agentmods.dev

agent-skills-toolkit: Instructions file for Claude Code

AGENTS.md

agent-skills-toolkit AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from product-on-purpose/agent-skills-toolkit. It costs 1,732 tokens per session, scanned A, original, Apache-2.0.

Project instructions for agent-skills-toolkit, a tool and standard for creating, checking, managing, and expanding libraries of reusable agent skills. The repository also checks itself against its own rules in CI.

In plain words
What is it for?
Finding the source of truth, following repository conventions, and running the required build, test, and validation checks.
Why use it?
They give agents the project’s governing rules and current state before making changes. This reduces assumptions about what the toolkit currently supports.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also the file is AGENTS.md. Also seen: mentions subagents; mentions Claude Code; mentions AGENTS.md.

This is product-on-purpose/agent-skills-toolkit's own configuration. It tells Claude Code, Codex and OpenCode how to work on agent-skills-toolkit 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 agent-skills-toolkit configures →

not rated 2repo changed yesterday A scan 1,732 tokens original Apache-2.0
View source ↗ product-on-purpose/agent-skills-toolkit product-on-purpose.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to product-on-purpose/agent-skills-toolkit. 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/product-on-purpose/agent-skills-toolkit/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/product-on-purpose/agent-skills-toolkit

Made for: Claude Code, 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-skills-toolkit AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/product-on-purpose/agent-skills-toolkit/agents-md.svg)](https://agentmods.dev/instructions/product-on-purpose/agent-skills-toolkit/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/product-on-purpose/agent-skills-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/product-on-purpose/agent-skills-toolkit/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,732 This file is loaded in full into every session.
When invoked 1,732 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 $0.01732 $0.01732
Opus 5 $0.00866 $0.00866
Sonnet 5 $0.00346 $0.00346
Haiku 4.5 $0.00173 $0.00173

Measured yesterday against content hash 1e3551d7b57f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agent-skills-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 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 · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - agent-skills-toolkit

Project-level instructions and navigation for any agent (Claude Code, Codex, or other agentskills.io-compatible agents) working in this repository. This is the agent-facing counterpart to the human-facing INDEX.md.

What this project is

agent-skills-toolkit is a self-hosting plugin and a versioned Standard for authoring, validating, governing, and scaling cross-agent skill libraries. The normative rules live in STANDARD.md (the Advanced Skill Library Standard). The toolkit is built to its own Standard and, at v1, validates itself against that Standard in CI.

The single source of truth for the rules is STANDARD.md. The consolidated design and decision record is docs/internal/DESIGN.md.

Current state (read before assuming capabilities)

This repository declares tier: advanced (Gold) and self-validates against its own Standard in CI - the deterministic validation spine lives in scripts/. The full gate (Bronze U1-U9, U11-U18, Silver S1-S8, Gold G1-G10) is green and tier-report reports tier: advanced with an empty burndown, so the toolkit is a self-proving example of the Standard. See docs/internal/BOOTSTRAP.md for historical context: the one-time Bronze bootstrap that ended once the spine existed.

Components present on disk:

  • Skills: askit-evaluate (assess a skill or plugin against the Standard) plus the askit-build-* builder family - one builder per component type (skill, subagent, command, mcp, hook, chain-contract, agents-md, output-style, and more as the catalog fills), each with create/improve modes following docs/reference/builder-pattern.md. Core loop: askit-build-skill (create) -> askit-evaluate -> askit-build-skill (improve). The exact current component list lives in library.json and INDEX.md (this section stays terse on purpose - brevity is a feature).
  • Subagents: askit-skill-author (the bounded authoring delegate behind askit-build-skill) and askit-evaluator (the read-only assessment delegate behind askit-evaluate). Both are Claude-only (agent-targets: [claude]; Standard sec 3.3) and carry the askit- prefix like every other component (sec 8.2). The chain contract agents/_chain-permitted.yaml permits all five declared edges: askit-build-skill -> askit-skill-author, askit-build-skill -> askit-reviewer (the v1.7.0 craft pass, ADR 0037), askit-evaluate -> askit-evaluator, askit-evaluate -> askit-quality-grader, askit-evaluate -> askit-reviewer, and askit-skill-author -> askit-evaluator. Read the file, not this list, when it matters: agents/_chain-permitted.yaml is the contract and this is a convenience summary. The full per-subagent reference is docs/reference/subagents.md.
  • Commands: /askit-evaluate (maps-to: askit-evaluate) and /askit-build-skill (maps-to: askit-build-skill). Commands are Claude-native; on Codex the backing skill is the invocable form (Standard sec 3.2).
  • Scripts: the Node validation spine in scripts/ - conformance checks, generators (gen-index, gen-manifest, sync-agents-md), tier-report.mjs, the aggregate gate check.mjs, and evaluate.mjs.
  • Silver checks (Convergent, reqId S1-S8) and Gold checks (Advanced, reqId G1-G10) gate the declared tier: advanced alongside the Universal ones. S3 now validates components.skills, components.subagents, and components.commands against disk. S4 orphan detection is complete: a frontmatter chain: invocation not permitted by agents/_chain-permitted.yaml is an orphan error; a contract entry naming a missing component is a phantom error. S6 checks per-target manifest presence at the plugin level. S7 (command-contract) checks that every command declares a non-empty description and a maps-to resolving to exactly one on-disk skill or workflow (conditional on commands existing).
  • Hooks, workflows: none yet (later phases).

Read the full file on GitHub · 108 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. yesterday Changed 1e3551d7b57f
  2. 8d ago First seen · 108 lines · 1,732 tokens per session scan A ac08238905a4

Subscribe to this mod's changes

agent-skills-toolkit AGENTS.md is an instructions file published in the GitHub repository product-on-purpose/agent-skills-toolkit (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,732 tokens to every session, about $0.0087 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.

Building agentsClaude Codeagent-skillscodexconformancepluginskills
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens