent_kit/features/strategic_planning/manifest.yamlsrc/open_agent_kit/features/strategic_planning/rfc.pysrc/open_agent_kit/features/strategic_planning/commands/src/open_agent_kit/features/strategic_planning/templates/
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 · 80 lines · 854 tokens per session scan A 47656b8a1cdd
open-agent-kit AGENTS.md is an instructions file published in the GitHub repository goondocks-co/open-agent-kit (10 stars, last pushed 1mo ago), licensed MIT. It adds 854 tokens to every session, about $0.0043 per session on Opus 5. A static security scan graded it A with 0 findings. It is 84% identical to open-agent-kit copilot-instructions.md, differing in 24 lines, and is treated as a copy.
Other instructions, from other repositories
claude-code-settings copilot-instructions.md
Instructions for feiskyer/claude-code-settings, covering claude.md, environment setup, required dependencies, configuration and skills.
PromptKit copilot-instructions.md
Instructions for microsoft/PromptKit, covering promptkit — copilot instructions, how to use this repository, what this repository is, architecture and component conventions.
agent-rules testing.instructions.md
Instructions for lirantal/agent-rules, covering testing guidelines for node.js applications, general testing principles, guiding principles, descriptive test naming (three-part structure) and structure tests by the aaa pattern.
apex-accelerator agent-skills.instructions.md
Guidelines for creating high-quality Agent Skills for GitHub Copilot.
apex-accelerator code-quality.instructions.md
Code quality guidelines: commenting best practices (WHY not WHAT) and review priorities with security checks.
apex-accelerator javascript.instructions.md
JavaScript and Node.js conventions for validation scripts and tooling.