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/aneja5/forge-skills/api-designnpx skills add aneja5/forge-skills --skill api-designgit clone --depth 1 https://github.com/aneja5/forge-skillsWrote 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/aneja5/forge-skills/api-design)<a href="https://agentmods.dev/skills/aneja5/forge-skills/api-design"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/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 | $0.00048 | $0.02209 |
| Opus 5 | $0.00024 | $0.01104 |
| Sonnet 5 | $0.00010 | $0.00442 |
| Haiku 4.5 | $0.00005 | $0.00221 |
Grade A, and why
api-design 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 4d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Design
Overview
Define the project's API conventions before endpoints proliferate. Output is .forge/api-design.md — verbs and status codes, the error envelope schema, versioning + deprecation policy, pagination/filter contract, rate-limiting envelope, auth/authz envelope, idempotency rules for mutations, and the public-vs-internal API boundary. Consumed by architecture-and-contracts (per-module contracts inherit these), incremental-implementation (endpoints must conform), and code-review-and-quality (PR review checklist).
When to Use
- A new service or new public endpoint is being designed
- Two services need a stable interface and there's no project-wide envelope
- Error shapes vary across endpoints and clients have to special-case each one
- A breaking change is about to ship and there's no versioning policy
- A list endpoint is being added and pagination shape is unclear
- A mutation endpoint will be retried by clients and there's no idempotency story
When NOT to Use
- A single trivial endpoint is being added to a service that already has documented conventions
- Internal-only RPC inside one service (use module contracts via
architecture-and-contracts) - GraphQL or gRPC — adapt the principles but the file should call out the protocol
Common Rationalizations
| Thought | Reality |
|---|---|
| "We'll version when we break something" | By then clients are coupled to the unversioned shape. Versioning costs nothing on day one, costs a migration on day 200. |
| "Every endpoint is different, no need to standardize" | Inconsistency is a bug, not flexibility. Every divergent error shape costs clients a special case. |
| "Just return 200 with an error field" | Clients can't distinguish success from failure without parsing the body. Proxies and CDNs cache 200s aggressively. |
| "Internal APIs don't need contracts" | Internal APIs become external APIs the moment a second team touches them. Two consumers = production interface. |
| "PATCH replaces the resource" | RFC 7396 says PATCH merges. Clients that depend on merge semantics will break silently if you replace. |
| "Idempotency keys are only for payments" | Network retries happen on every endpoint. Without idempotency, retries create duplicates everywhere. |
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.
- 4d ago First seen · 144 lines · 48 tokens per session scan A a1923d72e9d7
api-design is a skill published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 2,209 once invoked, about $0.0002 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
focus-problem
Deeply scope a problem before coding: parallel Explore agents map related files, similar implementations, and test patterns, producing a problem definition, boundaries, and minimal implementation plan. Use when planning a feature, investigating a bug, or entering an unfamiliar codebase area.
create-subagent
Generates single-purpose Claude Code sub-agents for use via the Task tool. Use when creating dedicated sub-agents, scaffolding agent definitions, or generating agents with diagnostics and permissions setup.
pipeline-templates
Pre-defined F# pipe workflows for multi-agent orchestration. Provides code review, fix validation, test audit, new feature, research & planning, and test execution pipelines. Triggered via PostToolUse hook after significant code changes.
subagent-output-templating
Template for structured sub-agent output including YAML log format, task completion reports (WHY/WHAT/TRADE-OFFS/RISKS), and summary constraints. Use when defining how sub-agents should report results.
create
Create a fresh NeatContext context from a user-defined behavioral profile and an existing local knowledge folder. Use only when the user explicitly invokes this skill or asks to create a new context rather than save the current conversation.
slice
Turn a feature into well-defined, independently shippable slices — whether it's an epic that needs breaking apart or a single story that needs sharpening into a job story.