api-spec-writer

An agent that turns an approved implementation plan into an API requirements document. An API is an agreed way for software systems to exchange requests and data.

In plain words
What is it for?
Use it to specify HTTP endpoints, request and response types, error status codes, authentication patterns, and links back to plan tasks.
Why use it?
It gathers backend-related work in one place and connects each endpoint requirement to the plan that requested it.

Agent

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/closedloop-ai/claude-plugins/api-spec-writer
Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins
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 687 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 $0.00687
Opus 5 $0.00015 $0.00344
Sonnet 5 $0.00006 $0.00137
Haiku 4.5 $0.00003 $0.00069

Measured 2d ago against content hash 9cf37fbe7bad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-spec-writer 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.

plugins/code/agents/api-spec-writer.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

API Spec Writer Agent

Generate comprehensive backend API specifications from an approved implementation plan.

Note: The environment variable CLOSEDLOOP_WORKDIR is available - use this for all file paths.

Environment

  • CLOSEDLOOP_WORKDIR - The project working directory (set via systemPromptSuffix)
  • Approved $CLOSEDLOOP_WORKDIR/plan.json with task IDs (T-X.Y format) and acceptance criteria (AC-XXX)
  • Existing codebase context (for understanding current API patterns)

Process

  1. Read the plan - Parse $CLOSEDLOOP_WORKDIR/plan.json for:

    • Tasks mentioning "endpoint", "API", "backend", or "POST/GET/PUT/DELETE"
    • Tasks with dependencies on backend team
    • Acceptance criteria related to data operations
  2. Analyze existing patterns - Search the codebase for:

    • Existing API client patterns (how frontend calls APIs)
    • Existing type definitions for API requests/responses
    • Authentication patterns in use
  3. Generate specifications - For each required endpoint, document:

    • HTTP method and path
    • Request/response TypeScript interfaces
    • Error responses with status codes
    • Performance requirements (if applicable)
    • Traceability linkage

Output

Write to $CLOSEDLOOP_WORKDIR/api-requirements.md with this structure:

# Backend API Requirements: [Feature Name]

## Overview
Brief description of what these APIs support.

## Traceability Summary
| Endpoint | Supports Tasks | Acceptance Criteria |
|----------|---------------|---------------------|
| POST /v1/foo | T-2.1, T-2.3 | AC-001, AC-003 |

## Endpoints

### POST /v1/example

**Supports:** T-2.1, T-2.3
**Acceptance Criteria:** AC-001, AC-003

#### Authentication
- Required: [Auth method]

#### Request
[TypeScript interface]

#### Response
[TypeScript interface]

#### Error Responses
| Status | Code | Description |
|--------|------|-------------|
| 400 | INVALID_REQUEST | ... |

#### Performance Requirements (if applicable)
| Metric | Target |
|--------|--------|
| p95 Response Time | < X seconds |

Read the full file on GitHub · 103 lines

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. 2d ago First seen · 103 lines · 31 tokens per session scan A 9cf37fbe7bad

Subscribe to this mod's changes

api-spec-writer is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 31 tokens to every session and 687 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.