agentmods.dev

extract-skill

extract-skill is a skill for Claude Code from mostafa-drz/claude-skills. It costs 134 tokens per session (3,162 once invoked), scanned B, original, MIT.

A conversation-review tool that turns repeated feedback, workflows, and corrections into reusable skills or single memory rules.

In plain words
What is it for?
Use it to capture coding practices, recurring setups, and step-by-step workflows from a conversation. It can also preview candidates or limit them to skills or memory rules.
Why use it?
It helps avoid losing useful lessons from earlier work and reduces the chance of proposing rules that already exist.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Claude Code.

not rated 4repo changed 1mo ago B scan 134 tokens original MIT

Good fit Use it to capture coding practices, recurring setups, and step-by-step workflows from a conversation. It can also preview candidates or limit them to skills or memory rules.

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

Made for: Claude Code.

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 extract-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/extract-skill/github.svg)](https://agentmods.dev/skills/mostafa-drz/claude-skills/extract-skill)
Your own site
<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/extract-skill"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/extract-skill/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 extract-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/mostafa-drz/claude-skills/extract-skill"><img src="https://agentmods.dev/badge/skills/mostafa-drz/claude-skills/extract-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,162 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00134 $0.03162
Opus 5.5 $0.00054 $0.01265
Sonnet 5.5 $0.00027 $0.00632
Haiku 4.5 $0.00013 $0.00316

Measured 1mo ago against content hash 7bb0429a235d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

extract-skill scanned grade B with 1 finding 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 1mo 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

1. _List existing skills: `ls ~/.claude/skills/`_
code/extract-skill/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

extract-skill

Turn the current conversation into a reusable skill or memory rule. From experience → reusable artifact.

Preferences

On startup, use Read to load ~/.claude/skills/extract-skill/preferences.md. If it does not exist, treat as "no preferences set" — proceed with sensible defaults.

Context

On startup, use Bash to:

  1. List existing skills: ls ~/.claude/skills/
  2. Read ~/.claude/skills/SKILLS_GUIDE.md (inventory + conventions)
  3. Read ~/.claude/projects/<project-slug>/memory/MEMORY.md if accessible (the user's auto-memory index)

Skip any that fail. The point is to know what already exists so we don't propose duplicates.

Command routing

Check $ARGUMENTS:

  • help → display help then stop
  • config → interactive setup, then stop
  • reset → delete ~/.claude/skills/extract-skill/preferences.md, confirm, stop
  • --memory-only → only propose memory entries, never skills
  • --skill-only → only propose skills, never memory entries
  • --dry-run → print candidates + classification, do not create anything
  • anything else (including empty) → run the skill

Help

extract-skill — Capture conversation learnings as a skill or memory rule

Usage:
  /extract-skill                Scan this conversation, propose skill/memory candidates
  /extract-skill --memory-only  Only propose memory entries (single-rule preferences)
  /extract-skill --skill-only   Only propose skills (multi-step workflows)
  /extract-skill --dry-run      Print candidates + classification, do not create anything
  /extract-skill config         Set preferences
  /extract-skill reset          Clear preferences
  /extract-skill help           This help

Examples:
  /extract-skill                After a chat where you taught Claude how to do X
  /extract-skill --dry-run      Preview what would be captured before committing

Current preferences:
  (loaded from preferences.md, shown above)

Config

Use AskUserQuestion to collect:

Read the full file on GitHub · 278 lines

Files

What ships with it

1 file 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. 1mo ago Changed · +3 lines 7bb0429a235d
  2. 1mo ago First seen · 275 lines · 134 tokens per session scan B d057f3a6732a

Subscribe to this mod's changes

extract-skill is a skill published in the GitHub repository mostafa-drz/claude-skills (4 stars, last pushed yesterday), licensed MIT. It adds 134 tokens to every session and 3,162 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsClaude CodeMemory and contextai-toolsautomationclaudeclaude-skillsdeveloper-tools
Related

Other skills, from other repositories

skill-learner

Persistent correction system that captures mistakes from skills or Claude behavior and ensures they never repeat across sessions. Use whenever the user indicates something went wrong — "that's wrong", "fix this", "not what I wanted", "learn from this", "don't do that again", "esto está mal", "aprende de esto", "no…

j4rk0r/claude-skills · 140 tokens

shipkit-work-memory

Log session progress and save resume state. Infers from conversation and git. Triggers: 'log progress', 'session summary', 'checkpoint', 'save progress', 'end session'.

stefan-stepzero/shipkit · 42 tokens

shipkit-claude-md

Update CLAUDE.md with learnings, preferences, or project context. Use when user says "update claude.md", "add to claude.md", or wants to persist something.

stefan-stepzero/shipkit · 45 tokens

init-project-memory

Use when the user says "init memory", "set up memory", "scaffold memory", "init project memory", or invokes /init-project-memory — creates the .claude/ session memory system in a new project.

jkm-4314/claude-code-skills · 48 tokens

session-update

Use when the user says "update session", "log progress", "checkpoint session", or invokes /session-update — especially before /clear or handoff.

jkm-4314/claude-code-skills · 33 tokens

milestone

Use when tracking multi-session development work, resuming context from previous conversations, planning phased features, or capturing architectural decisions. Triggers: 'milestone', 'retomar', 'dónde lo dejé', 'seguimos con', 'estado del proyecto', 'qué falta', 'siguiente tarea', 'qué hicimos la última vez'…

j4rk0r/claude-skills · 164 tokens