agentmods.dev

cac-create-skill

cac-create-skill is a skill for Claude Code from getklaim/claude-auto-context. It costs 36 tokens per session (649 once invoked), scanned A, original, MIT.

A tool that turns detected coding-work patterns into SKILL.md instruction files, which describe repeatable workflows for an agent.

In plain words
What is it for?
Use it to review pending prompts in .claude-auto-context/skill-prompts/ and create a skill for a selected detected pattern.
Why use it?
It saves you from manually rewriting recurring workflow prompts and keeps the creation process tied to pending pattern files.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the claude-auto-context plugin — 6 skills, 2 agents, 6 hooks shipped together

not rated 10repo 5mo ago A scan 36 tokens original MIT

Good fit Use it to review pending prompts in .claude-auto-context/skill-prompts/ and create a skill for a selected detected pattern.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/getklaim/claude-auto-context/cac-create-skill
View source ↗ getklaim/claude-auto-context
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.

Any agent
npx skills add getklaim/claude-auto-context --skill cac-create-skill
Clone the repo
git clone --depth 1 https://github.com/getklaim/claude-auto-context

Made for: Claude Code.

Or install claude-auto-context, the plugin that ships this one along with the rest of its 6 skills, 2 agents, 6 hooks.

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 cac-create-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/getklaim/claude-auto-context/cac-create-skill.svg)](https://agentmods.dev/skills/getklaim/claude-auto-context/cac-create-skill)
Your own site
<a href="https://agentmods.dev/skills/getklaim/claude-auto-context/cac-create-skill"><img src="https://agentmods.dev/badge/skills/getklaim/claude-auto-context/cac-create-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 649 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00036 $0.00649
Opus 5 $0.00018 $0.00324
Sonnet 5 $0.00007 $0.00130
Haiku 4.5 $0.00004 $0.00065

Measured 7d ago against content hash 65bf89b44d25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

cac-create-skill 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 7d 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/cac-create-skill/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Skill from Detected Pattern

Review pending skill-prompt files generated by Auto Context's skills-agent and delegate to skill-creator to produce high-quality SKILL.md files.

Arguments

  • No argument: list all pending prompt files, ask user to select
  • {slug}: process specific prompt file matching the slug (e.g., /cac-create-skill edit-test-commit)

Procedure

Step 1: Check skill-creator availability

  1. Run: command -v skill-creator
  2. If not found, output: 
    skill-creator not found. Install from https://github.com/anthropics/skills
    and STOP.

Step 2: Scan pending prompt files

  1. Read all .md files in .claude-auto-context/skill-prompts/
  2. Filter: skip files containing the bare line applied, rejected, or failed
  3. Remaining files are pending prompt files

Step 3: No argument -- interactive selection

  1. Display numbered list of pending prompt files (timestamp + slug extracted from filename)
  2. If 0 pending: output "No pending skill prompts found." and STOP
  3. Ask user to select which prompt to process

Step 4: Process selected prompt

  1. Read the full prompt file content
  2. Run: skill-creator <prompt_file_path>
  3. If skill-creator exits non-zero:
    • Append ## Status\nfailed to the prompt file
    • Output error details and STOP

Step 5: Locate generated SKILL.md

  1. After skill-creator completes, identify the generated SKILL.md path
    • Check skill-creator stdout for the output path
    • If not reported, scan .claude/skills/ for the newest SKILL.md file
  2. Read the generated SKILL.md and display a summary to the user

Step 6: Mark prompt file as applied

  1. Append to the end of the prompt file: 
    
## Status
applied

## Applied At
<ISO 8601 timestamp>

## Generated Skill
<path to generated SKILL.md>

Step 7: Output summary

Report:

  • Skill name and description
  • SKILL.md file path

Error Handling

  • If .claude-auto-context/skill-prompts/ directory does not exist: output "No skill-prompts directory found. The skills-agent has not run yet." and STOP
  • If skill-creator is not installed: output install guidance and STOP
  • If skill-creator fails: mark prompt as failed, report error

Read the full file on GitHub · 84 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. 7d ago First seen · 84 lines · 36 tokens per session scan A 65bf89b44d25

Subscribe to this mod's changes

cac-create-skill is a skill published in the GitHub repository getklaim/claude-auto-context (10 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 649 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.

Building agents
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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens