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 skills/vthinkdeveloper/vthink-agent-toolkit/generate-endpointnpx skills add vthinkdeveloper/vthink-agent-toolkit --skill generate-endpointgit clone --depth 1 https://github.com/vthinkdeveloper/vthink-agent-toolkitWhat 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 | $0.00055 | $0.00895 |
| Opus 5 | $0.00028 | $0.00447 |
| Sonnet 5 | $0.00011 | $0.00179 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
generate-endpoint scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- How to test them (e.g., `curl` examples or test command) How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Endpoint
Generate a complete CRUD endpoint for a new resource, adapting to the project's existing structure and conventions.
Step 1: Detect Project Structure
Before generating anything, explore the project to understand how it's organized:
Find the routes/controller layer
Search for common patterns:
Glob: src/routes/*.js, app/routes/*.py, routes/*.js, controllers/*.js
Grep: "router.get\|app.get\|@app.route\|@router.get"
Find the database/model layer
Glob: src/db.js, src/models/*.js, db/*.js, models/*.py, prisma/schema.prisma
Grep: "CREATE TABLE\|sequelize.define\|mongoose.model\|db.prepare"
Find the test layer
Glob: tests/*.test.js, __tests__/*.js, test_*.py, spec/**/*.js
Check package.json / requirements for framework clues
Read package.json or requirements.txt to identify the framework and test runner.
If structure is ambiguous
Ask the user:
- "Where should I add the routes? (e.g.,
src/app.js,src/routes/)" - "Where should I add the database queries? (e.g.,
src/db.js,src/models/)" - "What test framework is this project using?"
Step 2: Ask for Resource Details
Ask the user:
- What is the resource name? (should be lowercase plural, e.g.,
products,orders) - What columns/fields does this resource need beyond
idandcreated_at?
Example prompt:
"I'll generate a CRUD endpoint for
products. What fields does a product have? For example:name (text),price (decimal),in_stock (boolean). I'll includeidandcreated_atautomatically."
Step 3: Read Existing Patterns
Read 1-2 existing route handlers and db functions to understand the conventions:
- How are responses structured?
{ data: [...] }or flat arrays? - How are errors handled? Try/catch with status codes? Error middleware?
- What HTTP status codes are used for create (201 vs 200)?
- What is the naming style for functions?
getAllProductsvsfetchProductsvslist_products?
Follow the patterns you find. Do not introduce new patterns.
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.
- 2d ago First seen · 101 lines · 55 tokens per session scan A de9d353ac75b
generate-endpoint is a skill published in the GitHub repository vthinkdeveloper/vthink-agent-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 895 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…