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 JuanMarchetto/doc-standards-skill --skill doc-standardsgit clone --depth 1 https://github.com/JuanMarchetto/doc-standards-skillWrote 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/juanmarchetto/doc-standards-skill/doc-standards)<a href="https://agentmods.dev/skills/juanmarchetto/doc-standards-skill/doc-standards"><img src="https://agentmods.dev/badge/skills/juanmarchetto/doc-standards-skill/doc-standards/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/juanmarchetto/doc-standards-skill/doc-standards"><img src="https://agentmods.dev/badge/skills/juanmarchetto/doc-standards-skill/doc-standards.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 | $0.00164 | $0.01589 |
| Opus 5 | $0.00082 | $0.00794 |
| Sonnet 5 | $0.00033 | $0.00318 |
| Haiku 4.5 | $0.00016 | $0.00159 |
Grade A, and why
doc-standards 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 8d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
doc-standards — write documentation that survives translation, retrieval, and skepticism
Documentation written by an LLM has a smell: elegant-variation synonyms, subordinate clauses, filler, hedging. The fix is not "write better" — it is adopting the constraints professional documentation systems already use. This skill stacks five criteria layers, from structure down to the word, and ends in a machine gate.
The five layers
| Layer | Question it answers | Source standard |
|---|---|---|
| 1. Structure | Which document am I writing, for whom? | Diátaxis + ISO 24495 |
| 2. Controlled language | Is each sentence unambiguous? | ASD-STE100 |
| 3. House style | Is it consistent with developer-docs convention? | Google / Microsoft style guides |
| 4. AI readability | Can an agent retrieve and use each section alone? | llms.txt + retrieval practice |
| 5. Verification | Can a machine confirm 2–4? | Vale / bundled checker |
Workflow
1. Structure first (delegate, don't duplicate)
Classify the document before writing a word: tutorial, how-to, reference, or explanation (Diátaxis). Each has a different contract with the reader — a tutorial promises safe success, a reference promises completeness, a how-to promises a working result, an explanation promises understanding. Mixing them is the #1 structural defect.
- Generating new docs or auditing coverage → if a Diátaxis-structure skill is installed
(for example gstack's
document-generate/document-release), invoke it — it owns the Diátaxis map. Otherwise classify and scaffold the document type yourself before writing. This skill governs the prose inside whatever gets scaffolded. - Then apply ISO 24495's reader-first gate: state who the reader is and what they must be able to DO after reading. If you cannot name the reader, stop and find out. The four plain-language principles — relevant, findable, understandable, usable — are the acceptance criteria for the whole document, not decoration.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 120 lines · 164 tokens per session scan A 9cac3cc06580
doc-standards is a skill published in the GitHub repository JuanMarchetto/doc-standards-skill (16 stars, last pushed 1mo ago), licensed MIT. It adds 164 tokens to every session and 1,589 once invoked, about $0.0008 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 skills, from other repositories
slides-to-pdf
Use when the user asks to convert, export, or save an HTML slide deck as a PDF ("save the slides as PDF", "export the deck to PDF", "make a PDF of the presentation"). Works on decks built by the SlideOps (slideops) skill and on any single-file HTML deck that shows one slide per URL hash (#1.
analyze
Analyze a collection of documents to build a knowledge map, identify themes, find gaps, duplicates, conflicts, and staleness, then produce an organized analysis with improvement recommendations. Designed for document ecosystems (cross-repo docs, research collections, mixed-format doc repos) where the challenge is…
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
treatment-plans
Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and…
venue-templates
Prepare journal manuscripts, conference papers, research posters, and grant documents using venue-specific formatting guidance and bundled LaTeX scaffolds. Use when selecting an official template, checking current page or anonymity rules, adapting academic writing to a venue, or inspecting a submission PDF.
xlsx
Create, edit, analyze, or convert Excel spreadsheets (.xlsx, .xlsm, .xltx) where the workbook file is the primary deliverable. Use for formulas, formatting, financial models, multi-sheet workbooks, and tabular cleanup exported to Excel. Also applies to .csv/.tsv when the user wants spreadsheet output. Do NOT use for…