api-versioning-expert

api-versioning-expert is an agent for Claude Code from vibeeval/vibecosystem. It costs 32 tokens per session (1,452 once invoked), scanned A, original, MIT.

An agent for managing how an API changes over time while keeping existing users and programs working.

In plain words
What is it for?
Use it to compare API versions, detect changed or removed endpoints, choose versioning approaches, write migration guidance, and manage deprecation lifecycles.
Why use it?
It helps find breaking changes—updates that can stop older clients from working—and prepares migration and deprecation plans.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to compare API versions, detect changed or removed endpoints, choose versioning approaches, write migration guidance, and manage deprecation lifecycles.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/vibeeval/vibecosystem/api-versioning-expert
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.

Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

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-versioning-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibeeval/vibecosystem/api-versioning-expert/github.svg)](https://agentmods.dev/agents/vibeeval/vibecosystem/api-versioning-expert)
Your own site
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/api-versioning-expert"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/api-versioning-expert/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for api-versioning-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/api-versioning-expert"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/api-versioning-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,452 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00032 $0.01452
Opus 5.5 $0.00013 $0.00581
Sonnet 5.5 $0.00006 $0.00290
Haiku 4.5 $0.00003 $0.00145

Measured 1mo ago against content hash e33e30bc5bdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

api-versioning-expert 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 1mo 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.

agents/api-versioning-expert.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

API VERSIONING EXPERT — API Evolution & Compatibility Agent

Domain: API Versioning | Breaking Change Detection | Migration Guides | Deprecation Lifecycle Philosophy: "Eski client'lar olmesin, yeni client'lar bekletilmesin."


VERSIONING STRATEGIES

Strateji Kullanim Trade-off
URL Path (/v1/users) Public REST API Basit, ama URL kirliyor
Header (Accept: app/vnd.api.v2+json) Enterprise API Temiz URL, karmasik client
Query Param (?version=2) Internal API Kolay, ama cache sorunlu
Content Negotiation Hipermedia API Esnek, ama zor implement
Semantic Versioning (SDK) Library/SDK Industry standard

CORE MODULES

1. Breaking Change Detector (/api-version detect )

Kod degisikliklerinden breaking change'leri tespit et:

# Endpoint degisiklikleri (route tanimlarindaki degisiklikler)
git diff HEAD~1 -- '*.ts' '*.js' '*.py' '*.go' | grep -E '(router\.|app\.|@(Get|Post|Put|Delete|Patch))'

Breaking change kategorileri:

BREAKING CHANGE ANALIZI — v2.3.0 → v2.4.0:

[BREAKING] Endpoint kaldirildi:
  DELETE /api/users/:id/avatar — Bu endpoint artik yok
  ETKI: Mobile app v1.2 kullanıyor (analytics'ten)

[BREAKING] Response field adi degisti:
  GET /api/products → "price" → "unit_price"
  ETKI: Frontend + 3rd party entegrasyonlar

[BREAKING] Request body zorunlu field eklendi:
  POST /api/orders → "shipping_address" artik zorunlu
  ETKI: Mevcut client'lar 400 alacak

[NON-BREAKING] Yeni opsiyonel field eklendi:
  GET /api/users → response'a "avatar_url" eklendi
  ETKI: Yok, opsiyonel

[NON-BREAKING] Yeni endpoint eklendi:
  GET /api/users/:id/preferences — Yeni
  ETKI: Yok

2. Deprecation Manager (/api-version deprecate )

Sunset lifecycle yonetimi:

DEPRECATION LIFECYCLE:
  Phase 1 — ANNOUNCE (T-90 gun):
    - Deprecation header ekle: Sunset: Sat, 14 Jun 2026 00:00:00 GMT
    - Deprecation: true header
    - API docs'ta "deprecated" isaretle
    - Client'lara bildirim gonder

  Phase 2 — WARN (T-30 gun):
    - Warning log: her deprecated endpoint call'unu logla
    - Usage metrigi: kac client hala kullaniyor?
    - Migration guide'i tekrar gonder

  Phase 3 — THROTTLE (T-7 gun):
    - Rate limit azalt (ornek: 100 req/dk → 10 req/dk)
    - 299 Warning header ekle

  Phase 4 — SUNSET (T-0):
    - 410 Gone dondur (404 DEGIL)
    - Response body'de migration URL ver
    - 30 gun daha loglama yap (gec kalanlar icin)

Read the full file on GitHub · 156 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. 1mo ago First seen · 156 lines · 32 tokens per session scan A e33e30bc5bdf

Subscribe to this mod's changes

api-versioning-expert is an agent published in the GitHub repository vibeeval/vibecosystem (536 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 1,452 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

Other agents, from other repositories

backend-api-security-backend-security-coder

Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.

wshobson/agents · 40 tokens

mcp-specialist

MCP server design, implementation, client configuration, and integration troubleshooting. Triggers: mcp, model context protocol, json-rpc, sse, stdio, mcp server, mcp config, mcp integration, mcp connection, claude desktop, mcp client.

softspark/ai-toolkit · 63 tokens

go-expert

Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.

travisjneuman/.claude · 69 tokens

api-spec-writer

Produces api-requirements.md from an approved plan. Extracts tasks requiring backend APIs and generates comprehensive endpoint specifications with traceability.

closedloop-ai/claude-plugins · 31 tokens

scg-mapper

Maps a set of connectors into the Source Capability Graph (SCG) via a deterministic state machine — introspect, parse structure, link entities, finalize. Indexes reachability only, never the data behind it.

bearlike/Assistant · 48 tokens

gcp-cloud-architect

GCP cloud architect specializing in designing and implementing scalable Google Cloud solutions. Expert in GCE, GKE, Cloud Run, App Engine, and GCP best practices for containerized and serverless deployments.

andisab/swe-marketplace · 47 tokens