Borrowing it
Nothing to install: this file belongs to jayminwest/kotadb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jayminwest/kotadb/develop/.claude/commands/docs/load-ai-docs.mdgit clone --depth 1 https://github.com/jayminwest/kotadbWrote 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/commands/jayminwest/kotadb/load-ai-docs)<a href="https://agentmods.dev/commands/jayminwest/kotadb/load-ai-docs"><img src="https://agentmods.dev/badge/commands/jayminwest/kotadb/load-ai-docs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/jayminwest/kotadb/load-ai-docs"><img src="https://agentmods.dev/badge/commands/jayminwest/kotadb/load-ai-docs.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00017 | $0.00980 |
| Opus 5.5 | $0.00007 | $0.00392 |
| Sonnet 5.5 | $0.00003 | $0.00196 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade A, and why
load-ai-docs 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 1mo 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Load AI Docs
Template Category: Action Prompt Level: 2 (Parameterized)
Load documentation from their respective websites into local markdown files our agents can use as context.
Variables
DELETE_OLD_AI_DOCS_AFTER_HOURS: 24 DEFAULT_CATEGORY: all
Usage
/docs:load-ai-docs- Load all documentation/docs:load-ai-docs claude-code- Load only Claude Code docs/docs:load-ai-docs anthropic- Load only Anthropic docs/docs:load-ai-docs uv- Load only UV (development tools) docs/docs:load-ai-docs zod- Load only Zod validation docs/docs:load-ai-docs supabase- Load only Supabase docs/docs:load-ai-docs stripe- Load only Stripe docs/docs:load-ai-docs openai- Load only OpenAI docs/docs:load-ai-docs google- Load only Google AI docs/docs:load-ai-docs nextjs- Load only Next.js docs
Category URL Mappings
Claude Code
| URL | Output Path |
|---|---|
| https://code.claude.com/docs/en/mcp.md | claude-code/mcp.md |
| https://code.claude.com/docs/en/slash-commands.md | claude-code/slash-commands.md |
| https://code.claude.com/docs/en/sub-agents.md | claude-code/sub-agents.md |
| https://code.claude.com/docs/en/sdk/sdk-python.md | claude-code/sdk-python.md |
| https://code.claude.com/docs/en/sdk/sdk-typescript.md | claude-code/sdk-typescript.md |
| https://code.claude.com/docs/en/hooks.md | claude-code/hooks.md |
Anthropic
| URL | Output Path |
|---|---|
| https://docs.anthropic.com/en/docs/about-claude/models/overview | anthropic/models-overview.md |
Validation (Zod)
| URL | Output Path |
|---|---|
| https://zod.dev/?id=introduction | validation/zod/getting-started.md |
| https://zod.dev/?id=primitives | validation/zod/primitives.md |
| https://zod.dev/?id=objects | validation/zod/objects.md |
| https://zod.dev/?id=arrays | validation/zod/arrays.md |
| https://zod.dev/?id=unions | validation/zod/unions.md |
| https://zod.dev/?id=error-handling | validation/zod/error-handling.md |
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.
- 1mo ago First seen · 94 lines · 0 tokens per session scan A 7317315f43b4
load-ai-docs is a command published in the GitHub repository jayminwest/kotadb (100 stars, last pushed 6mo ago), licensed MIT. It adds 17 tokens to every session and 980 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other commands, from other repositories
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
verify-math
Verify a self-authored mathematical result end to end by routing claims across adversarial review, numerical falsification, symbolic or CAS checks, and Lean, then aggregating one report. Use when a theorem, proposition, conjecture, or paper-wide mathematical argument needs the appropriate combination of verification…
synthesise-reviews
Deduplicate and reconcile multiple completed review reports into one prioritised revision plan with conflicts and dependencies made explicit. Use when parallel reviewers have returned findings that need a single action sequence. Not for running the reviews; use $review-cluster.
firebase-publish
Create or reuse a Firebase project, configure Hosting, and deploy the current static site. Never deletes.
tdd-feature
Implement a new feature using full TDD loop.
auditoria-legal
Grupo: Trabajo con el framework En una frase: Auditoría de cumplimiento legal del producto — territorio, evidencia y lo que el código no cubre. Cuándo: Antes de publicar una app o web: registro, cookies, analítica, emails, suscripciones, contenido de usuarios. Quién: Cualquier operador del repo.