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 skills add nitinjain999/platform-skills --skill awesome-docsgit 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/skills/nitinjain999/platform-skills/awesome-docs)<a href="https://agentmods.dev/skills/nitinjain999/platform-skills/awesome-docs"><img src="https://agentmods.dev/badge/skills/nitinjain999/platform-skills/awesome-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/skills/nitinjain999/platform-skills/awesome-docs"><img src="https://agentmods.dev/badge/skills/nitinjain999/platform-skills/awesome-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 | $0.00141 | $0.02847 |
| Opus 5.5 | $0.00056 | $0.01139 |
| Sonnet 5.5 | $0.00028 | $0.00569 |
| Haiku 4.5 | $0.00014 | $0.00285 |
Grade A, and why
awesome-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 5d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate, convert, and maintain animated Markdown documents with GitHub-safe SVG animations.
Mode: generate
Create a new animated Markdown document from scratch. Adapts structure and SVGs to the document type — not limited to demo docs.
Steps:
- Ask one at a time:
- Document type — what kind of document? Choose from:
readme,architecture-guide,runbook,tutorial,api-reference,how-it-works,rfc,post-mortem, orcustom(user defines sections) - Topic / subject — what is the document about? (e.g. "KEDA autoscaling", "orders-service API", "Kubernetes upgrade runbook")
- Output path — where should the file be written? (e.g.
README.md,docs/architecture.md,runbooks/keda.md) - Key components — the main moving parts, concepts, or resources covered (3–6 items)
- Document type — what kind of document? Choose from:
- Show the user an outline of the proposed document structure and which SVG patterns will apply:
- List the sections from the doc-type section map (see below) in order
- Next to each section that will get an SVG, note the pattern name: e.g.
Architecture → arch-flow - Ask: "Does this structure look right? Confirm to continue or describe what to change."
- Only proceed after explicit confirmation; adjust sections or pattern choices on request
- Classify which SVG patterns are relevant to this doc type and topic:
arch-flow— any doc that describes a system with multiple components or a data flowlifecycle-loop— docs covering a repeating control loop, approval cycle, or state machinesequence-diagram— docs covering request/response chains, API call sequences, or auth flowsstate-machine— docs covering distinct states and transitions (deployment lifecycle, approval workflow, error/retry paths)field-carousel— docs covering a configurable resource (YAML, HCL, JSON, or TOML); ask the user to paste their config at this point and identify the format before generatingtimeline-phases— docs covering distinct phases, stages, or a lifecycle with durations- For
rfc,post-mortem,runbook: SVGs are optional — ask "Would diagrams help here?" before generating
- For each applicable SVG pattern (incremental):
- Generate the SVG using the blueprint in
references/awesome-docs.md - Write to
assets/<topic-slug>-<pattern>.svg - Show to the user and ask: "Does this look right? Confirm to continue or describe what to adjust."
- Only proceed to the next SVG after explicit confirmation
- Generate the SVG using the blueprint in
- Build the document structure from the doc type section map below
- Write the file to the output path with all confirmed SVGs embedded using
<img>tags, each followed by a>blockquote caption - Commit:
git add <output-path> assets/ && git commit -m "docs(<scope>): add <doc-type> for <topic>"
Doc type section map — use these as the default structure, adapt to user needs:
| Doc type | Default sections |
|---|---|
readme |
Header (title + badges), Overview, Architecture diagram (arch-flow), How it works, Getting started, Configuration (field-carousel if applicable), Examples, Troubleshooting |
architecture-guide |
Overview, System diagram (arch-flow), Component responsibilities, Data flow, Scaling/state behavior (lifecycle-loop or state-machine), Configuration reference (field-carousel), Deployment phases (timeline-phases), Decisions & trade-offs |
runbook |
Prerequisites, Health check commands, Architecture diagram, State/failure paths (state-machine if applicable), Step-by-step procedure, Validation, Rollback |
tutorial |
Introduction, Prerequisites, Architecture overview (arch-flow), Request flow (sequence-diagram if API-heavy), Step-by-step walkthrough, What you built, Next steps |
api-reference |
Overview, Authentication, Request flow (sequence-diagram), Endpoints, Request/response fields (field-carousel), Error codes, Examples |
how-it-works |
Overview, Architecture diagram (arch-flow), Lifecycle/control loop (lifecycle-loop or state-machine), Request flow (sequence-diagram if applicable), Configuration fields (field-carousel), Load phases (timeline-phases if applicable) |
rfc |
Context and problem, Proposal, Architecture diagram, Alternatives considered, Decision criteria, Open questions |
post-mortem |
Incident summary, Timeline, Root cause analysis, Impact (state-machine of failure path if helpful), Action items, Lessons learned |
custom |
Ask the user to list the sections they want, then generate them in order |
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.
- 5d ago First seen · 190 lines · 141 tokens per session scan A 8a9749a15f61
awesome-docs is a skill published in the GitHub repository nitinjain999/platform-skills (70 stars, last pushed 3d ago), licensed Apache-2.0. It adds 141 tokens to every session and 2,847 once invoked, about $0.0006 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 2026-10-12.
Other skills, from other repositories
write-strategy
Interactive strategy document creation. Reads company context, researches competitors and market trends, then generates a comprehensive product strategy with vision, pillars, positioning, and metrics.
md-to-pdf
Convert Markdown to PDF via reportlab or weasyprint engines. Triggers - pdf, md to pdf, markdown to pdf, generate pdf.
ia-md-docs
Manages project documentation: CLAUDE.md, AGENTS.md, README.md, CONTRIBUTING.md, DOCS.md. Use when asked to update, create, or init these context files. Not for general markdown editing.
docx
This skill should be activated when the user asks to create a Word document, report, memo, letter, proposal, whitepaper, or anything involving .docx output. Also triggers when the user says 'write a report', 'create a document', 'make a Word file', 'draft a proposal', 'generate a whitepaper', or mentions .docx.…
xlsx
This skill should be activated when the user asks to create, edit, read, or analyze Excel spreadsheet files (.xlsx, .xlsm, .csv, .tsv). Triggers for: building financial models, creating data tables, formatting spreadsheets, adding formulas, cleaning tabular data, converting between tabular formats. Also triggers when…
documentation-templates
Documentation templates and structure guidelines. README, API docs, code comments, and AI-friendly documentation.