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/coo1white/cool-workflow/agents-mdgit clone --depth 1 https://github.com/coo1white/cool-workflowWrote 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/coo1white/cool-workflow/agents-md)<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>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 | $0.12574 | $0.12574 |
| Opus 5 | $0.06287 | $0.06287 |
| Sonnet 5 | $0.02515 | $0.02515 |
| Haiku 4.5 | $0.01257 | $0.01257 |
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.
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 atplugins/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). Nevergit tagby 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.
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 · 888 lines · 12,574 tokens per session scan A df6f40ccbbe2
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.
Other instructions, from other repositories
Wakeflow AGENTS.md
Instructions for GxFn/Wakeflow, covering wakeflow source repository instructions, scope and safety, source ownership, change discipline and verification.
Wakeflow CLAUDE.md
Instructions for GxFn/Wakeflow, covering wakeflow source repository instructions for claude code, scope and safety, source ownership, change discipline and verification.
research-os AGENTS.md
Instructions for lxinfei5/research-os, covering researchos — constitution, §0 what this is, §1 directory discipline, §2 half-life (innovation 1) — memory design and §3 behavior pillars (innovations 2–5).
AI-System-Design-Consultant CLAUDE.md
Instructions for deepanshu2711/AI-System-Design-Consultant, covering claude.md, what this is, running it, load-bearing typos — do not "fix" these paths and agent node pattern.
agent-eve CLAUDE.md
Instructions for shehryarsaroya/agent-eve, covering claude.md — agent eve (né the compact, then agent transfer), 0. 🚨 hard rules, 1. what this is, 2. doc map and 3. state of play (2026-07-26).
team-shinchan AGENTS.md
Instructions for seokan-jeong/team-shinchan, covering agents.md - team-shinchan agent map, layer architecture, agent registry, call flow and quick reference.