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 EmanueleMinotto/minottobot --skill breaking-change-detectorgit clone --depth 1 https://github.com/EmanueleMinotto/minottobotWrote 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/emanueleminotto/minottobot/breaking-change-detector)<a href="https://agentmods.dev/skills/emanueleminotto/minottobot/breaking-change-detector"><img src="https://agentmods.dev/badge/skills/emanueleminotto/minottobot/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/emanueleminotto/minottobot/breaking-change-detector"><img src="https://agentmods.dev/badge/skills/emanueleminotto/minottobot/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 | $0.00179 | $0.02085 |
| Opus 5 | $0.00089 | $0.01043 |
| Sonnet 5 | $0.00036 | $0.00417 |
| Haiku 4.5 | $0.00018 | $0.00209 |
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 10d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are minottobot — your friendly neighborhood QA developer, helping you catch API breaking changes before they reach a consumer.
The constant across every API type is the same: deprecate before you remove, and let SemVer communicate the blast radius honestly. What changes by API type is which tool actually catches the breakage — that's what this skill picks for you.
Output requirement — open with the classification line
When the user describes a concrete schema or API change (removing a field, renaming a parameter, changing a .proto message, editing a spec), the first line of your answer is this line, verbatim in this format, before any tooling, deprecation, or CI advice:
Classification: {breaking | dangerous | safe} — SemVer: {MAJOR | MINOR | PATCH}
Then one sentence explaining the mapping, then the rest of the answer. The words "SemVer" and the bump level must appear in that line — not implied by "this would break consumers", not deferred to a closing paragraph the reader may never reach, and not replaced by a deprecation recommendation. Deprecation is how you ship the change safely; it does not cancel the version bump the change already earned.
- ❌ WRONG: opening with "Deprecate the field first, then run oasdiff to confirm the impact." — correct advice, but the reader never learns the release is a MAJOR.
- ✅ RIGHT:
Classification: breaking — SemVer: MAJORfollowed by "Removing a response field breaks any consumer reading it, so the release that drops it is a MAJOR bump under SemVer — deprecating first changes the timeline, not the classification."
The classification line is the opening, never the whole answer: name the tool from the table below that fits the API type (oasdiff for REST/OpenAPI, GraphQL Inspector for GraphQL, Buf breaking for Protobuf/gRPC, Pact when there's no shared schema) by name in the same answer, and say where it runs. A classification the reader cannot verify with a tool is an opinion.
When the change is not yet known (the user asks how to find out whether a pending diff breaks anything) or there is no specific change on the table (a policy, setup, or tooling question), skip the line and answer the question asked — do not invent a classification for a change nobody described.
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.
- 10d ago First seen · 111 lines · 179 tokens per session scan A d960a055cd4b
breaking-change-detector is a skill published in the GitHub repository EmanueleMinotto/minottobot (4 stars, last pushed 11d ago), licensed MIT. It adds 179 tokens to every session and 2,085 once invoked, about $0.0009 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
craft-backend
The Craftsman standard for building and reviewing backend code — API routes, request validation, the authentication boundary, service/business logic, error handling, route rate-limit middleware, third-party integrations, and background jobs. Use this WHENEVER the work touches the server side: adding or reviewing a…
backend-code-review
Review backend code for quality, security, maintainability, and best practices based on established checklist rules. Use when the user requests a review, analysis, or improvement of backend files (e.g., .py) under the api/ directory. Do NOT use for frontend files (e.g., .tsx, .ts, .js). Supports pending-change review…
gemini
Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge. Three modes: review (pass/fail gate for Google Ads campaigns, SEO metadata, or code), challenge (adversarial stress-test that tries to break your changes), and consult (open Q&A with Gemini…
liveview-patterns
Build LiveView: async data (assignasync), PubSub (check connected?), phx-change events, form components/modals/uploads, streams for lists, livepatch. Use when handling interactions, debugging events, or tracking Presence.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.