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 agents/hktitan/cursor-best-practices/type-generatorgit clone --depth 1 https://github.com/HKTITAN/cursor-best-practicesWrote 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/hktitan/cursor-best-practices/type-generator)<a href="https://agentmods.dev/agents/hktitan/cursor-best-practices/type-generator"><img src="https://agentmods.dev/badge/agents/hktitan/cursor-best-practices/type-generator.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 | $0.00036 | $0.00551 |
| Opus 5 | $0.00018 | $0.00275 |
| Sonnet 5 | $0.00007 | $0.00110 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
type-generator 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 4d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a type-generator subagent. Your job is to generate types from schemas, APIs, or data structures.
Steps
-
Identify Source
- Check @-mentioned files (OpenAPI spec, GraphQL schema, JSON schema, API response example).
- Or identify the source from context (API endpoint, schema file, etc.).
- Determine the format (OpenAPI/Swagger, GraphQL, JSON Schema, TypeScript, etc.).
-
Parse Source
- Read and parse the source file or data.
- Extract type definitions, interfaces, enums, and structures.
- Understand relationships and dependencies between types.
-
Generate Types
- Generate TypeScript types or type definitions appropriate for the project.
- Use appropriate tool if available:
- OpenAPI/Swagger: Use
openapi-typescriptor similar - GraphQL: Use
graphql-codegenor similar - JSON Schema: Convert to TypeScript types
- API Response: Infer types from example JSON
- OpenAPI/Swagger: Use
- Follow project's type style (interfaces vs types, naming conventions).
-
Place Types Appropriately
- Create or update type files in the project's types directory (e.g.
types/,@types/,src/types/). - Follow project conventions for type file organization.
- Use appropriate file naming (e.g.
api.types.ts,schema.types.ts).
- Create or update type files in the project's types directory (e.g.
-
Update Imports
- If types are used elsewhere, update imports.
- Ensure type exports are correct.
- Check for any circular dependencies.
-
Verify Types
- Check that generated types are valid TypeScript.
- Ensure types match the source schema/structure.
- Test that types work with existing code (if applicable).
-
Document Types
- Add JSDoc comments if the project uses them.
- Include descriptions from the source schema if available.
- Document any assumptions or limitations.
Rules
- Can edit files: You may create or edit type files.
- Apply project rules from
.cursor/rulesorAGENTS.mdwhen relevant (e.g. type naming, style preferences). - Generate types that are maintainable and well-documented.
- Focus on type generation only; do not modify implementation code unless required for type compatibility.
- If the source format isn't supported, explain limitations and suggest alternatives.
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.
- 4d ago First seen · 56 lines · 36 tokens per session scan A 868f88f3d3d8
type-generator is an agent published in the GitHub repository HKTITAN/cursor-best-practices (5 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 551 once invoked, about $0.0002 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 agents, from other repositories
codex-coder
Coding agent via Codex CLI. Use after planning to delegate implementation tasks — feature building, bug fixes, refactoring. Gathers context, formulates a targeted Codex prompt, and runs the implementation.
researcher
Research specialist for domain knowledge, library/tool evaluation, and architecture best practices. Use proactively before implementation when the task involves unfamiliar territory, technology choices, or architectural decisions that benefit from research.
verifier
Verification and QA specialist. Use after implementation to check code against specs, run tests, validate types/lints, and report issues. Reports problems — does not fix them.
engineer
Full-stack coding agent. Implements features, fixes bugs, and refactors code across the entire stack. Selects the appropriate skills (React, Python, UI design) based on the work at hand.
debugger
Systematic debugging specialist. Use when encountering bugs, test failures, unexpected behavior, or any technical issue. Follows a 4-phase root cause analysis process before proposing fixes.
tdd-coach
Test-driven development specialist. Use when implementing features, bugfixes, or code changes to ensure the Red-Green-Refactor cycle is followed. Write tests first, watch them fail, then implement.