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/kreek/consult/apinpx skills add kreek/consult --skill apigit clone --depth 1 https://github.com/kreek/consultWhat 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 | $0.00025 | $0.01818 |
| Opus 5 | $0.00013 | $0.00909 |
| Sonnet 5 | $0.00005 | $0.00364 |
| Haiku 4.5 | $0.00003 | $0.00182 |
Grade A, and why
api 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 yesterday.
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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API
Iron Law
DESIGN THE CONTRACT FIRST. EVOLVE WITHOUT BREAKING. PICK STATUS BY ORIGIN.
When to Use
- Adding, removing, renaming, or reviewing REST endpoints, fields, status codes, webhooks, auth, pagination, rate limits, or idempotency.
- Writing or changing OpenAPI, JSON Schema, public SDK boundaries, or integration contracts external callers depend on.
When NOT to Use
- Internal function signatures with no caller contract; use
domain-modelingorrefactoring. - Auth, secrets, or trust-boundary review beyond API shape; use
security. - Database schema design; use
database. - Non-REST API styles (gRPC, GraphQL, message queues): contract,
error, and evolution conventions differ; use
architecturefor style-of-API decisions and the relevant ecosystem's conventions for shape.
Core Ideas
- Contract first. Sketch OpenAPI or the repo's API contract source
before controller code; implement from the contract, not toward it.
Every response shape is explicit, including errors, empty states,
pagination, and auth failures. Durable API interfaces route through
contract-first; error shape is part of the contract. - Evolution: additive in place; breaking needs a path forward.
Optional fields, query params, headers, methods, and endpoints
evolve in place. Renames, removals, required additions, status-code
changes, and semantic changes need a successor contract or
deprecation path. Never break in place. See
references/api-evolution.md. - Versioning: one strategy per service. Pick URL path, media
type, header, or date and apply it consistently. Major bumps for
breaking changes only; compatible additions never re-version.
Retire versions with an overlap window; route deprecation
primitives through
release. Seereferences/api-evolution.md. - Errors: status by origin, shape by contract.
4xxfor consumer-request problems,5xxfor upstream or your-service problems; never mix origins in one response. Use the chosen data model's native error shape (JSON:APIerrors[], FHIROperationOutcome, or RFC 9457 Problem Details). These are structurally distinct conventions, not interchangeable. Never leak raw upstream or internal errors. Seereferences/rest-error-status-codes.md. - Default to JSON:API; switch only when the domain has its own
standard. JSON:API is the default for REST resource APIs (envelope
with
id/type/attributes/relationships, sparse fieldsets, includes, pagination conventions, error array). Switch to a domain-specific standard when one applies: FHIR for healthcare, HAL for hypermedia-centric APIs, JSON-LD when semantic-web interop matters. Document deviations from the chosen standard explicitly. Seereferences/data-models.md.
What ships with it
8 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.
- yesterday First seen · 154 lines · 25 tokens per session scan A 35cf670c8610
api is a skill published in the GitHub repository kreek/consult (1 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 1,818 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 skills, from other repositories
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.