docs-profile

docs-profile is a command for Claude Code from ihudak/ihudak-claude-plugins. It costs 99 tokens per session (5,371 once invoked), scanned A, original, MIT.

A command that scans a documentation repository and creates or refreshes a machine-readable profile describing its content areas and development commands. A repository is a project folder managed with version control.

In plain words
What is it for?
Use it to profile one or more documentation areas, including their content roots, local servers, linting, build, formatting, templates, and links, then prepare the changes as a reviewable pull request.
Why use it?
It gives other documentation workflows reliable information about where content lives and how to build, check, or format it.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dev-workflows plugin — 2 skills, 28 commands, 38 agents, 3 hooks shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ihudak/ihudak-claude-plugins
Claude Code
/plugin install dev-workflows

Made for: Claude Code.

Or install dev-workflows, the plugin that ships this one along with the rest of its 2 skills, 28 commands, 38 agents, 3 hooks.

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 docs-profile

README.md
[![agentmods](https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/docs-profile.svg)](https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/docs-profile)
Your own site
<a href="https://agentmods.dev/commands/ihudak/ihudak-claude-plugins/docs-profile"><img src="https://agentmods.dev/badge/commands/ihudak/ihudak-claude-plugins/docs-profile.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,371 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 $0.00099 $0.05371
Opus 5 $0.00049 $0.02686
Sonnet 5 $0.00020 $0.01074
Haiku 4.5 $0.00010 $0.00537

Measured today against content hash 34c9bd436aed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

docs-profile 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.

plugins/dev-workflows/commands/docs-profile.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Profile the documentation repository: $ARGUMENTS

$ARGUMENTS is an optional repo path (default: the current working directory), optionally followed by --inline. The --inline token is passed when /document (keyed mode) invokes this flow inline (its Phase 0 case (c)); it switches this command to inline mode — see Phase 5 step 1, step 2, step 6, and Phase 6.

/docs-profile bootstraps or refreshes the machine-readable docs-profile that /document (keyed mode) consumes. It scans a documentation repository, synthesises a .dev-workflows/docs-profile.yml (and complementary CLAUDE.md guidance) that conforms to ${CLAUDE_PLUGIN_ROOT}/references/docs-profiles/docs-profile-schema.md, then writes the result as a reviewable PR — branch + commit + a drafted PR message. It never pushes or auto-merges.

The command is generic — it works on any docs repo. A repo publishing one documentation set gets a single spaces[] entry; a repo publishing several gets one entry per content root, plus the per-space dev-server and lint/build/format commands that go with them.

It does not re-specify changelog or owners rules. Those are owned by the docs-frontmatter skill (+ ${CLAUDE_PLUGIN_ROOT}/references/docs-profiles/changelog-guidelines.md, ${CLAUDE_PLUGIN_ROOT}/references/docs-profiles/default-owners.txt); the profile's frontmatter: fields are pointers only.

For one-off doc edits use direct mode; for keyed feature documentation use /document (keyed mode).


Phase 0 — Resolve and validate the target repo

  1. Resolve the repo path. Take the first token of $ARGUMENTS as the target path; if $ARGUMENTS is empty, default to the current working directory. Resolve it to an absolute path and record it as <repo>. Treat a --inline token (in any position) as the inline-mode flag, not a path; record inline = true when present.

  2. Validate it is a writeable git work tree:

    • git -C <repo> rev-parse --is-inside-work-tree must print true. If it errors or prints anything else, stop with the named error: NOT_A_GIT_WORKTREE: <repo> is not inside a git work tree.
    • test -w <repo> must succeed. If not, stop with the named error: REPO_NOT_WRITEABLE: <repo> is not writeable.
    • Resolve and record the repo's git root: git -C <repo> rev-parse --show-toplevel. All later detection and writes are relative to this root.
  3. Detect docs-repo signals under the git root:

    • package.json with any doc script (matching *:start, *:build, *:lint, docs:*, prettier),
    • a .docstack/ directory,
    • a .vale.ini file,
    • any */_content/ directory (e.g. cloud/_content, self-hosted/_content),
    • any _snippets/ directory.

    If ≥ 1 signal is present → proceed silently to Phase 1. If 0 signals are present → ask before continuing:

    "No documentation-repo signals detected under <repo> (checked: package.json doc scripts, .docstack/, .vale.ini, */_content/, _snippets/). Profile it anyway?"
    choices: ["Proceed — I confirm this is a docs repo (Recommended)", "Cancel — point me at a docs repo first"]
    

    Default = Proceed. On Cancel, stop and report.


Read the full file on GitHub · 259 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 Changed 34c9bd436aed
  2. 5d ago First seen · 259 lines · 99 tokens per session scan A 852b75ede139

Subscribe to this mod's changes

docs-profile is a command published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 3d ago), licensed MIT. It adds 99 tokens to every session and 5,371 once invoked, about $0.0005 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 2026-08-31.