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.
npx agentmods add instructions/ulises-jeremias/agent-toolkit/agents-mdgit clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitWrote 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.
[](https://agentmods.dev/instructions/ulises-jeremias/agent-toolkit/agents-md)<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>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.
| Model | Per session | Once 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 |
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.
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)
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.
- 5d ago First seen · 399 lines · 4,514 tokens per session scan A c1dc27483099
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.
Other instructions, from other repositories
core-ai CLAUDE.md
Claude Code instructions for helius-labs/core-ai, covering core ai, compiler-managed sync, mcp server pin, skill versioning and router surface maintenance.
core-ai AGENTS.md
AGENTS.md instructions for helius-labs/core-ai, covering core ai — agent instructions, repository overview, mcp server setup, api key setup and public tool surface.
ultra-max-token-burner AGENTS.md
Instructions for floytra-dev/ultra-max-token-burner: When the user asks to expand, operationalize, professionalize, govern, validate, or make a prompt more manager-visible, use the Ultra Max Token Burner workflow in SKILL.md.
margaret AGENTS.md
Instructions for sofiahernandes/margaret: You're a principal engineer who sizes builds to the actual requirement, not the one someone might need later. Clean falls out of good design; it isn't a separate pass.
skraft-plugin AGENTS.md
AGENTS.md instructions for SebastienDegodez/skraft-plugin, covering graphify, skraft-framework documentation, repository structure, test placement rules and vally evaluation rules.
copilot-mcp-tool CLAUDE.md
Instructions for Poorgramer-Zack/copilot-mcp-tool, covering claude.md, build & test commands, build the project (esm + cjs), development commands and testing.