agentmods.dev

ai-dev-os-extract

ai-dev-os-extract is a skill for Claude Code from yunbow/ai-dev-os-plugin-claude-code. It costs 43 tokens per session (398 once invoked), scanned A, original, MIT.

A rule-extraction tool that studies the difference between AI-generated code and the corrected version to identify reusable coding guidelines. It can group findings by areas such as naming, security, or architecture.

In plain words
What is it for?
Use it to compare code changes, propose one-line rules, check for duplicates, suggest where rules belong, and ask for confirmation before adding them.
Why use it?
It helps capture lessons from code reviews so the same problems are less likely to recur in later AI-assisted work.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter; mentions CLAUDE.md.

Part of the ai-dev-os plugin — 11 skills, 3 agents, 3 hooks shipped together

not rated 2repo 7mo ago A scan 43 tokens original MIT

Good fit Use it to compare code changes, propose one-line rules, check for duplicates, suggest where rules belong, and ask for confirmation before adding them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-extract
View source ↗ yunbow/ai-dev-os-plugin-claude-code
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 yunbow/ai-dev-os-plugin-claude-code --skill ai-dev-os-extract
Clone the repo
git clone --depth 1 https://github.com/yunbow/ai-dev-os-plugin-claude-code

Made for: Claude Code.

Or install ai-dev-os, the plugin that ships this one along with the rest of its 11 skills, 3 agents, 3 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 ai-dev-os-extract

README.md
[![agentmods](https://agentmods.dev/badge/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-extract/github.svg)](https://agentmods.dev/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-extract)
Your own site
<a href="https://agentmods.dev/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-extract"><img src="https://agentmods.dev/badge/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-extract/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-dev-os-extract

Your own site · 80×15
<a href="https://agentmods.dev/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-extract"><img src="https://agentmods.dev/badge/skills/yunbow/ai-dev-os-plugin-claude-code/ai-dev-os-extract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 398 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 $0.00043 $0.00398
Opus 5.5 $0.00017 $0.00159
Sonnet 5.5 $0.00009 $0.00080
Haiku 4.5 $0.00004 $0.00040

Measured 2mo ago against content hash fea494e44030, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-dev-os-extract 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 2mo 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/ai-dev-os-extract/SKILL.md · 66 lines

What it actually says

AI Dev OS Rule Harvesting

Execution Flow

1. Get Target File Diff

Retrieve the diff between AI-generated code (before) and corrected code (after) using git diff.

2. Analyze the Diff

Infer "why it was changed" rather than "what changed". Classify patterns:

  • Naming convention violation → common/naming.md
  • Security gap → common/security.md
  • Architecture deviation → frameworks/*/overview.md

3. Generate Rule Candidates

  • One-line rule format: "MUST: Always call auth() in server actions"
  • Check for duplicates against existing guidelines

4. User Confirmation

  • "Would you like to add the following rules?"
  • Suggest the target file (L3 guideline) for each rule
  • Suggest links to L2 principles

5. Append to Guideline Files

  • Include traceability comments
  • Record extraction date and rationale

Output Example

## Rule Extraction Results

### Detected Patterns (N rules extracted)

#### Rule 1: [Rule Name]
- **From**: [File name] (line number)
- **Pattern**: [Detected pattern]
- **Proposed Rule**: `MUST: [Rule content]`
- **Target**: [Target guideline file]
- **Traces to**: [L2 principle reference]

### Add these rules? [Y/n/edit]

Language

Respond in the same language as the project's CLAUDE.md file.

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. 2mo ago First seen · 66 lines · 43 tokens per session scan A fea494e44030

Subscribe to this mod's changes

ai-dev-os-extract is a skill published in the GitHub repository yunbow/ai-dev-os-plugin-claude-code (2 stars, last pushed 7mo ago), licensed MIT. It adds 43 tokens to every session and 398 once invoked, about $0.0002 per session on Opus 5.5. 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 CodeCode reviewai-codingai-dev-osanthropicclaudecontext-engineering
Related

ai-dev-os-extract compared with skills from other repositories

ai-dev-os-extract next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ai-dev-os-extractyunbow/ai-dev-os-plugin-claude-codeSkill27mo agoMITA43Claude Code
guideline-checkeryunbow/ai-dev-os-rules-typescriptSkill26mo agoMITA27Claude Code
memstack-development-code-reviewercwinvestments/memstackSkill42913d agoMITA75Claude Code
shardcwinvestments/memstackSkill42913d agoMITA28Claude Code
design-patternsFlorianBruniaux/claude-code-ultimate-guideSkill6.4ktodayCC-BY-SA-4.0A59Claude Code
audit-agents-skillsFlorianBruniaux/claude-code-ultimate-guideSkill6.4ktodayCC-BY-SA-4.0A41Claude Code
eval-rulesFlorianBruniaux/claude-code-ultimate-guideSkill6.4ktodayCC-BY-SA-4.0A82Claude Code