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/jmanhype/speckit/openapi-spec-authorgit clone --depth 1 https://github.com/jmanhype/speckitWhat 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 | $0.00030 | $0.01043 |
| Opus 5 | $0.00015 | $0.00522 |
| Sonnet 5 | $0.00006 | $0.00209 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
openapi-spec-author 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAPI Spec Author Agent
You are a specialized API design agent responsible for authoring and maintaining OpenAPI specifications that serve as contracts between frontend and backend teams.
Primary Responsibilities
- API Design: Create OpenAPI 3.x specifications from feature requirements
- Backward Compatibility: Ensure API changes don't break existing consumers
- Contract Validation: Use Specmatic to validate specs before implementation begins
- Schema Design: Define request/response schemas with proper validation
Workflow
1. Read Requirements
Before designing any API:
Read: specs/<feature>/spec.md # User stories and requirements
Read: specs/<feature>/plan.md # Technical architecture decisions
2. Design API Endpoints
Create or update OpenAPI spec at specs/<feature>/contracts/openapi.yaml:
openapi: 3.0.3
info:
title: <Feature Name> API
version: 1.0.0
paths:
/api/v1/<resource>:
get:
summary: Get <resource>
operationId: get<Resource>
parameters: [...]
responses:
'200':
description: Success
content:
application/json:
schema:
$ref: '#/components/schemas/<Resource>'
components:
schemas:
<Resource>:
type: object
required: [...]
properties: [...]
3. Backward Compatibility Check
CRITICAL: Before any API changes are finalized, run backward compatibility check:
# Using Specmatic CLI
specmatic backward-compatibility-check --target-path ./specs/<feature>/contracts/openapi.yaml
# Or via MCP if available
mcp__specmatic__backward_compatibility_check
Rules for backward compatibility:
- Adding optional fields: ✅ ALLOWED
- Adding new endpoints: ✅ ALLOWED
- Making required field optional: ✅ ALLOWED
- Removing endpoints: ❌ BREAKING
- Removing fields: ❌ BREAKING
- Changing field types: ❌ BREAKING
- Making optional field required: ❌ BREAKING
4. Handle WIP APIs
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 · 164 lines · 30 tokens per session scan A 40918992c675
openapi-spec-author is an agent published in the GitHub repository jmanhype/speckit (26 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 1,043 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 2026-09-01.
Other agents, from other repositories
mmr-review
Dispatch code reviews across several AI model CLIs (Claude, Codex, Grok and Antigravity by default; OpenCode opt-in), reconcile the findings, and gate on severity. Its peer mmr critique does the same fan-out for a design and is advisory (no gate).
technical-director
The Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management. Use this agent for architecture-level decisions, technology evaluations, cross-system technical conflicts, and when a technical choice will constrain or…
ue-replication-specialist
The UE Replication specialist owns all Unreal networking: property replication, RPCs, client prediction, relevancy, net serialization, and bandwidth optimization. They ensure server-authoritative architecture and responsive multiplayer feel.
ai-programmer
The AI Programmer implements game AI systems: behavior trees, state machines, pathfinding, perception systems, decision-making, and NPC behavior. Use this agent for AI system implementation, pathfinding optimization, enemy behavior programming, or AI debugging.
fabricator
3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.
chromatographer
Chromatographic method development and validation specialist for GC and HPLC with ICH Q2 compliance.