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/cosmix/loom/loom-api-designnpx skills add cosmix/loom --skill loom-api-designgit clone --depth 1 https://github.com/cosmix/loomWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cosmix/loom/loom-api-design)<a href="https://agentmods.dev/skills/cosmix/loom/loom-api-design"><img src="https://agentmods.dev/badge/skills/cosmix/loom/loom-api-design.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.03519 |
| Opus 5 | $0.00013 | $0.01759 |
| Sonnet 5 | $0.00005 | $0.00704 |
| Haiku 4.5 | $0.00003 | $0.00352 |
Grade A, and why
loom-api-design 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 today.
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.
| Media type `Accept: application/vnd.api.v2+json` | clean URLs, granular | harder to test/curl; caches need `Vary: Accept` | How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Design
Overview
Design intuitive, consistent, evolvable API contracts across REST, GraphQL, and gRPC. Get the resource model, HTTP semantics, error envelope, pagination, and versioning right up front — they are the hardest things to change once clients depend on them.
Design Workflow
- Model resources and relationships before URLs; name the nouns, then map operations onto them.
- Pick the paradigm: REST (resource CRUD, caching, broad tooling), GraphQL (client-shaped reads, aggregation, mobile), gRPC (internal, low-latency, streaming, strong contracts).
- Lock the error envelope, pagination shape, and versioning policy once — reuse everywhere.
- Design for change: additive evolution, tolerant readers, deprecation windows.
- Write the spec (OpenAPI/SDL/proto) as the source of truth; generate clients/servers from it.
REST
Resource & URL conventions
- Nouns, plural collections:
/users,/users/{id},/users/{id}/orders. Never verbs in paths (/getUsersis wrong — the method is the verb). - Pick one case (
snake_caseorcamelCase) and keep it identical across paths, query params, and bodies. - Keep nesting shallow (≤2 levels); deep hierarchies couple resources. Prefer
/orders?user_id=over/users/{id}/orders/{oid}/items/.... - Sub-resource actions that aren't CRUD: model as a resource (
POST /orders/{id}/refunds) rather than an RPC verb (POST /orders/{id}/refund) when the action produces a trackable entity.
HTTP methods, safety, idempotency
| Method | Purpose | Safe | Idempotent | Body |
|---|---|---|---|---|
| GET | Read | yes | yes | no |
| HEAD | Read headers | yes | yes | no |
| POST | Create / non-idempotent action | no | no | yes |
| PUT | Full replace (client sets full state) | no | yes | yes |
| PATCH | Partial update | no | not inherently | yes |
| DELETE | Remove | no | yes | maybe |
- Idempotent = same request repeated yields same server state (not same response — a repeated DELETE may return 404 the second time; that's fine).
- PUT replaces the entire resource — omitted fields are cleared. If a client can't send full state, use PATCH.
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.
- today Changed · -21 tokens per session f8bdcf22446c
- 4d ago First seen · 288 lines · 46 tokens per session scan A 77d0ec9f32f3
loom-api-design is a skill published in the GitHub repository cosmix/loom (54 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 3,519 once invoked, about $0.0001 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
hardcoded-secret
A bundle that leaks a real credential. This must never publish.
code-review
Perform thorough code reviews focusing on correctness, security, and maintainability.
checkpointed-workflow
Use when the user asks to assemble and validate a checkpointed report bundle.
deterministic-transform
Use when the user asks to transform a JSON data file deterministically.
document-formatter
Use when the user asks to format a document against the house style guide.
dangerous-skill
Example skill that demonstrates security scanner detection.