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/version-guardgit 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/version-guard)<a href="https://agentmods.dev/commands/sigistry/marketplace/version-guard"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/version-guard.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 | $0.00017 | $0.00923 |
| Opus 5 | $0.00009 | $0.00462 |
| Sonnet 5 | $0.00003 | $0.00185 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
version-guard 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Classify changes to the API surface as breaking or non-breaking using oasdiff-style semantics, then recommend a semver bump. $ARGUMENTS is either a git range (from-ref..to-ref, e.g. v1.4.0..HEAD) to diff two versions of the spec, or a single spec file to compare against its previous committed version. This is a static analysis of the contract, no server or live traffic. Load the openapi-drift skill for the breaking-change rules.
Process
Step 1: Resolve the two versions of the surface
- Git range: check out (or
git show) the spec file at each ref; if the spec is code-first, diff the extracted surface (routes, DTOs, GraphQL SDL) at each ref. - Single file: diff the working copy against
HEAD(or the last tag) via git. Handle both OpenAPI/Swagger and GraphQL SDL. For GraphQL, GraphQL's own rules apply (adding a nullable field is safe; making an output field non-null is safe; making an input field required or non-null is breaking).
Step 2: Classify every change
Walk the diff and label each change using references/breaking-change-rules.md. Summary of the rules:
| Change | Verdict | Why |
|---|---|---|
| Remove or rename an endpoint/field/enum value | Breaking | Existing clients call/read it |
| Add a new required request field/param | Breaking | Old clients omit it → rejected |
Narrow a type / tighten validation (smaller max, new pattern, int→enum) |
Breaking | Previously-valid requests now fail |
| Make a response field nullable / remove a response field | Breaking | Clients depend on presence/non-null |
| Change a status code or the error shape | Breaking | Client branching/handling breaks |
| Make an optional request field required | Breaking | Same as adding a required field |
| Add a new optional request field/param | Non-breaking | Old clients omit it safely |
| Add a new endpoint / new enum value in a response | Non-breaking* | *response enum growth can surprise strict clients, flag |
| Add a response field / widen a type / loosen validation | Non-breaking | Superset accepts old inputs/outputs |
| Make a required response field... it stays required | Non-breaking | No client impact |
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 · 52 lines · 17 tokens per session scan A 77887d67c793
version-guard is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 923 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.