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.
npx agentmods add skills/dropfan/claude-code-plugins/extract-componentnpx skills add DropFan/claude-code-plugins --skill extract-componentgit clone --depth 1 https://github.com/DropFan/claude-code-pluginsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00110 | $0.00463 |
| Opus 5 | $0.00055 | $0.00231 |
| Sonnet 5 | $0.00022 | $0.00093 |
| Haiku 4.5 | $0.00011 | $0.00046 |
Grade A, and why
extract-component 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 yesterday.
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.
What it actually says
Extract Component
Overview
Analyze the current conversation history and extract reusable patterns into Claude Code components — Skills, Commands, or Agents. This skill identifies valuable methodology, operation sequences, and decision workflows from the conversation and generates properly formatted component files.
Intent Classification
When the user triggers this skill, determine the extraction intent:
- Explicit type — User specifies what they want (e.g., "extract a skill", "make this a command")
- Auto-detect — User wants extraction but hasn't specified the type (e.g., "extract pattern", "save this workflow")
Component Type Guidelines
- Skill — A methodology, technique, or approach for solving a category of problems. Skills describe how to think about a problem, with progressive disclosure of details. Best for: debugging strategies, review processes, design methodologies, domain-specific expertise.
- Command — A concrete sequence of operations that can be executed with parameters. Commands are action-oriented with clear inputs and outputs. Best for: build workflows, deployment steps, data processing pipelines, repetitive multi-step tasks.
- Agent — An autonomous workflow that requires decision-making, branching logic, and tool usage. Agents operate independently within defined boundaries. Best for: code review workflows, test generation, documentation creation, complex analysis tasks.
Execution
Route to the /skill-extractor:extract command with the user's intent:
- If the user specified a type, pass it as an argument (e.g.,
/skill-extractor:extract skill) - If auto-detect, pass no type argument — the command will analyze and recommend
Invoke the command: /skill-extractor:extract $ARGUMENTS
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.
- yesterday First seen · 33 lines · 110 tokens per session scan A f5187aaa530c
extract-component is a skill published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 26d ago), licensed MIT. It adds 110 tokens to every session and 463 once invoked, about $0.0006 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.
Other skills, from other repositories
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
agent-check
Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
hook-template
Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.
skill-check
Validate skill/command file format and structure. Use after creating or editing a skill, before committing skill changes, or when a skill fails to load or trigger.
agent-template
Generate custom agent from template. Use when creating a new subagent from scratch, or scaffolding an agent file with correct frontmatter.
session-relay
Continue real repository work between Claude Code, Codex CLI, and Grok Build with a privacy-bounded, drift-aware handoff packet. Use for cross-vendor takeover, context-limit checkpoints, multi-hop Claude→Codex→Grok relays, or receiving an existing Director packet. Use native resume commands for same-CLI history; never…