anthropic-reference

anthropic-reference is a skill for Claude Code, Codex from houarnu166/skillful-agent-system-builder. It costs 73 tokens per session (781 once invoked), scanned A, original, MIT.

A reference to Anthropic's official guidance for defining Skills and subagents, including their names, descriptions, tools, models, and permission settings.

In plain words
What is it for?
Use it when creating or reviewing Skills and subagents, choosing permission modes, or applying progressive disclosure, where basic instructions load before extra resources.
Why use it?
It helps you check whether these configuration files follow Anthropic's documented rules and structure.

Skill for Claude CodeCodex

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 skills/houarnu166/skillful-agent-system-builder/anthropic-reference
Any agent
npx skills add houarnu166/skillful-agent-system-builder --skill anthropic-reference
Clone the repo
git clone --depth 1 https://github.com/houarnu166/skillful-agent-system-builder

Made for: Claude Code, Codex.

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 anthropic-reference

README.md
[![agentmods](https://agentmods.dev/badge/skills/houarnu166/skillful-agent-system-builder/anthropic-reference.svg)](https://agentmods.dev/skills/houarnu166/skillful-agent-system-builder/anthropic-reference)
Your own site
<a href="https://agentmods.dev/skills/houarnu166/skillful-agent-system-builder/anthropic-reference"><img src="https://agentmods.dev/badge/skills/houarnu166/skillful-agent-system-builder/anthropic-reference.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 781 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00073 $0.00781
Opus 5 $0.00036 $0.00391
Sonnet 5 $0.00015 $0.00156
Haiku 4.5 $0.00007 $0.00078

Measured 5d ago against content hash 6310ca0d3d90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

anthropic-reference 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/skills/anthropic-reference/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anthropic Official Guide Reference

This Skill provides bundled core content from Anthropic official guidelines.


Skills Guide

→ See skills-guide.md for complete reference

Core Rules:

Field Constraints
name 1-64 chars, lowercase + hyphens, matches directory name
description 1-1024 chars, functionality + usage timing

Progressive Disclosure:

  1. Metadata (~100 tokens) - Always loaded
  2. Instructions (< 5000 tokens) - When activated
  3. Resources - When needed

Subagents Guide

→ See subagents-guide.md for complete reference

Core Fields:

Field Description
name Unique identifier in lowercase + hyphens
description Claude auto-delegation trigger
tools Allowed tools list
model haiku/sonnet/opus/inherit
permissionMode Permission mode

Permission Modes:

  • default - Standard confirmation
  • acceptEdits - Auto-accept edits
  • plan - Read-only
  • bypassPermissions - Skip all confirmations (caution)

Naming Rules

→ See naming-rules.md for validation rules

Common Rules:

  • 1-64 characters
  • Lowercase + numbers + hyphens only
  • No hyphen at start/end
  • No consecutive hyphens
  • No reserved words: anthropic, claude

Validation:

[[ "$name" =~ ^[a-z][a-z0-9-]*[a-z0-9]$ ]] && [ ${#name} -le 64 ]

Quick Reference

Skill Frontmatter

---
name: skill-name
description: |
  What it does. Use when: (1) scenario, (2) scenario.
  Triggers: "keyword1", "keyword2"
---

Agent Frontmatter

---
name: agent-name
description: |
  Role description.
  Trigger: Use when condition.
tools: [Read, Grep, Glob]
model: sonnet
permissionMode: default
---

Validation Scenarios

name Validation

  1. Lowercase + hyphens only?
  2. 1-64 characters?
  3. No hyphen at start/end?
  4. No consecutive hyphens?
  5. No reserved words?
  6. (Skill) Matches directory name?

Read the full file on GitHub · 131 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 131 lines · 73 tokens per session scan A 6310ca0d3d90

Subscribe to this mod's changes

anthropic-reference is a skill published in the GitHub repository houarnu166/skillful-agent-system-builder (23 stars, last pushed 6mo ago), licensed MIT. It adds 73 tokens to every session and 781 once invoked, about $0.0004 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens