A structured way to write a guide, plan, report, proposal, or other document with its author. It breaks the document into pieces, supports different levels of author involvement, and includes review rounds.

Use it to create or revise Markdown documents such as guides, process descriptions, plans, reports, and README files.

Large documents are easier to control when their structure and each section are reviewed progressively. The process also keeps a record of what has been drafted and approved.

How Dynokostya/just-works configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Dynokostya/just-works. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Dynokostya/just-works/main/.claude/skills/staged-docs/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Dynokostya/just-works

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dynokostya/just-works/staged-docs/github.svg)](https://agentmods.dev/skills/dynokostya/just-works/staged-docs)

Your own site

<a href="https://agentmods.dev/skills/dynokostya/just-works/staged-docs"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/staged-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dynokostya/just-works/staged-docs"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/staged-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,129 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00106	$0.03129
Opus 5.5	$0.00042	$0.01252
Sonnet 5.5	$0.00021	$0.00626
Haiku 4.5	$0.00011	$0.00313

Measured 17d ago against content hash 64e2b9ccab02, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

staged-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 17d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/proposals.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/staged-docs/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Staged docs

This skill builds a document together with its author. The document is one that people read to understand or to act, such as a guide, a plan or a report, written as one or more Markdown files. The author approves a structure first. A piece is one part of that structure: usually one file, or one section when the document is a single file. Each piece is written in one of three modes, and the document then goes through review rounds before it is finished.

auto: you draft the piece from the topic and the sources, after the author approves its piece sheet (a short list of what the piece will say) at one stop that covers all auto pieces.
step-by-step: you draft the piece, and the author comments on the diagram, when the piece has one, and then on the text.
author-led: the author gives their view of the piece first, and you shape it into a diagram or an outline, and then text, without adding claims of your own.

Start or resume

NOTES.md holds the state of the work in its frontmatter, and it is the only record of where the work stands. It lives in the working folder, the one folder that holds all the working files (see Working files). Draft files can be ahead of what the author approved, so do not infer progress from them.

Look for a NOTES.md whose frontmatter has skill: staged-docs: in the current folder, its notes-*/ subfolders and its parent folders, and in any folder the author names.
If none is found, or the author's message names a topic that none of them covers, read stages/start.md and begin. If several are found and the message does not say which one to continue, ask.
Otherwise read the frontmatter of the NOTES.md for this topic and report the state in one line: the topic, the stage and what the last stop asked (waiting_for); in stage: pieces also piece n of N with its title and mode, and in other stages the round. Then wait for the author to confirm. When the author's message already says to continue, or answers waiting_for, report the line and go on in the same turn.
Go on with the file that the table under "What to read when" names for the stage. In the review and stakeholder stages, resume at the step that waiting_for names, and do not repeat a step whose files exist. If a folder reviews/r-* exists, that round is open: continue it rather than opening another.

Read the full file on GitHub · 99 lines

Files

What ships with it

13 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.

Changes

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.

17d ago Changed · +2 lines 64e2b9ccab02
28d ago First seen · 97 lines · 106 tokens per session scan A 388ddff9afaa

Subscribe to this mod's changes

staged-docs is a skill published in the GitHub repository Dynokostya/just-works (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 106 tokens to every session and 3,129 once invoked, about $0.0004 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 2026-10-09.

Writing and docs

staged-docs next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
staged-docsDynokostya/just-works	Skill	14	10d ago	Apache-2.0	A	106	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code

just-works: Skill for Claude Code