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/genkovich/sdd/apinpx skills add genkovich/sdd --skill apigit clone --depth 1 https://github.com/genkovich/sddWhat 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 | $0.00220 | $0.04247 |
| Opus 5 | $0.00110 | $0.02124 |
| Sonnet 5 | $0.00044 | $0.00849 |
| Haiku 4.5 | $0.00022 | $0.00425 |
Grade C, and why
api scanned grade C 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 2d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
**Determine the interface kind — read `sad.md` frontmatter `target_surfaces` FIRST** (design already declared it; the surface picks the contract form per [`../_shared/surfaces.md`](../_shared/surfaces.md): `backend-servi How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: api
Projects the upstream artifacts into one interface contract. By default that's an HTTP/OpenAPI contract; this skill is interface-kind aware — and the kind comes from the surface(s) design declared in sad.md frontmatter target_surfaces, read here, not re-derived (→ ../_shared/surfaces.md). For a non-HTTP project it produces the matching contract form (or steps aside):
- HTTP / REST (default) →
contracts/openapi.yaml(OpenAPI 3.1) +api-sync-report.md. - gRPC / RPC → a
.proto(or the repo's IDL) with the same derive-and-drift discipline. - CLI →
contracts/cli.md— the command/flag/exit-code surface derived from the AC. - Library / SDK →
contracts/public-api.md— the public signatures/types the feature exposes. - Event-only / worker → just
contracts/events.md(no request/response surface). - No external interface (pure internal logic) → skip with a one-line note in the report; go straight to
tasks.
Whatever the form, the contract is derived from data-model.md — or, on a legal no-schema-change skip, the existing schema — plus the sad.md §6 sequences + the spec's AC, never typed by hand — generation that diverges from the model or the sequences is the bug this skill exists to catch. The rest of this file details the HTTP path (the common case); the same derive → drift-check → reconcile loop applies to the other forms with the form-appropriate artifact.
This skill keeps only its own machinery. Question phrasing is shared → ../_shared/ask-style.md. Depth (events doc only when async; one resource vs full surface) follows the size matrix → ../_shared/size-matrix.md. The drift-resolution dialog reuses the shared 4-state actions — keep it short, point the machinery to _shared.
Contract summary/description prose follows artifact_language — paths, operationId, status codes and schema names never translate → ../_shared/artifact-language.md.
What ships with it
3 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.
- 2d ago First seen · 99 lines · 220 tokens per session scan C cdf9d3851121
api is a skill published in the GitHub repository genkovich/sdd (118 stars, last pushed 13d ago), licensed MIT. It adds 220 tokens to every session and 4,247 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…