AGENT
Use when designing a new HTTP/GraphQL API or changing an existing one — modeling resources, defining endpoint contracts, choosing status codes, pagination,…
Every finding gets exactly one severity. Calibration matters more than volume: an inflated severity makes the whole review untrustworthy. When unsure between two levels, pick the lower one and explain.
$ npx -y skills add vanara-agents/skills --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Every finding gets exactly one severity. Calibration matters more than volume: an inflated severity makes the whole review untrustworthy. When unsure between two levels, pick the lower one and explain.
Every finding gets exactly one severity. Calibration matters more than volume: an inflated severity makes the whole review untrustworthy. When unsure between two levels, pick the lower one and explain.
Exploitable vulnerability, data loss, or data corruption. The change must not merge as-is.
Examples:
**Action:** Verdict = Block. Author must fix before merge. Rotate any exposed secret immediately.
A real bug or significant security/quality risk that will bite in production, but not an immediate exploit/data-loss.
Examples:
**Action:** Verdict = Request-changes. Should be fixed before merge.
Maintainability concern or minor correctness issue. Won't cause an outage but adds risk or friction.
Examples:
**Action:** Fix when reasonable; author may defer with a tracking note.
Style, naming, micro-improvements. Never blocks a merge.
Examples:
**Action:** Note as a nit. Verdict can still be Approve-with-nits.
| Findings present | Verdict | |---|---| | Any CRITICAL | Block | | Any HIGH (no CRITICAL) | Request-changes | | Only MEDIUM/LOW | Approve-with-nits | | None | Approve |
🐒 Free agents, skills & packs for Claude Code One subscription. An army of Claude Code agents. 30 production-grade agents, skills, and packs for Claude Code — free, Apache-2.0, install with one command.
Repo: vanara-agents/skills
Use when designing a new HTTP/GraphQL API or changing an existing one — modeling resources, defining endpoint contracts, choosing status codes, pagination,…
This shows how the api-designer agent reviews a flawed draft. Findings are severity-ranked so the implementer fixes the contract-breakers first. Severity…
The contract is the deliverable. Express it as an **OpenAPI 3.1** document so it is human-readable *and* machine-checkable. This reference covers how to…
Run through this before declaring an API contract done. It is ordered the way you should *design*: resources first, cross-cutting rules last. Every box is a…
APIs are forever once published: a consumer you've never met may depend on any field you expose. Design so you can **add without breaking**, and version…
Copy-paste templates for leaving review comments. Keep each comment to one finding: an anchor, the problem, and the fix.