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.
git clone --depth 1 https://github.com/claude-market/marketplaceWrote 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.
[](https://agentmods.dev/commands/claude-market/marketplace/edit)<a href="https://agentmods.dev/commands/claude-market/marketplace/edit"><img src="https://agentmods.dev/badge/commands/claude-market/marketplace/edit.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00007 | $0.01739 |
| Opus 5 | $0.00003 | $0.00870 |
| Sonnet 5 | $0.00001 | $0.00348 |
| Haiku 4.5 | $0.00001 | $0.00174 |
Grade A, and why
edit 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping a user edit an existing component in a Claude Code plugin using natural language descriptions.
Step 1: Select Plugin
Use Glob to find all plugins in ./*/.claude-plugin/plugin.json and ask the user which plugin they want to edit (or let them specify a path).
Step 2: Read Current Plugin Configuration
Read the plugin.json to understand what components exist and their current configuration.
Step 3: List Available Components
Display all available components organized by type:
- Commands: List all command files with their descriptions (from frontmatter if available)
- Agents: List all agent files with their descriptions
- Hooks: List all hook configurations
- Skills: List all skill files with their descriptions
- MCP Servers: List all MCP server configurations
Use AskUserQuestion to ask which component they want to edit. Present options based on what exists in the plugin.
Step 4: Read the Selected Component
Read the full content of the selected component file to understand its current implementation.
Display a summary of the component to the user:
- Component name and type
- Current description
- Key functionality (summarized)
- File path
Step 5: Understand the Desired Edit
Ask the user to describe what changes they want to make in natural language.
Prompt: "Please describe the changes you want to make to this component. Be as specific or general as you like."
The user might say things like:
- "Add validation for email addresses"
- "Make it ask for confirmation before deleting"
- "Change the default model from haiku to sonnet"
- "Add better error handling"
- "Include examples in the documentation"
- "Make it work with TypeScript files too"
- "Update the description to be clearer"
- "Add support for multiple arguments"
Step 6: Route to Appropriate Builder Skill
Based on the component type, route the editing task to the corresponding builder skill with context about the existing component and desired 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.
- 8d ago First seen · 256 lines · 7 tokens per session scan A 35af5834de54
edit is a command published in the GitHub repository claude-market/marketplace (22 stars, last pushed 10mo ago), licensed MIT. It adds 7 tokens to every session and 1,739 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.