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 skills/marcusgoll/spec-flow/breaking-change-detectornpx skills add marcusgoll/Spec-Flow --skill breaking-change-detectorgit clone --depth 1 https://github.com/marcusgoll/Spec-FlowWrote 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/marcusgoll/spec-flow/breaking-change-detector)<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/breaking-change-detector"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/breaking-change-detector.svg" alt="Measured on agentmods" 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 | $0.00072 | $0.07343 |
| Opus 5 | $0.00036 | $0.03671 |
| Sonnet 5 | $0.00014 | $0.01469 |
| Haiku 4.5 | $0.00007 | $0.00734 |
Grade A, and why
breaking-change-detector scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Unknown clients (logged as "curl/7.0", "Python requests") How it starts
The opening of the file, as written. The whole thing — 1,119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breaking changes destroy trust and break client applications:
- Removing API endpoints breaks existing integrations
- Changing request/response formats breaks client code
- Dropping database columns causes data loss
- Modifying function signatures breaks dependent code
- Changing authentication schemes locks out users
This skill acts as a safety gate that:
- Detects breaking changes before they're implemented
- Warns developers with severity levels (CRITICAL, HIGH, MEDIUM)
- Suggests safe migration paths (versioning, deprecation, backward compatibility)
- Validates changes against project's API versioning strategy (from api-strategy.md)
- Blocks deployment if critical breaking changes lack migration plan
The result: Zero unintentional breaking changes, smooth API evolution, maintained client trust.
<quick_start> <trigger_pattern> Auto-trigger when detecting these modification patterns:
API modifications:
- "Remove endpoint", "Delete route", "Drop API"
- "Change request/response", "Modify payload", "Update schema"
- "Rename endpoint", "Change HTTP method"
Database modifications:
- "Drop column", "Remove field", "Delete table"
- "Change column type", "Modify constraint"
- "Rename column/table"
Interface modifications:
- "Change function signature", "Modify parameters"
- "Remove method", "Delete class"
- "Change return type" </trigger_pattern>
<basic_workflow> Step 1: Detect modification type
- User: "Remove the /api/v1/users endpoint"
- Detected: API endpoint deletion (BREAKING)
Step 2: Analyze breaking change risk
- Check: Is endpoint currently in use?
- Check: Are there clients depending on it?
- Check: What's the versioning strategy?
Step 3: Determine severity
- CRITICAL: Removing production endpoint with active users
- HIGH: Changing required field in request
- MEDIUM: Adding required parameter to function
Step 4: Suggest safe migration path
- Option A: Deprecate endpoint (mark for removal in v2.0)
- Option B: Version API (keep v1, add v2 without endpoint)
- Option C: Redirect to replacement endpoint
Step 5: Validate against api-strategy.md
- Check project's versioning policy
- Verify deprecation timeline
- Confirm backward compatibility requirements
Step 6: Block or warn
- CRITICAL → BLOCK implementation until migration plan approved
- HIGH → WARN and require justification
- MEDIUM → LOG for review </basic_workflow>
<immediate_value> Without breaking-change-detector:
Developer: "Let me remove this old /api/users endpoint"
*Removes endpoint*
*Deploys*
Result: 15 mobile apps break, support tickets flood in, emergency rollback
With breaking-change-detector:
Developer: "Let me remove this old /api/users endpoint"
Detector: "🚨 BREAKING CHANGE DETECTED
Removing: GET /api/users
Severity: CRITICAL
Impact: 15 active clients (iOS app, Android app, web dashboard)
This will break:
- Mobile app v2.1-2.5 (500K users)
- Partner integrations (3 companies)
Safe migration path:
1. Deprecate endpoint (add X-Deprecated header)
2. Announce removal timeline (90 days)
3. Monitor usage (track who's still calling it)
4. Version API (v2 without endpoint, v1 keeps it)
5. Remove after 90 days when usage drops to 0
Cannot proceed without migration plan. Would you like me to implement the deprecation strategy?"
Developer: "Yes, let's deprecate it properly"
Result: Smooth transition, zero broken clients, maintained trust
</immediate_value> </quick_start>
Parse user request to identify change type:
API endpoint changes:
- Removal: "remove", "delete", "drop" + "endpoint", "route", "API"
- Modification: "change", "update", "modify" + "request", "response", "payload"
- Renaming: "rename", "move" + "endpoint"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 1,119 lines · 72 tokens per session scan A 54d82a2fa1e5
breaking-change-detector is a skill published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It adds 72 tokens to every session and 7,343 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
improve-codebase-architecture
Avaliar a arquitetura de um codigo existente, encontrar friccoes comprovaveis, gerar obrigatoriamente um relatorio HTML e propor refatoracoes incrementais com impacto tecnico e de produto. Usar quando o usuario pedir melhoria arquitetural, crescimento sustentavel, reducao de acoplamento, modulos mais testaveis ou um…
code-review
Run a comprehensive code review.
skill-scope-control
Analisa se alterações, diffs e PRs continuam alinhados ao objetivo declarado, identificando escopo extra e propondo manter, separar ou justificar.
refactoring-assistant
Guide refactoring decisions and large-scale code improvements. Use when: refactoring code, legacy modernization, technical debt, rewrite decisions. Keywords: refactor, rewrite, legacy, strangler, technical debt, 重構, 重寫, 技術債.
code-review-assistant
Systematic code review checklist and pre-commit quality gates for PRs. Use when: reviewing pull requests, checking code quality, before committing code. Keywords: review, PR, pull request, checklist, quality, commit, 審查, 檢查, 簽入.
code-simplifier
Use when user asks to simplify, clean up, or refactor recently modified code for readability, consistency, or maintainability without changing behavior, especially after implementation and before broader review.