agent-father

agent-father is a skill for Claude Code, Codex from lexfrei/ccc. It costs 31 tokens per session (2,990 once invoked), scanned A, original, BSD-3-Clause.

A guide for creating, checking, and rewriting Claude Code subagents—smaller agents that handle specific tasks. It explains how their instructions and activation descriptions work.

In plain words
What is it for?
Use it to create a new subagent or review an existing agent file against Claude Code documentation standards.
Why use it?
It helps prevent agents from being configured incorrectly or hiding important activation rules where Claude cannot see them.

Skill for Claude CodeCodex

Part of the agent-father plugin — 1 skill shipped together

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/lexfrei/ccc/agent-father
Any agent
npx skills add lexfrei/ccc --skill agent-father
Clone the repo
git clone --depth 1 https://github.com/lexfrei/ccc

Made for: Claude Code, Codex.

Or install agent-father, the plugin that ships this one along with the rest of its 1 skill.

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-father

README.md
[![agentmods](https://agentmods.dev/badge/skills/lexfrei/ccc/agent-father.svg)](https://agentmods.dev/skills/lexfrei/ccc/agent-father)
Your own site
<a href="https://agentmods.dev/skills/lexfrei/ccc/agent-father"><img src="https://agentmods.dev/badge/skills/lexfrei/ccc/agent-father.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,990 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 $0.00031 $0.02990
Opus 5 $0.00015 $0.01495
Sonnet 5 $0.00006 $0.00598
Haiku 4.5 $0.00003 $0.00299

Measured 4d ago against content hash c2b497f17497, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-father 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 4d 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.

skills/agent-father/skills/agent-father/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create new or review and rewrite existing Claude Code subagents.

Mode Detection

  • If the user provides an existing agent file path or pastes agent content → Review mode
  • If the user asks to create a new agent → Create mode
  • If unclear → ask the user

Review Mode: Audit and Rewrite an Existing Agent

Read the agent file and audit it against every rule below. Fix ALL issues found.

Visibility Model (CRITICAL — most common mistake)

Claude sees TWO separate things at TWO separate times:

  1. BEFORE delegation: Claude reads ONLY the description field from frontmatter. Nothing else. The body is invisible.
  2. AFTER delegation: The subagent receives ONLY the body as its system prompt, plus basic env details (working directory, platform). It does NOT get the full Claude Code system prompt.

Consequences:

  • "When to Activate" / "MANDATORY activation for" sections in the body are WASTED — Claude never sees them before delegating
  • Activation triggers, keywords, and conditions MUST be in description
  • The body should contain ONLY what the agent needs DURING execution: role, workflow, patterns, constraints, checklists
  • If useful trigger info is in the body but not in description — move it to description

Audit Checklist

Frontmatter:

  • name — lowercase, hyphens only
  • description — contains ALL activation triggers and keywords; written for Claude (the delegator), not for humans; states plainly when to delegate instead of shouting "Use proactively" / "MUST BE USED"
  • description — quoted when it contains a colon followed by a space, otherwise the YAML fails to parse (this rule is stated again under Create mode on purpose: each mode is a separate firing moment, and a check absent where it must fire does not fire)
  • tools — omitted unless there is a concrete reason to restrict, and the reason is written down. Per-agent allowlists cost more in maintenance than they return: every tool the agent turns out to need has to be added later, and the list is the first thing to go stale
  • permissionMode — set only on project and user agents; a plugin-shipped agent drops it, along with hooks and mcpServers
  • model — set explicitly if agent needs a specific capability level
  • effort — set only when the work needs a different reasoning level than the session's
  • No unnecessary fields (don't add fields just because they exist)

Read the full file on GitHub · 248 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. 4d ago First seen · 248 lines · 31 tokens per session scan A c2b497f17497

Subscribe to this mod's changes

agent-father is a skill published in the GitHub repository lexfrei/ccc (9 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 31 tokens to every session and 2,990 once invoked, about $0.0002 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.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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