A documentation-generation command that scans source code and creates a fact-based set of project documents, including architecture, data, tests, security, environment, and API information.

Use it to preview captured code facts, create documentation skeletons, or export a machine-readable plan for an AI agent.

It reduces the gap between what the code actually does and what the documentation says, including in projects using several programming languages or a monorepo, a repository containing multiple related projects.

generate — Command for Claude Code by raccioly/docguard

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.

Clone the repo

git clone --depth 1 https://github.com/raccioly/docguard

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/commands/raccioly/docguard/generate/github.svg)](https://agentmods.dev/commands/raccioly/docguard/generate)

Your own site

<a href="https://agentmods.dev/commands/raccioly/docguard/generate"><img src="https://agentmods.dev/badge/commands/raccioly/docguard/generate/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/commands/raccioly/docguard/generate"><img src="https://agentmods.dev/badge/commands/raccioly/docguard/generate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,063 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	$0.00009	$0.01063
Opus 5.5	$0.00004	$0.00425
Sonnet 5.5	$0.00002	$0.00213
Haiku 4.5	$0.00001	$0.00106

Measured today against content hash ccc8c15192f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

generate 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.

extensions/spec-kit-docguard/commands/generate.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DocGuard Generate

Scans your codebase (JS/TS, Python, Rust, Go, Java/Kotlin, Ruby, PHP, C# — polyglot/monorepo-aware) and generates the canonical documentation memory: ARCHITECTURE.md, DATA-MODEL.md, TEST-SPEC.md, SECURITY.md, ENVIRONMENT.md, API-REFERENCE.md, SCREENS.md.

Two modes:

--plan (AI-powered, recommended) — emits a structured agent task manifest + writes the code-truth skeleton inside  markers. The AI agent then writes the prose grounded in scanned facts. Human prose is preserved.
default — purely deterministic generation: writes templated docs with TODO placeholders. Use when no AI agent is available.

With docs.roles, a missing or explicitly generated single-role target can receive a full document. Existing human documents receive only bounded updates inside unique source=code sections. Shared roles and malformed markers fail before any mapped document is written, even with --force.

Running DocGuard

Run docguard from PATH when it is installed. Otherwise run npx --yes [email protected], the release these instructions ship with, in its place. Every docguard … command below means one of the two.

As-built specs for code that has none

--spec <area> reverse-engineers a Spec Kit spec for one directory of existing code:

docguard generate --spec src/billing            # preview the candidates
docguard generate --spec src/billing --write    # create specs/NNN-as-built-src-billing/spec.md

DocGuard proposes one FR-NNN candidate per fact it can establish without an LLM: routes, exported symbols, environment variables and entities. Each candidate carries a  marker and a file citation. The requirement statement is left to you as an  note. Replace each note, keep the markers, and move any fact you deliberately do not specify under ## Out of Scope with a reason.
--write registers the spec as origin: as_built with its source paths. From then on, guard reports a fact that appears in the code without a requirement, and a cited fact that disappears (SPR007). The spec cannot silently drift from the code it describes.
It composes with the brownfield community extensions. Brownfield Bootstrap, BrownKit and Time Machine can draft the narrative, and DocGuard adds the fact candidates and keeps them in sync. Unlike Time Machine, it never re-runs /speckit.implement over existing code.

Read the full file on GitHub · 106 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.

today Changed ccc8c15192f7
3d ago Changed 42b99546b370
5d ago Changed d9de3b7ed59a
6d ago Changed 143501d14dfd
15d ago Changed · +6 lines c04eddaf024e
17d ago Changed · +21 lines 921e69448a4f
1mo ago Changed · +5 lines 72816613f60c
1mo ago First seen · 74 lines · 9 tokens per session scan A ec61ee12fba8

Subscribe to this mod's changes

generate is a command published in the GitHub repository raccioly/docguard (32 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 1,063 once invoked, about $0.0000 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 2026-08-30.

Writing and docs ai-agents cdd cli documentation drift-detection eu-ai-act

generate

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

DocGuard Generate

Running DocGuard

As-built specs for code that has none

What this file has done since we first saw it

Other commands, from other repositories

dev-docs-update

dev-docs

explain

checklist

clarify

specify