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/sananthanarayan/skilldrop/api-contract-draftnpx skills add sananthanarayan/skilldrop --skill api-contract-draftgit clone --depth 1 https://github.com/sananthanarayan/skilldropWhat 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 | $0.00099 | $0.01566 |
| Opus 5 | $0.00049 | $0.00783 |
| Sonnet 5 | $0.00020 | $0.00313 |
| Haiku 4.5 | $0.00010 | $0.00157 |
Grade A, and why
api-contract-draft 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 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.
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
api-contract-draft
Produces the contract before the code — a valid OpenAPI 3.1 document two teams can argue about and then build against in parallel. The YAML is half the artifact; the other half is the decisions log, because reviewers should debate "cursor vs offset pagination", not line 240. Designs new contracts; documenting an existing API is guide-builder's job.
How to respond
-
Extract the resources from the brief. Nouns the API owns, their relationships, and their lifecycle (who creates, what mutates, is delete real or soft). Ask at most 2 questions, and spend them on consumer shape ("who calls this — our SPA, partners, both?") and write semantics ("can a refund be requested twice?") — the two answers that change the contract most. Everything else: pick the convention from
reference.mdand tag the choice[assumption]in the decisions log. -
Apply the house conventions (full detail in
reference.md) — deviate only when the brief forces it, and log the deviation:- Paths: plural-noun resources, no verbs — ✅
POST /refunds❌POST /createRefund; nesting one level max, then flatten with filters - Errors: RFC 9457
application/problem+json, every 4xx the operation can return enumerated with a stable machine-readablecode; no bare unexplained 500 - Pagination: cursor-based by default (
cursor+limit, response carriesnext_cursor); offset only with a logged reason - Idempotency: every unsafe POST takes
Idempotency-Key; PUT/DELETE idempotent by construction - Versioning: URL major version (
/v1/), additive changes don't bump, breaking changes do — the policy sentence goes in the spec'sdescription - Auth: a
securitySchemeexists and every operation declares its requirement — including the explicitly-public ones
- Paths: plural-noun resources, no verbs — ✅
-
Type every field like a reviewer will reject sloppiness. Formats (
uuid,date-time,int64), constraints (maxLength,minimum,enum,patternfor codes), required vs optional explicit on every schema, money as integer minor units (never float), timestamps UTC ISO-8601. A schema that's all baretype: stringis a draft of a draft.
What ships with it
5 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 · 70 lines · 99 tokens per session scan A 271f627af5c3
api-contract-draft is a skill published in the GitHub repository sananthanarayan/skilldrop (2 stars, last pushed 18d ago), licensed MIT. It adds 99 tokens to every session and 1,566 once invoked, about $0.0005 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
openlore-plan-refactor
Identify a high-priority refactoring target, assess its blast radius, and write .openlore/refactor-plan.md without changing code. Use when asked to plan or prioritize a refactor.
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
openlore-debug
Debug with OpenLore structural context, an explicit root-cause hypothesis, and RED/GREEN verification. Use when a bug, failure, or regression needs diagnosis and repair.
openlore-execute-refactor
Apply a confirmed .openlore/refactor-plan.md with a test gate after each change. Use when asked to execute or continue an OpenLore refactoring plan.
openlore-analyze-codebase
Run a full static OpenLore analysis and summarize architecture, call graph, refactoring issues, and duplicate code. Use when asked to analyze, map, or assess a codebase without LLM inference.
team-repair
Re-index OKF v0.2 index.md/log.md files, derive CDR.md, rebuild .skills.json and AGENTS.md in team-ai-directives, migrate v0.1→v0.2 frontmatter, scan for rule conflicts, and verify directive freshness. Use when indexes are inconsistent, orphans are detected, after bulk changes, or for periodic team AI directives…