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 sigistry/marketplace --skill openapi-driftgit clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/sigistry/marketplace/openapi-drift)<a href="https://agentmods.dev/skills/sigistry/marketplace/openapi-drift"><img src="https://agentmods.dev/badge/skills/sigistry/marketplace/openapi-drift.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 | $0.00106 | $0.00925 |
| Opus 5 | $0.00053 | $0.00463 |
| Sonnet 5 | $0.00021 | $0.00185 |
| Haiku 4.5 | $0.00011 | $0.00093 |
Grade A, and why
openapi-drift 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 7d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAPI Drift
Purpose
Provide a standardized, static methodology for keeping an API specification and its implementation in sync, without starting the server. Two problems live here: drift (the spec and the code disagree about what the API does) and breaking-change classification (does a change to the surface break existing clients?). Both are read off the source: OpenAPI/Swagger YAML/JSON or GraphQL SDL on one side, and framework route/validation/serializer code on the other. This is the gap left when Optic (the popular OSS drift tool) was archived in January 2026.
The two-model method
- Build the spec model: endpoints (path + method), parameters, request/response schemas per status, required/nullable, security. From OpenAPI
paths/components, or GraphQLtype/input/enum/field args. - Build the code model: the same facts, read from the framework (routes, validators, DTOs, serializers, status calls). See
references/drift-signals.md. - Align by path template + method (normalize
/x/{id}≡/x/:id) or GraphQL type + field. - Diff each axis and record which side each fact came from, that provenance is what lets you assign authority.
Drift classes and default authority
| Drift class | Example | Usually authoritative |
|---|---|---|
| Undocumented endpoint | Route in code, absent from spec | Code (add to spec) |
| Phantom endpoint | Endpoint in spec, no handler | Code (remove/implement), confirm intent |
| Missing param | Handler reads ?status, spec omits it |
Code |
| Param type mismatch | Spec integer, code parses string |
Investigate; often code |
| Response field mismatch | Code returns a field the schema lacks | Depends, may be intentionally internal |
| Status-code mismatch | Code returns 409, spec lists only 200/400 |
Code |
| Nullability mismatch | Spec nullable: false, code can return null |
Code (bug) or spec (fix) |
| Auth mismatch | Spec security: [], code requires a token |
Code |
"Authoritative" is a default, not a law: a deliberate public contract can be the source of truth over an accidental code change. When ambiguous, surface it for a human rather than silently rewriting either side.
What ships with it
2 files 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.
- 7d ago First seen · 45 lines · 106 tokens per session scan A 9552dada62f5
openapi-drift is a skill published in the GitHub repository sigistry/marketplace (3 stars, last pushed 3d ago), licensed MIT. It adds 106 tokens to every session and 925 once invoked, about $0.0005 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
design-code-architecture
Guided journey from an app idea to a deliberate architecture: boundaries, domain model, data decisions, and resilience, making only the expensive-to-reverse decisions and deferring the rest. Orchestrates eight skills phase by phase - clean-architecture, domain-driven-design, system-design, ddia-systems…
system-design
Design scalable distributed systems using structured approaches for load balancing, caching, database scaling, and message queues. Use when the user mentions "system design", "scale this", "high availability", "rate limiter", "design a URL shortener", "design Twitter", "design Uber", "design a news feed", "system…
architect
This skill should be used when the user asks to "design system architecture", "evaluate microservices vs monolith", "create architecture diagrams", "analyze dependencies", "choose a database", "plan for scalability", "make technical decisions", or "review system design".
backend
This skill should be used when the user asks to "design REST APIs", "optimize database queries", "implement authentication", "build microservices", "review backend code", "set up GraphQL", "handle database migrations", or "load test APIs".
mcp-server-dev
Create MCP servers — multi-tool services exposed via Model Context Protocol. Use this skill whenever users mention MCP servers, building servers, server scaffolding, tool registration, or want to package tools for distribution via uvx or npx. Also use when the conversation involves stdio transport, server lifecycle…
mcp-tool-dev
Create MCP tools — individual tool functions exposed via Model Context Protocol. Use this skill whenever users mention MCP tools, tool handlers, tool functions, tool definitions, or want to add capabilities to an MCP server. Also use when the conversation involves designing tool schemas, writing tool descriptions, or…