tokenroom AGENTS.md

tokenroom AGENTS.md is an instructions file for Codex, OpenCode from tyejcoleman/tokenroom. It costs 222 tokens per session, scanned A, original, Apache-2.0.

Repository instructions stored in an AGENTS.md file. They tell coding agents to read the repository’s context and planning documents and follow its safety and extension rules.

In plain words
What is it for?
Use it to guide agents working in the tyejcoleman/tokenroom repository, especially before implementing changes or claiming that work is complete.
Why use it?
They give agents the project-specific rules they need before changing code, including required checks and restrictions on dependencies, network access, and undocumented interfaces.

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

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 tokenroom AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tyejcoleman/tokenroom/agents-md.svg)](https://agentmods.dev/instructions/tyejcoleman/tokenroom/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tyejcoleman/tokenroom/agents-md"><img src="https://agentmods.dev/badge/instructions/tyejcoleman/tokenroom/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 222 This file is loaded in full into every session.
When invoked 222 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 $0.00222 $0.00222
Opus 5 $0.00111 $0.00111
Sonnet 5 $0.00044 $0.00044
Haiku 4.5 $0.00022 $0.00022

Measured 3d ago against content hash 209596e282d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tokenroom 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 · 17 lines

What it actually says

Agent instructions

This repo's working context lives in CLAUDE.md — read it first; it applies to every agent and harness, not just Claude Code.

Before any work, read in order:

  1. docs/ARCHITECTURE.md — data flow, module map, extension points.
  2. docs/DECISIONS.md — the ADR log; never silently violate a decision.
  3. docs/PLAN.md — tasks with acceptance criteria (AC = definition of done).

Hard gates: scripts/check-invariants.mjs (also in npm test/CI) blocks new dependencies, non-builtin imports, any network surface, compliance tripwires, and crash-prone entry points — each failure cites the ADR explaining why. Run it before claiming done. Hard rules: official extension points only; never reuse subscription OAuth tokens outside the official client, call undocumented endpoints, spoof harness identity, or burn interactive quota headlessly. Full detail in CLAUDE.md.

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 · 17 lines · 222 tokens per session scan A 209596e282d1

Subscribe to this mod's changes

tokenroom AGENTS.md is an instructions file published in the GitHub repository tyejcoleman/tokenroom (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 222 tokens to every session, about $0.0011 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.