project-docs

project-docs is a command for Claude Code from Dynokostya/just-works. It costs 26 tokens per session (2,750 once invoked), scanned A, original, Apache-2.0.

A command that creates or updates three project documents: a mission statement, a technology inventory, and an architecture description. It explores the codebase and uses repository evidence before writing them.

In plain words
What is it for?
Use it to document what a project is for, which languages and tools it uses, and how its parts connect. It can account for existing files and recent Git history when updating the documents.
Why use it?
It turns scattered project knowledge into a small set of maintained documents. Evidence checks help avoid describing tools or structures that the codebase does not actually contain.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/dynokostya/just-works/project-docs
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.

agentmods badge for project-docs

README.md
[![agentmods](https://agentmods.dev/badge/commands/dynokostya/just-works/project-docs.svg)](https://agentmods.dev/commands/dynokostya/just-works/project-docs)
Your own site
<a href="https://agentmods.dev/commands/dynokostya/just-works/project-docs"><img src="https://agentmods.dev/badge/commands/dynokostya/just-works/project-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,750 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.02750
Opus 5 $0.00013 $0.01375
Sonnet 5 $0.00005 $0.00550
Haiku 4.5 $0.00003 $0.00275

Measured today against content hash a4cd1307d0c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

project-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 today.

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/commands/project-docs.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Documentation

Generate or update project documentation in docs/. Produces three files:

  • docs/mission.md — What the project is and who it's for
  • docs/tech-stack.md — Inventory of languages, frameworks, tools, infrastructure
  • docs/architecture.md — How the system is structured and how parts connect

Phase 1: Detect State

Classify each file independently:

File Exists & non-empty Status
docs/mission.md yes update
docs/mission.md no create
docs/tech-stack.md yes update
docs/tech-stack.md no create
docs/architecture.md yes update
docs/architecture.md no create

A file with only whitespace or markdown headers with no content counts as create, not update.

Git context gathering. If .git exists, run these two commands via Bash and include the output as background context for all Explore agents in Phase 2:

git log --oneline -30
git shortlog -s -n --no-merges

If the repo has fewer than 5 commits, note this — it signals an early-stage project where exploration will find less and user questions become more important.

Announce the per-file status table and commit count to the user before continuing.

Phase 2: Explore

Launch three parallel Explore agents using the Agent tool (subagent_type: "Explore"). All three are independent — launch them in a single message, never sequentially. Specify search breadth "very thorough" in each prompt.

Every agent prompt must include:

  • The git context gathered in Phase 1 (last 30 commit subjects + contributor summary)
  • This instruction: "For every finding, include the source file path and line number (e.g., src/main.py:42). Findings without a file reference will be discarded."
  • This ignore directive: "Skip these directories entirely: node_modules/, .venv/, venv/, __pycache__/, dist/, build/, .git/, .next/, .nuxt/, target/, vendor/ (unless vendor is committed Go code)."

Read the full file on GitHub · 292 lines

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.

  1. today First seen · 292 lines · 26 tokens per session scan A a4cd1307d0c0

Subscribe to this mod's changes

project-docs is a command published in the GitHub repository Dynokostya/just-works (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 2,750 once invoked, about $0.0001 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 2026-09-04.