cool-workflow AGENTS.md

cool-workflow AGENTS.md is an instructions file for Codex, OpenCode from coo1white/cool-workflow. It costs 12,574 tokens per session, scanned A, original, BSD-2-Clause.

A repository instruction file that tells coding agents how to work on the project and release changes.

In plain words
What is it for?
Use it to guide autonomous development, conflict handling, release preparation, engineering practices, and interactions with different coding-agent vendors.
Why use it?
It gives agents shared project rules, such as working through branches and pull requests instead of pushing directly to the main branch.

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/coo1white/cool-workflow/agents-md
Clone the repo
git clone --depth 1 https://github.com/coo1white/cool-workflow

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for cool-workflow AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/coo1white/cool-workflow/agents-md.svg)](https://agentmods.dev/instructions/coo1white/cool-workflow/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/coo1white/cool-workflow/agents-md"><img src="https://agentmods.dev/badge/instructions/coo1white/cool-workflow/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 12,574 This file is loaded in full into every session.
When invoked 12,574 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 $0.12574 $0.12574
Opus 5 $0.06287 $0.06287
Sonnet 5 $0.02515 $0.02515
Haiku 4.5 $0.01257 $0.01257

Measured 3d ago against content hash df6f40ccbbe2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cool-workflow 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.

AGENTS.md · 888 lines

How it starts

The opening of the file, as written. The whole thing — 888 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cool Workflow — Autonomous Development Agent

Place this file at the repository root. Claude Code / Codex and most coding agents auto-load AGENTS.md. The companion reviewer prompt lives at plugins/cool-workflow/agents/release-reviewer.md.

Quick Index

This is the one file to read. Sections most needed mid-session:

  • HARD RULE — never push to main; branch -> PR -> green CI -> merge.
  • Project Memory — what CW is and is not (FreeBSD discipline inside, Homebrew spirit outside), the product moat and positioning, and the build-memory lessons carried in from DIRECTION.md / PROJECT_MEMORY.md.
  • FreeBSD Engineering Discipline — POLA, mechanism not policy, fail closed, zero runtime dependencies, JS/TS only, and the rest. Binding, not aspirational.
  • Shipping a release — the two-step flow (agent preps the bump PR; the operator runs npm run release -- X.Y.Z). Never git tag by hand; the verdict signing key stays with the operator.
  • Resolving merge conflicts — rebase the work branch, never merge the base in; semantic conflicts in release/security code are a stop sign.
  • Multi-Vendor Agent Standards — rules for calling CW as a client and for vendor agents working together on CW itself (full doc: plugins/cool-workflow/docs/multi-vendor-agent-standards.7.md).

Role

You are the autonomous release engineer for Cool Workflow (CW), a zero-dependency TypeScript/Node.js agent workflow control-plane. You run a continuous improvement loop: plan → implement → verify → release. Your job is to grow real capability, not version numbers.

HARD RULE — Never push directly to main

All changes go through a feature branch → PR → review → merge workflow. git push origin main is forbidden. Use descriptive branch names (e.g. fix/audit-findings, feat/parallel-review). Create a PR with gh pr create and merge through GitHub. If this rule is violated, immediately git revert the push on main and re-create the change as a proper PR. This rule exists because direct pushes bypass review, CI gating, and the audit trail.

Read the full file on GitHub · 888 lines

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. 3d ago First seen · 888 lines · 12,574 tokens per session scan A df6f40ccbbe2

Subscribe to this mod's changes

cool-workflow AGENTS.md is an instructions file published in the GitHub repository coo1white/cool-workflow (2 stars, last pushed 7d ago), licensed BSD-2-Clause. It adds 12,574 tokens to every session, about $0.0629 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.

Related

Other instructions, from other repositories