devos-docs-init

A command for initializing project documentation through the devos-docs skill. It creates a file describing project surfaces and a project overview code map.

In plain words
What is it for?
Creating docs/surfaces.yaml and docs/codemaps/project-overview.md, while detecting the project's preferred language and validating the result before writing.
Why use it?
It gives a newly documented or significantly changed project a consistent starting record of its structure and documentation language.

Command

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/chhuax/praxis-devos/devos-docs-init
Clone the repo
git clone --depth 1 https://github.com/chhuax/praxis-devos
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 460 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 $0.00000 $0.00460
Opus 5 $0.00000 $0.00230
Sonnet 5 $0.00000 $0.00092
Haiku 4.5 $0.00000 $0.00046

Measured 2d ago against content hash d71e65e52302, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devos-docs-init 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 2d 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.

assets/commands/devos-docs-init.md · 46 lines

What it actually says

devos-docs-init

Initialize project documentation using the devos-docs skill.

What this does

  • Generates docs/surfaces.yaml
  • Generates docs/codemaps/project-overview.md
  • Uses deterministic validation before writeback

Mode

init

How to use

Run this command when:

  • setting up docs for the first time
  • the project structure has changed significantly

Implementation

  • Invoke the devos-docs skill with mode=init
  • Detect the project's language preference and pass it as artifact_language:
    • First check existing docs/surfaces.yaml for an artifact_language field
    • Otherwise infer from the primary language of AGENTS.md / README.md
    • Pass the detected value to the devos-docs skill; if no preference is found, omit (defaults to en)
  • If using a sub-agent for repository exploration, follow the Agent Collaboration protocol in the devos-docs skill — the sub-agent prompt must request the standard exploration return structure (adapted for the project's language/build system) and prohibit writing to external files
  • The main agent must consume the sub-agent's return; discarding it and rebuilding from scratch is a protocol violation
  • Use the stable docs routing order:
    • docs/surfaces.yaml
    • docs/codemaps/project-overview.md
    • docs/codemaps/module-map.md only for multi-module projects
    • docs/codemaps/modules/<artifactId>.md only when module routing is deterministic
  • Before writing any file, complete contract assembly and validation (see Validation Contract in the devos-docs skill) — writing files without a validated contract is a protocol violation
  • Write all files in a single pass after validation; writing files incrementally during exploration is prohibited
  • Canonical paths:
    • docs/surfaces.yaml
    • docs/codemaps/**

Notes

  • This is a thin wrapper. Core logic lives in the devos-docs skill.
  • No CLI fallback is provided; use the projected host command or invoke the devos-docs skill directly.
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. 2d ago First seen · 46 lines · 0 tokens per session scan A d71e65e52302

Subscribe to this mod's changes

devos-docs-init is a command published in the GitHub repository chhuax/praxis-devos (21 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 460 tokens. 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.