agent-toolkit AGENTS.md

agent-toolkit AGENTS.md is an instructions file for Codex, OpenCode from ulises-jeremias/agent-toolkit. It costs 4,514 tokens per session, scanned A, original, MIT.

A set of instructions for working in agent-toolkit, a library that shares AI skills, agent roles, workflow templates and tool settings across coding assistants. It explains the repository’s structure and contribution rules.

In plain words
What is it for?
Use it when adding, changing or reviewing skills, agent profiles, integrations or other files in the agent-toolkit repository.
Why use it?
It helps an AI agent understand how changes in one shared toolkit can affect many coding tools and users.

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/ulises-jeremias/agent-toolkit/agents-md
Clone the repo
git clone --depth 1 https://github.com/ulises-jeremias/agent-toolkit

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 agent-toolkit AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ulises-jeremias/agent-toolkit/agents-md.svg)](https://agentmods.dev/instructions/ulises-jeremias/agent-toolkit/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ulises-jeremias/agent-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/ulises-jeremias/agent-toolkit/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,514 This file is loaded in full into every session.
When invoked 4,514 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 5.1 $0.04514 $0.04514
Opus 5 $0.02257 $0.02257
Sonnet 5 $0.00903 $0.00903
Haiku 4.5 $0.00451 $0.00451

Measured 5d ago against content hash c1dc27483099, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agent-toolkit 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 5d 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 · 399 lines

How it starts

The opening of the file, as written. The whole thing — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — AI Agent Contract

Purpose: This file is the primary contract for any AI agent contributing to or working inside this repository. Read it before touching any file.


What This Toolkit Does

agent-toolkit is a modular library of AI capabilities — skills, agent personas, loop templates, MCP configs, and per-tool profiles — designed to work across every major AI coding assistant (Claude Code, Cursor, OpenCode, GitHub Copilot, Windsurf, Pi Coding Agent, Muse Code).

The goal is a single source of truth: author a skill once, deploy it to any tool via its profile. When you add, modify, or remove anything here, you are affecting every downstream consumer who installs this toolkit.

Operate accordingly: be precise, cite sources, and validate before finalizing.


Repository Structure

agent-toolkit/
├── skills/
│   ├── core/           # Session bootstrap, handshake, workspace, project
│   ├── delivery/       # PRD, ADR, work items, delivery workflows
│   ├── design/         # UI/UX, Figma, frontend
│   ├── forge/          # GitHub/GitLab CLI, CI, PRs, worktrees
│   ├── integrations/   # Slack, Linear, ClickUp, MCP
│   ├── data/           # dbt, Snowflake
│   ├── tooling/        # Playwright, Jupyter, Herdr, inventory
│   ├── ops/            # Triage, swarm, docs, cost
│   ├── loops/          # loop-runner
│   ├── agentic-security/
│   ├── architecture/
│   ├── cloud/
│   ├── accessibility/
│   └── quality/
├── agents/             # Tool-agnostic agent persona definitions
├── profiles/
│   ├── claude-code/    # .claude/settings.json overlay + CLAUDE.md
│   ├── cursor/         # .mdc rule files for Cursor
│   ├── opencode/       # System prompt overlays for OpenCode
│   ├── copilot/        # copilot-instructions.md for GitHub Copilot
│   ├── windsurf/       # rules.md + memory files for Windsurf
│   ├── pi/             # Skill files for Pi Coding Agent
│   └── muse-code/      # Muse Code Agent Skills
├── mcp/
│   └── templates/      # MCP server config templates (JSON)
├── loops/              # Loop engineering templates (loop.yaml per docs/HOW_TO_CREATE_LOOP.md)
│   └── <name>/
│       ├── loop.yaml   # Required: loop definition (tier, cadence, goal, request, budget, allow/deny)
│       ├── STATE.md    # Runtime: checkpoint state (written by runner, not committed)
│       └── report.md   # Runtime: output report (written by agent, not committed)
├── packs/              # Docs-only solution packs (ADR-006) — workflow templates, not loaded by compiler
├── plugins/            # Compiler-generated target manifests (do not hand-edit; ADR-003/004)
├── distributions/      # Product specification for compiler input (products.yaml)
├── integrations/       # Swarm UI integrations (e.g., Herdr plugin; ADR-008)
├── catalogs/
│   ├── skill-catalog.yaml
│   └── agent-catalog.yaml
├── schemas/            # JSON schemas for validation
│   ├── skill-md-frontmatter.schema.json
│   └── loop.schema.json
├── docs/               # Human-facing documentation
│   ├── CONCEPTS.md     # Public concept model — see "Three kinds of packs"
│   └── adrs/           # Architecture Decision Records
└── scripts/            # validate-skills.vsh, validate-agents.vsh, validate-loops.vsh, generate-catalogs.vsh (provenance.py kept)

Read the full file on GitHub · 399 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. 5d ago First seen · 399 lines · 4,514 tokens per session scan A c1dc27483099

Subscribe to this mod's changes

agent-toolkit AGENTS.md is an instructions file published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed today), licensed MIT. It adds 4,514 tokens to every session, about $0.0226 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.

Related

Other instructions, from other repositories