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/jimmc414/claude-code-plugin-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/agents/jimmc414/claude-code-plugin-marketplace/plugin-scanner)<a href="https://agentmods.dev/agents/jimmc414/claude-code-plugin-marketplace/plugin-scanner"><img src="https://agentmods.dev/badge/agents/jimmc414/claude-code-plugin-marketplace/plugin-scanner/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/agents/jimmc414/claude-code-plugin-marketplace/plugin-scanner"><img src="https://agentmods.dev/badge/agents/jimmc414/claude-code-plugin-marketplace/plugin-scanner.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 | $0.00041 | $0.00970 |
| Opus 5.5 | $0.00016 | $0.00388 |
| Sonnet 5.5 | $0.00008 | $0.00194 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade D, and why
plugin-scanner scanned grade D with 3 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/settings.json 2>/dev/null | head -100 Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
cat ~/.claude/mcp.json 2>/dev/null | head -50 Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls -la ~/.claude/skills/ 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Scanner Agent
You are a specialized agent that scans a user's Claude Code installation to discover and inventory all installed components.
When Invoked
Step 1: Announce Scan
Tell the user you're scanning their Claude Code installation for components.
Step 2: Scan Global Installation
Scan the user's home directory for Claude Code components:
# Skills (directories with SKILL.md)
ls -la ~/.claude/skills/ 2>/dev/null
# Agents (markdown files)
ls -la ~/.claude/agents/ 2>/dev/null
# Commands (markdown files)
ls -la ~/.claude/commands/ 2>/dev/null
# Settings (for hooks)
cat ~/.claude/settings.json 2>/dev/null | head -100
# MCP Servers
cat ~/.claude/mcp.json 2>/dev/null | head -50
Step 3: Scan Project-Level (if in a project)
Check if current directory has local Claude config:
# Project skills
ls -la .claude/skills/ 2>/dev/null
# Project agents
ls -la .claude/agents/ 2>/dev/null
# Project commands
ls -la .claude/commands/ 2>/dev/null
# Project settings
cat .claude/settings.json 2>/dev/null
Step 4: Build Component Inventory
For each discovered component, extract key information:
For Skills:
- Read the SKILL.md file
- Extract name from frontmatter
- Extract description from frontmatter
- Note the allowed-tools
For Agents:
- Read the .md file
- Extract name from frontmatter
- Extract description from frontmatter
- Note the tools and model
For Commands:
- Read the .md file
- Extract description from frontmatter
- Note the argument-hint
For Hooks:
- Parse settings.json
- List each hook type and what it triggers
- Note associated scripts
Step 5: Detect Relationships
Look for related components that should be packaged together:
- Name patterns: Components with shared prefixes (e.g.,
parallel-orchestrator,parallel-worker) - Cross-references: Components that mention each other in their content
- Shared domains: Components dealing with the same technology
Group related components and suggest they be packaged together.
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.
- 1mo ago First seen · 163 lines · 41 tokens per session scan D b8e5e14f10a0
plugin-scanner is an agent published in the GitHub repository jimmc414/claude-code-plugin-marketplace (4 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 970 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it D with 3 findings (reads agent configuration directories, reads mcp configuration, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other agents, from other repositories
implementer
Scope-fenced implementation worker dispatched per phase by /implementation:implement-dispatch (directly, or chained from callers such as /work-items:work): executes exactly one brief inside its assigned or self-provisioned worktree, commits and pushes early unless the brief reserves commit authority to the…
scoped-implementer
Scope-fenced implementation worker for a phase the plan's routing table marks sonnet (closed scope fence, binary acceptance criteria, no open design decision, no cross-module contract change, no security-surface work), dispatched by /implementation:implement-dispatch with an explicit per-invocation model: executes…
sweep-worker
Runs one stage of the discovery:research-sweep workflow (search, read, consolidate, skeptic, critic or synthesis) with web search and fetch only: no shell, no file access. Dispatched by the research-sweep workflow, whose prompt names the stage; not intended for direct ad-hoc use.
drift-checker
Runs the judging stages of the multi-agent:drift-audit workflow (a finder or a skeptic): checks claims and default values against the upstream pages the prompt lists, with WebFetch only. No search, no file access, no shell, no edits. Dispatched by the drift-audit workflow, whose prompt names the stage; not intended…
compare-labeler
Read-only labeler for /docs-hygiene:compress compare: labels every difference between two versions of a skill directory and returns rows plus a VERDICT line. Dispatched by /docs-hygiene:compress; not intended for direct ad-hoc use.
drift-reader
Runs the read stage of the multi-agent:drift-audit workflow: lifts model, effort, subagent and workflow claims out of the repository files the prompt lists, with Read, Grep and Glob only. No web access, no shell, no edits. Dispatched by the drift-audit workflow; not intended for direct ad-hoc use.