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 commands/dropfan/claude-code-plugins/extractgit 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 | $0.00012 | $0.02293 |
| Opus 5 | $0.00006 | $0.01146 |
| Sonnet 5 | $0.00002 | $0.00459 |
| Haiku 4.5 | $0.00001 | $0.00229 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Working directory: !
pwd - Current date: !
date '+%Y-%m-%d %H:%M'
Task
Analyze the current conversation history and extract reusable patterns into Claude Code component files (Skill, Command, or Agent).
User arguments: $ARGUMENTS
Step 0: Load Configuration
- Use the Read tool to check if
.claude/skill-extractor.local.mdexists in the project root - If it exists, parse the YAML frontmatter between
---markers to extract:default_output_dir— default save directory (default:~/.claude/skills/)default_type— default component type:auto,skill,command, oragent(default:auto)
- If the file does not exist, silently use built-in defaults (no error)
- Settings are overridden by explicit command arguments
Step 1: Analyze Conversation History
Scan the conversation history and identify extractable patterns.
For long conversations: If the conversation history exceeds the available context window, focus on the most recent exchanges first, as they are most likely to contain the pattern the user wants to extract. If early parts of the conversation were truncated or not analyzed, inform the user: "Note: Only the most recent portion of the conversation was analyzed. If the pattern you want to extract is from earlier in the conversation, please describe it."
Look for:
Potential Skills (methodology / technique):
- A debugging approach that involved multiple analysis steps
- A review or evaluation methodology with specific criteria
- A problem-solving strategy with decision points
- Domain-specific knowledge applied to solve a problem
- A multi-step reasoning process that could be reused
Potential Commands (executable operation sequence):
- A repeated sequence of tool calls or shell commands
- A data processing or transformation pipeline
- A build, test, or deployment workflow
- A file generation or scaffolding process with clear parameters
Potential Agents (autonomous decision workflow):
- A complex analysis that required branching decisions
- A multi-file investigation with dynamic scope
- A code generation task requiring context-aware decisions
- A review or audit workflow with autonomous judgment
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 · 272 lines · 12 tokens per session scan A 1bc228d70645
extract is a command published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 26d ago), licensed MIT. It adds 12 tokens to every session and 2,293 once invoked, about $0.0001 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 commands, from other repositories
prompt
System instructions for writing effective prompts. Apply when generating commands, skills, agents, or any LLM instructions.
full
Run the full hope pipeline — intent, shape, target, freeze as needed — then execute.
status
Show tlive daemon, channel, and Codex companion status.
csv-to-numbers
Convert a CSV into a formatted Numbers workbook.
rust-critique
Deep code critique — read the target Rust code and apply the full review process. Evaluates soundness, ownership, error handling, type design, async correctness, performance, and architecture. Think like a senior Rust engineer giving honest feedback.
dotnet-structure
Analyze and recommend .NET backend solution and folder structure improvements. Checks projects, layers, oversized files, and boundary clarity.