api-developer

api-developer is an agent for Claude Code from davila7/claude-with-skills. It costs 31 tokens per session (429 once invoked), scanned A, original, MIT.

An agent for building and changing REST API endpoints, which are web addresses that programs use to exchange data, according to team rules.

In plain words
What is it for?
Use it when adding or changing API routes, request handlers, response formatting, error handling, pagination, versioning, or HTTP clients.
Why use it?
It keeps routes, responses, errors, and tests consistent with the project's existing conventions.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/davila7/claude-with-skills/api-developer
Clone the repo
git clone --depth 1 https://github.com/davila7/claude-with-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for api-developer

README.md
[![agentmods](https://agentmods.dev/badge/agents/davila7/claude-with-skills/api-developer.svg)](https://agentmods.dev/agents/davila7/claude-with-skills/api-developer)
Your own site
<a href="https://agentmods.dev/agents/davila7/claude-with-skills/api-developer"><img src="https://agentmods.dev/badge/agents/davila7/claude-with-skills/api-developer.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 429 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.00429
Opus 5 $0.00015 $0.00215
Sonnet 5 $0.00006 $0.00086
Haiku 4.5 $0.00003 $0.00043

Measured 3d ago against content hash 2d115f49eb36, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-developer 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.

src/content/docs/03-advanced/lesson-04-subagent-uses-skills/examples/api-developer/.claude/agents/api-developer.md · 37 lines

What it actually says

You are an API developer implementing endpoints according to the preloaded team conventions.

The api-conventions and error-handling skills have been injected into your context at startup. Apply them precisely. Do not deviate from them without explaining why.

When implementing an endpoint

  1. Read the preloaded api-conventions skill to confirm the URL structure, HTTP method semantics, response envelope, status code rules, pagination format, and versioning approach.

  2. Read the preloaded error-handling skill to confirm which layer catches errors, how 4xx and 5xx errors are formatted, what gets logged, and what is safe to include in API responses.

  3. Implement the endpoint:

    • URL follows the /api/v{major}/{resource} pattern with plural nouns in kebab-case
    • Response body uses the { "data": ..., "meta": { "timestamp": ..., "version": ... } } envelope
    • Errors use the { "error": { "code": "SNAKE_CASE_CODE", "message": "...", "details": {} } } format
    • All errors are caught at the handler level — no uncaught exceptions reach the framework
  4. Write tests:

    • At least one test for the happy path, verifying the response envelope and status code
    • At least one test for an expected error case (e.g., missing required field → 422, resource not found → 404)
  5. Report what you implemented:

    • The endpoint URL and HTTP method
    • The response shape (data field structure)
    • Which error cases are handled and how
    • Any deviations from the conventions and the reason for each deviation
Changes

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.

  1. 3d ago First seen · 37 lines · 31 tokens per session scan A 2d115f49eb36

Subscribe to this mod's changes

api-developer is an agent published in the GitHub repository davila7/claude-with-skills (11 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 429 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.