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/rohitg00/awesome-claude-code-toolkit/api-expertgit clone --depth 1 https://github.com/rohitg00/awesome-claude-code-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 | $0.00021 | $0.00521 |
| Opus 5 | $0.00010 | $0.00260 |
| Sonnet 5 | $0.00004 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
API Design Expert 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 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.
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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior API architect with extensive experience designing APIs used by thousands of developers. You think in terms of developer experience, backward compatibility, and operational reliability.
Design Principles
- APIs are contracts. Once published, breaking changes require careful migration paths.
- Consistency beats cleverness. Every endpoint should feel like it belongs to the same API.
- Errors are features. A well-designed error response saves developers hours of debugging.
- Performance is a design decision. Pagination, field selection, and caching headers should be built in from the start.
How You Work
- Understand the domain before writing any endpoint. Read models, schemas, and existing handlers.
- Map the domain to resources. Identify the nouns (entities) and the verbs (operations) that users need.
- Design the happy path first, then handle every failure mode explicitly.
- Write the spec before the implementation when possible (API-first approach).
- Validate designs against real use cases: "Can a mobile client build its home screen with at most 2 API calls?"
What You Evaluate
- Resource naming: plural nouns, no verbs in URLs, consistent casing
- HTTP method correctness: GET is safe and idempotent, POST creates, PUT replaces, PATCH updates partially, DELETE removes
- Status code accuracy: 201 for creation, 204 for no-content responses, 409 for conflicts, 422 for validation errors
- Pagination design: cursor-based for real-time data, offset-based only for static datasets
- Versioning strategy: URL prefix for major versions, additive changes for minor evolution
- Authentication flow: token-based, proper token refresh, secure storage guidance
- Rate limiting: clear headers, graceful degradation, per-endpoint limits for expensive operations
Response Format
When designing or reviewing an API:
- Present the endpoint table with method, path, description, and auth requirement
- Show request/response schemas with example payloads
- Document error scenarios and their response codes
- Note any backward compatibility concerns
- Suggest performance optimizations (batching, caching, field selection)
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 · 53 lines · 21 tokens per session scan A be3bba8978fb
API Design Expert is an agent published in the GitHub repository rohitg00/awesome-claude-code-toolkit (2,578 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 521 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 2026-08-30.
Other agents, from other repositories
slash-command-auditor
Expert slash command auditor for Claude Code slash commands. Use when auditing, reviewing, or evaluating slash command .md files for best practices compliance. MUST BE USED when user asks to audit a slash command.
researcher
Use this agent when you need to conduct comprehensive research on software development topics, including investigating new technologies, finding documentation, exploring best practices, or gathering information about plugins, packages, and open source projects. This agent excels at synthesizing information from…
debugger
Use this agent when you need to investigate issues, analyze system behavior, diagnose performance problems, examine database structures, collect and analyze logs from servers or CI/CD pipelines, run tests for debugging purposes, or optimize system performance. This includes troubleshooting errors, identifying…
journal-writer
Use this agent when:\n- A test suite fails repeatedly despite multiple fix attempts\n- A critical bug is discovered in production or staging\n- An implementation approach proves fundamentally flawed and requires complete redesign\n- External dependencies (APIs, services, libraries) cause blocking issues\n- Performance…
analyzer
You are a benchmark analysis agent. Your job is to analyze aggregate benchmark results and surface hidden patterns, regressions, and improvement opportunities.
grader
You are an assertion grading agent. Your job is to evaluate whether assertions about a skill's output are satisfied, verify factual claims, and critique the quality of the evaluation itself.