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 commands/sigistry/marketplace/spec-syncgit 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/commands/sigistry/marketplace/spec-sync)<a href="https://agentmods.dev/commands/sigistry/marketplace/spec-sync"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/spec-sync.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 | $0.00021 | $0.01109 |
| Opus 5 | $0.00010 | $0.00554 |
| Sonnet 5 | $0.00004 | $0.00222 |
| Haiku 4.5 | $0.00002 | $0.00111 |
Grade A, and why
spec-sync 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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compare the API specification in $ARGUMENTS (or auto-discover it: openapi.yaml/openapi.json, swagger.{yaml,json}, *.graphql/schema.graphql, or a buf/proto file) against the actual handler code, report every point of drift, and reconcile it. This is a static analysis, no server is started and no requests are sent. Load the openapi-drift skill for the drift-signal catalog and breaking-change rules.
Process
Step 1: Locate the spec and detect the framework
Find the spec, then detect the web framework so you know how to read routes, params, and schemas from code:
| Framework | Signal |
|---|---|
| Express | express(), app.get/post, router.<verb>, routes/ |
| Fastify | fastify(), fastify.route, schema: route options |
| NestJS | @Controller, @Get/@Post, *.controller.ts, @ApiProperty |
| Koa | koa-router, router.<verb>, ctx.body |
| FastAPI | APIRouter, @app.get, response_model=, Pydantic models |
| Django REST Framework | urls.py, ViewSet, serializers.py, *_views.py |
| Flask | @app.route, @bp.route, blueprints |
| Spring Boot | @RestController, @GetMapping, @RequestBody, DTOs |
| Go net/http / Gin | http.HandleFunc, mux.HandleFunc, r.GET, gin.Context |
| Rails | config/routes.rb, *_controller.rb, respond_to, strong params |
For GraphQL, compare the SDL (type, input, enum, field args, nullability !) against resolver signatures and the code-first schema builders (Nexus, TypeGraphQL, Strawberry, gqlgen, graphql-ruby).
Step 2: Build both models and diff them
Extract the endpoint surface from both sides and align them by path+method (or GraphQL type+field). Compare on these axes and record which side each fact came from:
| Axis | Spec side | Code side |
|---|---|---|
| Route exists | paths./x.get |
a registered handler for GET /x |
| Path/query params | parameters[] |
route tokens, req.query, @Query, request.args |
| Request body schema | requestBody.content.schema |
validation schema / DTO / serializer |
| Response schema | responses.200.content.schema |
returned object / response_model / DTO |
| Status codes | declared responses keys |
res.status(), raise HTTPException, render status: |
| Required vs optional | required: [...], nullable |
validator .optional(), Optional[...], ? |
| Auth/security | security, securitySchemes |
auth middleware/decorators/guards |
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.
- 4d ago First seen · 59 lines · 21 tokens per session scan A 7cc7a2aaa8cc
spec-sync is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 1,109 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 commands, from other repositories
build
Guided feature development with approval gates at each phase.
release
Generate changelog, bump version, and create git tag.
bootstrap
Scaffold test, lint, and CI infrastructure for projects that lack it.
typescript-dev
Start TypeScript development workflow with architecture, implementation, review, and testing phases.
validate
Mechanically validate the sonu plugin repo before a PR — manifest sync, YAML frontmatter, shell-fence syntax, named-source and AI-attribution scans, cross-reference integrity, skill reachability. Only meaningful inside the claude-plugins repo; in any other repo, say so and stop.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.