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/skillmedev/skills/api-client-generatornpx skills add SkillMedev/skills --skill api-client-generatorgit clone --depth 1 https://github.com/SkillMedev/skillsWhat 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 | $0.00116 | $0.01259 |
| Opus 5 | $0.00058 | $0.00629 |
| Sonnet 5 | $0.00023 | $0.00252 |
| Haiku 4.5 | $0.00012 | $0.00126 |
Grade A, and why
API Client Generator scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const res = await fetch(url, { How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Client Generator
Generate the API surface from the spec so types stay honest, then wrap the generated code in a transport layer you own for resilience.
Workflow
- Confirm a spec exists. If the API ships an OpenAPI/Swagger document, generate from it. If there is no spec, or the integration is a single endpoint, hand-write a small typed wrapper with the same transport in step 4 - skip codegen.
- Generate the client. Run a codegen tool (openapi-typescript-codegen, openapi-generator, oapi-codegen, or equivalent) to produce request methods plus request/response types. Pin the spec by version or hash so an upstream change surfaces as a reviewable diff, not a silent runtime surprise.
- Treat generated code as a build artifact. Commit it, regenerate it from the pinned spec, and never hand-edit it - edits get clobbered on the next regen.
- Wrap, don't modify. Inject a custom HTTP transport (the client's configurable fetch/http layer) instead of editing generated files. Put timeouts, auth, default headers, and logging in that one wrapper so every generated call inherits them and the generated layer stays regenerable.
- Set an explicit per-request timeout in the transport - generated clients usually default to none.
- Make errors typed. Map non-2xx responses to a discriminated error type - auth (401/403), not-found (404), validation (422), rate-limit (429), server (5xx) - and parse the API's structured error body into a typed shape so callers branch on a tag, not on parsed strings. Never let a non-2xx return a half-empty success object.
- Centralize config. Hold base URL, auth token refresh, and default headers in one configured instance; don't scatter raw fetch calls across the codebase.
- Optionally validate critical responses against the schema at runtime so spec drift fails loudly. Generated types describe the contract, not reality.
- Defer cross-cutting policy. Add the retry/backoff hook point in the transport, but get the backoff policy (exponential backoff, full jitter, Retry-After, retriable status codes, idempotency) from rate-limit-handler. Get cursor pagination and incremental sync from pagination-and-sync-engineer. This skill owns the generated surface and the transport seam, not those policies.
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 · 73 lines · 116 tokens per session scan A 4263c65a5f80
API Client Generator is a skill published in the GitHub repository SkillMedev/skills (11 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 1,259 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webinar-funnel-builder
Designs a complete webinar funnel - registration page promise, reminder email sequence timed against typical 35-45 percent show-up rates, webinar structure with a 70 percent teach / 30 percent offer split and the pivot script, replay window and urgency rules, and the post-webinar email sequence - with a funnel-metrics…
Creator Content Calendar
Designs a sustainable publishing system for a solo creator - 3-4 content pillars, a cadence set at the creator's consistent floor, a fixed pillar rotation, a 30-day idea bank, and a monthly audit loop - delivered as a weekly calendar skeleton. Use when someone says "help me plan my content", "I keep falling off my…
Show Notes Writer
Produces complete podcast show notes from a transcript or episode outline - a standalone summary block, timestamped chapters that name what happens, screenshot-worthy key takeaways, guest bio, curated links, and keyword placement for search. Use when someone says "write show notes for this episode", "turn this…
YouTube Script Writer
Writes retention-engineered long-form YouTube scripts on a hook/body/payoff architecture - a first-30-seconds hook that survives the retention cliff, a beat-sheet body with mini-hooks and bridges, timed pattern interrupts, and a payoff that over-delivers - with B-roll and editing cues marked inline. Use when someone…
Systematic Review
Runs a PRISMA-compliant systematic review from PICO question and pre-registered protocol through search strings, two-stage screening, risk-of-bias appraisal, and GRADE-rated synthesis. Use when someone asks "run a systematic review", "build my search strategy and inclusion criteria", "screen these studies against a…
Policy Brief
Writes a concise, evidence-based policy brief - problem, options compared on consistent criteria, and a recommendation - that a decision-maker can act on in minutes. Use when someone asks "write a policy brief", "summarize the evidence and options for this decision", "brief the minister/board/council on X", or needs a…