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 skills add Notysoty/openagentskills --skill breaking-change-detectorgit clone --depth 1 https://github.com/Notysoty/openagentskillsWrote 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.
[](https://agentmods.dev/skills/notysoty/openagentskills/breaking-change-detector)<a href="https://agentmods.dev/skills/notysoty/openagentskills/breaking-change-detector"><img src="https://agentmods.dev/badge/skills/notysoty/openagentskills/breaking-change-detector/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.
<a href="https://agentmods.dev/skills/notysoty/openagentskills/breaking-change-detector"><img src="https://agentmods.dev/badge/skills/notysoty/openagentskills/breaking-change-detector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.01720 |
| Opus 5 | $0.00012 | $0.00860 |
| Sonnet 5 | $0.00005 | $0.00344 |
| Haiku 4.5 | $0.00002 | $0.00172 |
Grade A, and why
Breaking Change Detector 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breaking Change Detector
What this skill does
This skill directs the agent to compare two versions of a codebase, API schema, or interface definition and systematically identify every change that could break existing callers. It classifies each change by severity, explains why it is breaking, and provides a concrete migration hint so consumers know exactly what they need to update.
Use this before publishing a new package version, before deploying an API change that existing clients depend on, or during a code review to catch unintended contract changes.
How to use
Claude Code / Cline
Copy this file to .agents/skills/breaking-change-detector/SKILL.md in your project root.
Then ask:
- "Use the Breaking Change Detector skill to compare the old and new versions of our API."
- "I changed
src/auth/index.ts. Use the Breaking Change Detector skill to find any breaking changes."
Provide: the old version (paste, file path, or git ref) and the new version.
Cursor
Add the instructions below to your .cursorrules or paste them into the Cursor AI pane. Then share both the old and new code side by side.
Codex
Paste both versions clearly labeled as "OLD VERSION" and "NEW VERSION" and ask Codex to follow the instructions below.
The Prompt / Instructions for the Agent
When asked to detect breaking changes, follow this process:
Step 1 — Establish what constitutes the public contract
Before comparing, identify what is "public" — i.e., what external callers or consumers depend on:
- For a library: all exported functions, types, interfaces, and constants
- For a REST API: all endpoints (method + path), request body shapes, response shapes, status codes, and headers
- For a database schema: table names, column names, data types, nullability, and unique constraints
- For a TypeScript/JavaScript module: all
exportstatements
Changes to internal/private code are not breaking changes unless they affect something observable from outside.
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.
- 9d ago First seen · 186 lines · 23 tokens per session scan A d269fb4d0a6b
Breaking Change Detector is a skill published in the GitHub repository Notysoty/openagentskills (9 stars, last pushed 26d ago), licensed MIT. It adds 23 tokens to every session and 1,720 once invoked, about $0.0001 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 skills, from other repositories
API Versioning Testing
Testing API versioning strategies including URL path, header, and query parameter versioning with backward compatibility validation.
API Backward Compatibility Testing
Automated detection of breaking API changes including response format changes, removed endpoints, type changes, and deprecation enforcement.
Business Rule Extractor
Produces a documented inventory of the implicit business rules, edge cases, and bug-as-feature behaviors that tangled code encodes, with real input-to-output examples, so a rewrite preserves behavior. Use when you are about to rewrite, port, or replace legacy code whose only specification is the source, and you see…
refactor
Guides a refactor, cleanup, or restructure with the right decomposition. Use when the user asks to refactor, simplify, extract, or modernize code.
pre-publish-review
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…
work-with-pr
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the…