stem AGENTS.md

Repository instructions for stem.cooking, a project that packages engineering workflows as coding-agent skills.

In plain words
What is it for?
Use them when working on the stem.cooking skill, documentation, planning files, versions, or release checks, including the commands needed to install dependencies and verify the repository.
Why use it?
They tell agents how to plan, validate, lint, and build the project while preserving rules such as no telemetry, correct branding, and owner-controlled git operations.

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

Made for: Codex, OpenCode.

Per session 274 This file is loaded in full into every session.
When invoked 274 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 $0.00274 $0.00274
Opus 5 $0.00137 $0.00137
Sonnet 5 $0.00055 $0.00055
Haiku 4.5 $0.00027 $0.00027

Measured yesterday against content hash 7dfff9b7a077, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stem 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 · 34 lines

What it actually says

stem.cooking

Engineering discipline for coding agents, shipped as skills. This repository builds itself under its own rules.

Always work through the stem skill: size the work, keep docs/planning/ current, verify before done.

Commands

  • pnpm install — install workspace dependencies
  • pnpm check — validate skills, versions, and the forbidden-terms guard
  • pnpm lint — markdown lint
  • pnpm build — build the site shell

Invariants

  • No telemetry, no network calls from the plugin — ever.
  • Public copy always says stem.cooking, never the bare short name.
  • This repository stands alone: no references to other workflow products' branding or history, anywhere, by convention.
  • skills/stem/ (one skill plus its references) is canonical; there is no build step for plugin content.
  • Version lives once in package.json; manifests must match (scripts/check-versions.mjs).
  • The repository owner runs Git: never init, commit, or push without being asked.

Current state

Read docs/planning/worklog.md (newest first) and docs/planning/active/v1-build/work.md for status and the exact next action.

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 · 34 lines · 274 tokens per session scan A 7dfff9b7a077

Subscribe to this mod's changes

stem AGENTS.md is an instructions file published in the GitHub repository markskrypka/stem (2 stars, last pushed 27d ago), licensed Apache-2.0. It adds 274 tokens to every session, about $0.0014 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.