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/add)<a href="https://agentmods.dev/commands/claude-market/marketplace/add"><img src="https://agentmods.dev/badge/commands/claude-market/marketplace/add/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.
<a href="https://agentmods.dev/commands/claude-market/marketplace/add"><img src="https://agentmods.dev/badge/commands/claude-market/marketplace/add.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00008 | $0.01293 |
| Opus 5 | $0.00004 | $0.00647 |
| Sonnet 5 | $0.00002 | $0.00259 |
| Haiku 4.5 | $0.00001 | $0.00129 |
Grade A, and why
add 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 10d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are helping a user add a new component to an existing Claude Code plugin.
Step 1: Select Plugin
Use Glob to find all plugins in ./*/.claude-plugin/plugin.json and ask the user which plugin they want to add to (or let them specify a path).
Step 2: Read Current Plugin Configuration
Read the plugin.json to understand what components already exist.
Step 3: Select Component Type to Add
Use AskUserQuestion to ask what type of component they want to add:
- Slash Command - Reusable prompt template for frequent operations
- Agent (Subagent) - Specialized AI assistant for specific tasks
- Hook - Automated workflow trigger at lifecycle events
- Skill - Domain-specific expertise invoked when needed
- MCP Server - External tool/data source via Model Context Protocol
Present these as clear options explaining what each type does.
Step 4: Collect Basic Information
Based on the selected component type, collect the essential information:
For Slash Command:
Use AskUserQuestion to collect:
- Command name (kebab-case, must not conflict with existing commands)
- Brief description (what does this command do?)
For Agent (Subagent):
Use AskUserQuestion to collect:
- Agent name (kebab-case, must not conflict with existing agents)
- Brief description (when should this agent be invoked?)
For Hook:
Use AskUserQuestion to collect:
- Hook name (kebab-case identifier)
- Brief description (what workflow does this automate?)
For Skill:
Use AskUserQuestion to collect:
- Skill name (kebab-case, must not conflict with existing skills)
- Brief description (what domain expertise does this provide?)
For MCP Server:
Use AskUserQuestion to collect:
- Server name (kebab-case identifier)
- Brief description (what tools/data does this provide?)
Step 5: Invoke Appropriate Builder Skill
Based on the component type selected, invoke the corresponding builder skill to handle the detailed generation:
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.
- 10d ago First seen · 187 lines · 8 tokens per session scan A 98cb53c90aa5
add is a command published in the GitHub repository claude-market/marketplace (22 stars, last pushed 10mo ago), licensed MIT. It adds 8 tokens to every session and 1,293 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.