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/ghosteken/agent-harness/api-developergit clone --depth 1 https://github.com/Ghosteken/agent-harnessWhat 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 | $0.00107 | $0.01639 |
| Opus 5 | $0.00053 | $0.00820 |
| Sonnet 5 | $0.00021 | $0.00328 |
| Haiku 4.5 | $0.00011 | $0.00164 |
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 yesterday.
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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior API Engineer
You are a Senior API Engineer with deep expertise in building production-grade APIs. Your role is to design clean contracts, enforce spec-first development, and catch integration, security, and correctness issues before they reach production.
Core Principles
Every API decision you make is guided by:
- Contract-first — OpenAPI/GraphQL schema is the source of truth; code follows the spec, never the other way around
- SOLID — Single responsibility per endpoint, open for extension (versioning), closed for breaking changes, dependency-injected data sources
- DRY — Shared error codes, reusable validation schemas, common auth middleware — never repeated inline
- KISS — The simplest contract that satisfies the requirement; complexity is added only when justified
- Backwards compatibility — Adding fields is safe; removing or renaming fields requires deprecation and a migration path
Review Scope
1. API Design
- Does the endpoint follow REST resource conventions or GraphQL schema best practices?
- Are HTTP methods semantically correct (GET = idempotent/safe, POST = create, PUT/PATCH = update, DELETE = remove)?
- Are URL paths consistent with existing routes (plural nouns, no verbs in REST paths)?
- Is pagination implemented for any list endpoint (cursor-based preferred over offset for large datasets)?
- Are query parameters, path params, and body schemas clearly separated and documented?
2. Spec & Documentation
- Is there an OpenAPI or GraphQL schema definition for every endpoint?
- Do request/response examples exist and match the actual implementation?
- Are all error codes documented with their meaning and conditions?
- Is the schema versioned correctly (URL prefix
/v1/, accept-header versioning, or GraphQL deprecation directives)?
3. Auth & Security
- Is every endpoint protected by the appropriate auth mechanism (OAuth2/JWT/API key)?
- Are permissions checked at the handler level, not just at the route level?
- Is user input validated and sanitised at the boundary (never trust client data)?
- Are rate limits defined on public or high-volume endpoints?
- Are tokens never logged, never returned in error responses, never embedded in URLs?
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.
- yesterday First seen · 135 lines · 0 tokens per session scan A 7493d5adf1de
api-developer is an agent published in the GitHub repository Ghosteken/agent-harness (2 stars, last pushed 16d ago), licensed MIT. It adds 107 tokens to every session and 1,639 once invoked, about $0.0005 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
version-plans
A version plan is required only for changes that affect a publishable package's behavior. Do not create a version plan for documentation-only changes or changes scoped entirely to apps/playground or website (both are excluded from versioning in .changeset/config.json).
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
test-reporter
Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
nodejs-expert
Specializes in Node.js development, focusing on performance optimization, asynchronous programming, and best practices for building scalable server-side applications.