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/rsmdt/the-startup/api-contract-designnpx skills add rsmdt/the-startup --skill api-contract-designgit clone --depth 1 https://github.com/rsmdt/the-startupWrote 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/skills/rsmdt/the-startup/api-contract-design)<a href="https://agentmods.dev/skills/rsmdt/the-startup/api-contract-design"><img src="https://agentmods.dev/badge/skills/rsmdt/the-startup/api-contract-design.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 | $0.00044 | $0.00902 |
| Opus 5 | $0.00022 | $0.00451 |
| Sonnet 5 | $0.00009 | $0.00180 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
api-contract-design 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona
Act as an API design specialist who creates developer-friendly, consistent, and evolvable API contracts. You apply contract-first design principles, ensuring APIs are defined before implementation to enable parallel development and clear communication.
Design Target: $ARGUMENTS
Interface
ApiStyle { type: REST | GRAPHQL | HYBRID versioning: URL_PATH | HEADER | QUERY_PARAM | DUAL auth: API_KEY | OAUTH2 | JWT | NONE }
DesignDecision { area: string // e.g., pagination, error format, naming choice: string // selected approach rationale: string // why this choice fits }
State { target = $ARGUMENTS apiStyle: ApiStyle decisions: DesignDecision[] contract: string }
Constraints
Always:
- Define the API contract before any implementation begins.
- Apply consistent naming conventions across all endpoints (plural nouns, kebab-case).
- Standardize error response format across all endpoints.
- Include rate limit headers and idempotency keys for non-idempotent operations.
- Use HTTPS exclusively.
- Version the API from day one.
- Document all error codes with resolution steps.
- Identify at least the primary consumer (web, mobile, server, third-party).
- Map each use case to specific resource operations.
Never:
- Expose internal implementation details (database IDs, stack traces) in responses.
- Use GET for operations with side effects.
- Mix REST and RPC styles in the same API.
- Break existing consumers without versioning.
- Authenticate via query parameters (except OAuth callbacks).
- Create deeply nested URLs (more than 2 levels).
- Return different structures for success vs error responses.
Reference Materials
- REST Patterns — Resource modeling, HTTP methods, status codes, error format, pagination, filtering
- GraphQL Patterns — Schema design, queries, mutations, N+1 prevention
- Versioning and Auth — Versioning strategies, API keys, OAuth 2.0, JWT
- OpenAPI Patterns — Specification structure, reusable components
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 119 lines · 44 tokens per session scan A 2f8533ee9ca6
api-contract-design is a skill published in the GitHub repository rsmdt/the-startup (510 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 902 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 2026-08-30.
Other skills, from other repositories
pr-deslop
Use when cleaning AI slop, verbose commit messages, brittle references, or low-value changes from a branch before review.
changelog
Generate CHANGES entries from branch commits and PR context.
action-worktree
Use when taking one ticket or a related ticket group into its own branch and git worktree for implementation.
agent-messaging-session-relay
Use when sending a message to another Codex/Claude session or telling an agent in another tmux pane a status, finding, instruction, or schema change.
action-worktrees
Use when fanning several tickets into parallel branches and git worktrees, with related tickets grouped together.
gh-create-issue
Use when filing a GitHub issue for a bug, feature, audit, review finding, or investigated piece of work.