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/ivklgn/ai-kit/jsdocnpx skills add ivklgn/ai-kit --skill jsdocgit clone --depth 1 https://github.com/ivklgn/ai-kitWhat 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 | $0.00088 | $0.01136 |
| Opus 5 | $0.00044 | $0.00568 |
| Sonnet 5 | $0.00018 | $0.00227 |
| Haiku 4.5 | $0.00009 | $0.00114 |
Grade B, and why
jsdoc scanned grade B 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
**Mode C — Doc generator present.** `typedoc`, `jsdoc`, or `documentation` in devDependencies or scripts: match its tag dialect and config (entry points, `@group`/`@category` conventions), and verify the build (`npm run How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JSDoc Skill
You are documenting JavaScript/TypeScript code with JSDoc. Good doc comments state the contract the signature cannot: meaning, units, invariants, error behavior, and examples. Bad doc comments restate the code. Produce only the first kind.
Step 1: Detect the Documentation Mode
Read package.json, tsconfig.json/jsconfig.json, and a sample of existing doc comments. Pick the mode — it changes what a correct comment looks like:
Mode A — Typed JSDoc (plain JS). Signals: .js sources with checkJs/// @ts-check, or JSDoc types used for editor intellisense. Types live IN the comments and are load-bearing:
- Full type annotations:
@param {Map<string, number>} counts,@returns {Promise<User|null>} @typedef,@callback,@templatefor shapes and generics; import types with@typedef {import('./api').User} Useror inline@type {import('./api').User}- Verify with
npx tsc --noEmit(respecting the project's config) — typed JSDoc that doesn't check is worse than none
Mode B — TypeScript sources. Types live in the signature; JSDoc adds semantics only:
- NO type braces:
@param userId - The owner of the session, never@param {string} userId - Never repeat what the type already says; if a comment would only restate the signature, omit it
- TSDoc-flavored tags when the project uses TypeDoc/API Extractor (
@remarks,@internal,@alpha/@beta)
Mode C — Doc generator present. typedoc, jsdoc, or documentation in devDependencies or scripts: match its tag dialect and config (entry points, @group/@category conventions), and verify the build (npm run docs or equivalent) emits without warnings.
Match existing comment style: sentence casing, hyphen after param name, blank lines, @example formatting. Consistency beats personal preference.
Step 2: Decide What Deserves Documentation
Document, in priority order:
- Exported/public API — everything a consumer can reach: functions, classes, methods, types, constants, component props
- Non-obvious contracts — units (ms vs s), ranges, nullability semantics, mutation vs copy, ordering guarantees, idempotency
- Error behavior —
@throwswith the condition, rejected promise reasons - Deprecations —
@deprecatedwith the replacement and migration hint, never bare - Tricky internals — only where the "why" isn't recoverable from the code
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 · 68 lines · 88 tokens per session scan B 2c2fdbd29ac6
jsdoc is a skill published in the GitHub repository ivklgn/ai-kit (12 stars, last pushed 15d ago), licensed MIT. It adds 88 tokens to every session and 1,136 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
semantix-guide
Troubleshoot and configure Semantix capabilities: Skills (project/custom/global/builtin priority, discovery dirs), Commands (override order, /dir:file naming), Hooks (11 events, automatic project loading, matchers, timeouts), MCP (semantix-agent.toml + .mcp.json + plugin packages, autostart), plugin packages…
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
review-full
Run a comprehensive multi-perspective code review on recent changes. Also triggers on 'is this secure?', 'security review', 'check for vulnerabilities', 'could this be exploited?' for security-focused review. Produces: GO/NO-GO verdict + findings table (Severity | Category | File:Line | Issue | Recommendation)…
e2e-check
Run E2E tests or interactive browser verification. Triggers on: 'run e2e', 'e2e test', 'browser test', 'check in browser', 'verify UI', 'interactive test'.
elicit-requirements
Structured pre-feature requirements gathering. Run before writing any new feature or API endpoint to clarify scope, acceptance criteria, and technical constraints. Produces: a Requirements Summary (Problem | Scope | Stories | Acceptance Criteria | Out of Scope | Open Questions), presented to the user for confirmation…