agentmods.dev

toolmux: Instructions file for Codex

AGENTS.md

toolmux AGENTS.md is an instructions file for Codex, OpenCode from fiam/toolmux. It costs 7,546 tokens per session, scanned A, original, MIT.

Repository instructions for coding agents working on Toolmux, a tool that connects agents with providers, tools, workflows, and other services.

In plain words
What is it for?
Use it when changing Toolmux commands, providers, authentication, policies, supported tools, workflows, tests, releases, or documentation.
Why use it?
It keeps agent guidance, user documentation, contributor instructions, and release or security requirements consistent as the project changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

This is fiam/toolmux's own configuration. It tells Codex and OpenCode how to work on toolmux itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything toolmux configures →

not rated 2repo changed 2mo ago A scan 7,546 tokens original MIT
View source ↗ fiam/toolmux
Reuse

Borrowing it

Nothing to install: this file belongs to fiam/toolmux. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fiam/toolmux/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/fiam/toolmux

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 toolmux AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fiam/toolmux/agents-md/github.svg)](https://agentmods.dev/instructions/fiam/toolmux/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/fiam/toolmux/agents-md"><img src="https://agentmods.dev/badge/instructions/fiam/toolmux/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for toolmux AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/fiam/toolmux/agents-md"><img src="https://agentmods.dev/badge/instructions/fiam/toolmux/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,546 This file is loaded in full into every session.
When invoked 7,546 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.07546 $0.07546
Opus 5.5 $0.03018 $0.03018
Sonnet 5.5 $0.01509 $0.01509
Haiku 4.5 $0.00755 $0.00755

Measured 2mo ago against content hash c7f2ebbcf92e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

toolmux 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 2mo 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 · 630 lines

How it starts

The opening of the file, as written. The whole thing — 630 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file defines repository expectations for coding agents working on Toolmux. Keep it current whenever build, test, style, security, release, or workflow requirements change.

Maintenance

Agents must update this file when they:

  1. Change the supported Go version or toolchain setup.
  2. Add, remove, or rename important make targets or CI checks.
  3. Add a new provider, auth mode, policy behavior, or test class.
  4. Add, remove, rename, or change a supported native toolbox, remote MCP catalog entry, workflow template, or supported agent.
  5. Change commit, release, linting, formatting, or security expectations.
  6. Change the public OSS/private infrastructure repository boundary.
  7. Change CLI output behavior, terminal UX, or machine-readable schemas.
  8. Change public user behavior that should be reflected in README.md.
  9. Change developer workflow that should be reflected in CONTRIBUTING.md.

Agents must keep README.md, CONTRIBUTING.md, and this file in sync:

  1. README.md is for users. Update it for user-visible commands, provider status, supported toolboxes and tools, workflow templates, supported agents, auth flows, output modes, install instructions, and safety notes.
  2. CONTRIBUTING.md is for developers. Update it for local setup, test/lint workflow, provider integration rules, PR expectations, and release tooling.
  3. AGENTS.md is for coding agents. Update it for repository expectations that agents must follow while editing code or docs.
  4. Do not add or rename commands, flags, providers, auth behavior, policy behavior, or quality gates without checking whether all three docs need an update.

When updating Go guidance, check the official Go release notes and release history first:

  1. https://go.dev/doc/go1.26
  2. https://go.dev/doc/devel/release

Go Version

Use the latest stable Go toolchain. As of 2026-08-31, CI and release builds use Go 1.26.7 as the latest patch release for the supported Go 1.26 line.

Repository expectations:

Read the full file on GitHub · 630 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. 2mo ago Changed · +6 lines · +91 tokens per session c7f2ebbcf92e
  2. 2mo ago First seen · 624 lines · 7,455 tokens per session scan A 747915e23001

Subscribe to this mod's changes

toolmux AGENTS.md is an instructions file published in the GitHub repository fiam/toolmux (2 stars, last pushed 2mo ago), licensed MIT. It adds 7,546 tokens to every session, about $0.0302 per session on Opus 5.5. 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.

Goai-agentsclicredential-managementdeveloper-toolsgo
Related

toolmux AGENTS.md compared with instructions from other repositories

toolmux AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
toolmux AGENTS.mdfiam/toolmuxInstructions file22mo agoMITA7,546Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode