foolery AGENTS.md

A repository instruction file that tells coding agents how to work in a project, including which settings, task tracker, and Git worktree rules to follow. A Git worktree is a separate checkout of the same repository.

In plain words
What is it for?
Use it to control Codex settings, require Knots for work tracking, define when branches or pull requests are allowed, and explain how to install dependencies in a new worktree.
Why use it?
It gives every agent the same project-specific rules and prevents agents from using the wrong tracker or working in the wrong checkout.

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

Made for: Codex, OpenCode.

Per session 1,289 This file is loaded in full into every session.
When invoked 1,289 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 $0.01289 $0.01289
Opus 5 $0.00645 $0.00645
Sonnet 5 $0.00258 $0.00258
Haiku 4.5 $0.00129 $0.00129

Measured 3d ago against content hash b8feea0ad52e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

foolery 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 · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Codex Configuration

When using Codex CLI in this project:

  • approval_policy: never (autonomous mode for routine work)
  • model_reasoning_effort: xhigh (complex codebase, needs deep reasoning)

Override with: codex -c approval_policy=ask or codex -c model_reasoning_effort=medium as needed.

Repository Overrides

These repo-level rules are mandatory for all agents working in this project:

  1. Use Knots (kno) as the only work-tracking system.
  2. Do not use any alternate tracker in this repository.
  3. Never move knots to terminal states unless the user explicitly instructs you.
  4. Never use a PR workflow unless the user explicitly instructs you to use PRs.

Git Worktree Policy (Hard Override)

This repository supports parallel agent work using Git worktrees.

  1. Do implementation work in a dedicated Git worktree.
  2. Worktrees may use short-lived local branches for isolation.
  3. Final integrated changes must be pushed to remote main (origin/main).
  4. Do not require reviews or pull requests unless the user explicitly requests them.

Worktree Dependency Bootstrap

Each Git worktree is a separate checkout and does not share node_modules.

  1. After creating or switching to a worktree, run: bun install --frozen-lockfile
  2. Run dependency install before lint, typecheck, test, or build commands.
  3. Prefer bun run <script> over bunx <tool> so plugins resolve from local project dependencies.
  4. If node_modules is missing in the worktree, treat lint/typecheck results as invalid until install completes.

Code Style Constraints

  • File length: max 500 lines per source file
  • Function length: max 100 lines per function
  • Line length: max 100 columns per line

These are enforced by ESLint (max-lines, max-lines-per-function, max-len).

kno Workflows Are Authoritative

kno .loom workflows are the single source of truth; Foolery TS must never override, extend, or post-process them (no synthetic transitions, no parallel canonical graph). Correction actions that skip gates must be named as such and invoke kno idiomatically with force: true (see KnotsBackend.close()); details in docs/DEVELOPING.md.

Read the full file on GitHub · 107 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 · 107 lines · 1,289 tokens per session scan A b8feea0ad52e

Subscribe to this mod's changes

foolery AGENTS.md is an instructions file published in the GitHub repository acartine/foolery (54 stars, last pushed 1mo ago), licensed MIT. It adds 1,289 tokens to every session, about $0.0064 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.