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/jhlee0409/claude-plugins/mapgit clone --depth 1 https://github.com/jhlee0409/claude-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 | $0.02268 |
| Opus 5 | $0.00006 | $0.01134 |
| Sonnet 5 | $0.00002 | $0.00454 |
| Haiku 4.5 | $0.00001 | $0.00227 |
Grade A, and why
map 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 3d 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 — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAPI Map
Discover and track where your generated API code is used throughout your codebase. Essential for understanding impact of API changes.
EXECUTION INSTRUCTIONS
When /oas:map is invoked, Claude MUST perform these steps in order:
Step 0: MCP Dependency Check
Invoke skill: mcp-dependency
- Verify OpenAPI Sync MCP server is installed
- If not available, offer to install via
npm install -g @jhlee0409/openapi-sync-mcp - Only proceed after MCP is confirmed available
- Load config - Read
.openapi-sync.jsonfor generated file locations - Identify API exports - Find all exported functions, hooks, types
- Search codebase - Find all files that import these exports
- Build usage graph - Map API → Components/Pages/Hooks
- Store mapping - Save to
.openapi-sync.state.json - Report results - Show usage summary
Usage
# Full codebase mapping
/oas:map
# Map specific domain only
/oas:map --tag=users
# Map specific export
/oas:map --export=useUser
# Show detailed usage
/oas:map --verbose
Step 1: Load Configuration
1. Read .openapi-sync.json
2. Identify generated domains from entities/ or api/ directory
3. For each domain, find:
- API functions (e.g., userApi.getUser)
- Query hooks (e.g., useUser, useCreateUser)
- Types (e.g., User, CreateUserRequest)
Step 2: Identify API Exports
Scan generated API files and extract exports:
// From src/entities/users/api/users-queries.ts
export const useUsers = ... // Hook export
export const useUser = ... // Hook export
export const useCreateUser = ...// Hook export
// From src/entities/users/api/users-api.ts
export const userApi = { // API object export
list: ...,
get: ...,
create: ...,
}
// From src/entities/users/model/types.ts
export interface User { ... } // Type export
export interface CreateUserRequest { } // Type export
Build export registry:
{
"users": {
"hooks": ["useUsers", "useUser", "useCreateUser", "useUpdateUser", "useDeleteUser"],
"api": ["userApi"],
"types": ["User", "CreateUserRequest", "UpdateUserRequest", "UserFilters"]
}
}
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.
- 3d ago First seen · 377 lines · 12 tokens per session scan A a4d3050b8aed
map is a command published in the GitHub repository jhlee0409/claude-plugins (4 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 2,268 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
design-to-code
Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…
brand-setup
Configure a new brand profile with colors, fonts, logo, visual style, platforms, and compliance rules.
save
Save this conversation as a new or existing reusable context.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
screens
Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.
review
View your learning progress — quiz scores, weak areas, and what to study next.