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 commands/nitinjain999/platform-skills/documentgit clone --depth 1 https://github.com/nitinjain999/platform-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/commands/nitinjain999/platform-skills/document)<a href="https://agentmods.dev/commands/nitinjain999/platform-skills/document"><img src="https://agentmods.dev/badge/commands/nitinjain999/platform-skills/document.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 | $0.00031 | $0.00852 |
| Opus 5 | $0.00015 | $0.00426 |
| Sonnet 5 | $0.00006 | $0.00170 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
document 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate or improve technical documentation for a codebase or API.
Mode: docstrings
Add or improve inline documentation for functions, classes, and modules.
Steps:
- Ask for: language, preferred style (Google / NumPy / Sphinx for Python; JSDoc for TypeScript/JavaScript)
- Identify all public functions and classes missing documentation
- For each, document: purpose, all parameters with types, return value, exceptions raised, and at least one example
- Validate examples compile and run:
- Python:
python -m doctest file.pyorpytest --doctest-modules - TypeScript:
tsc --noEmit
- Python:
- Generate coverage report:
interrogate --fail-under=80 src/(Python) ornpx typedoc-coverage(TypeScript)
Rules:
- Do NOT document obvious getters/setters verbosely
- Do NOT repeat the function signature in prose
- Do NOT document private/internal methods unless they have complex invariants
Reference: references/documentation.md → Python Docstrings, TypeScript JSDoc
Mode: openapi
Generate or improve an OpenAPI 3.1 specification for a REST API.
Steps:
- Ask for: framework (FastAPI / Django / NestJS / Express / raw spec), existing routes or codebase to analyse
- Map all endpoints: method, path, request body schema, response schemas per status code
- Extract shared schemas into
components/schemas - Extract shared responses (400, 401, 404, 500) into
components/responses - Add
operationIdfor every operation - Add security scheme and apply globally or per-operation
- Validate:
npx @redocly/cli lint openapi.yaml - Generate HTML preview:
npx @redocly/cli build-docs openapi.yaml
For FastAPI: document with Pydantic model Field(description=...) and docstrings on route functions — auto-generates /docs.
For NestJS: use @ApiProperty, @ApiOperation, @ApiResponse decorators.
Reference: references/documentation.md → OpenAPI 3.1, FastAPI, NestJS
Mode: site
Set up a documentation site for a project.
Steps:
- Ask for: project type (Python library / TypeScript SDK / REST API / platform runbook)
- Recommend appropriate generator:
- Python projects → MkDocs + mkdocstrings + Material theme
- TypeScript projects → TypeDoc + typedoc-material-theme
- API portals → Redocly or Stoplight
- General docs → Docusaurus
- Generate site configuration file
- Define nav structure: Getting Started, API Reference, Guides, Changelog
- Wire docstring auto-generation from source code
- Add search plugin
- Provide
serveandbuildcommands
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 · 87 lines · 31 tokens per session scan A 628add7220a0
document is a command published in the GitHub repository nitinjain999/platform-skills (40 stars, last pushed 3d ago), licensed Apache-2.0. It adds 31 tokens to every session and 852 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 2026-08-30.
Other commands, from other repositories
octo-plan
Intelligent plan builder - creates strategic execution plans (doesn't execute). Use /octo:embrace to execute plans.
octo-auto
Smart router - Single entry point with natural language intent detection.
octo-usage
Your first output line MUST be: 🐙 Octopus Usage Report.
octo-preflight
Check provider health before running multi-LLM workflows.
octo-quick
Quick execution mode for ad-hoc tasks without full workflow overhead.
octo-budget-mode
Switch Octopus model routing to the configured budget tier.