agentmods.dev

docs-migrate

docs-migrate is a command for Claude Code from JOndarza/loadout. It costs 21 tokens per session (609 once invoked), scanned A, original, MIT.

A command for moving version 1 documentation summaries into version 2 rule files while keeping the original files as deprecated copies.

In plain words
What is it for?
Use it to map documentation about business context, architecture, coding rules, APIs, databases, technology, and deployment into the .claude/rules/ folder.
Why use it?
It gives projects a defined migration path and avoids deleting the existing documentation automatically.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions Claude Code.

not rated 3repo 5mo ago A scan 21 tokens original MIT

Good fit Use it to map documentation about business context, architecture, coding rules, APIs, databases, technology, and deployment into the .claude/rules/ folder.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jondarza/loadout/docs-migrate
View source ↗ JOndarza/loadout
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/JOndarza/loadout

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 docs-migrate

README.md
[![agentmods](https://agentmods.dev/badge/commands/jondarza/loadout/docs-migrate/github.svg)](https://agentmods.dev/commands/jondarza/loadout/docs-migrate)
Your own site
<a href="https://agentmods.dev/commands/jondarza/loadout/docs-migrate"><img src="https://agentmods.dev/badge/commands/jondarza/loadout/docs-migrate/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.

agentmods 80×15 button for docs-migrate

Your own site · 80×15
<a href="https://agentmods.dev/commands/jondarza/loadout/docs-migrate"><img src="https://agentmods.dev/badge/commands/jondarza/loadout/docs-migrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 609 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.00609
Opus 5.5 $0.00008 $0.00244
Sonnet 5.5 $0.00004 $0.00122
Haiku 4.5 $0.00002 $0.00061

Measured 1mo ago against content hash a5cc14b0175c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docs-migrate 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 1mo 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.

.claude/skills/docs-architect/assets/commands/docs-migrate.md · 28 lines

What it actually says

Run the docs-architect skill in migrate mode. Non-destructive: originals are preserved as .deprecated, nothing is deleted automatically.

Flow:

  1. Scan docs/_lite/*.summary.md and list all summary files found.
  2. For each summary, propose a target in .claude/rules/:
    • business-context.md → .claude/rules/business-context.md (always-loaded)
    • architecture.summary.md → .claude/rules/architecture.md (always-loaded)
    • coding-rules.summary.md → ask: split into backend.md+frontend.md (path-scoped) or keep as single coding-rules.md (always-loaded)?
    • api-contracts.summary.md → .claude/rules/api.md (path-scoped to **/Controllers/**, **/routes/**)
    • database-schema.summary.md → .claude/rules/database.md (path-scoped to **/Entities/**, **/migrations/**)
    • tech-stack.summary.md → .claude/rules/tech-stack.md (always-loaded)
    • deployment.summary.md → .claude/rules/deployment.md (path-scoped to docker-compose*, Dockerfile*, .env*)
    • roadmap.summary.md, backlog.summary.md, bugs.summary.md, ideas.summary.md, ai-rules.summary.md → NOT migrated (session-volatile or human-only)
  3. Show the full mapping to the user and ask for confirmation or edits.
  4. Copy content from each _lite/*.summary.md into its new .claude/rules/*.md target, adding paths: frontmatter where applicable. Strip Source: docs/...md lines and replace with <!-- mirrors: docs/<file>.md -->.
  5. Rename the originals: docs/_lite/<file>.summary.md → docs/_lite/<file>.summary.md.deprecated. Never delete.
  6. Update CLAUDE.md: remove the "Where to look" table pointing to _lite/, replace with <!-- subsystem rules live in .claude/rules/ -->.
  7. Update docs/README.md: replace the "3 levels" explanation with the "2 layers" explanation.
  8. Run /docs-audit to verify the migration.
  9. Tell the user: "Migration complete. Originals preserved as .deprecated. Run rm docs/_lite/*.deprecated after verifying a fresh Claude Code session loads context correctly."

Safety: never writes outside docs/_lite/, .claude/rules/, CLAUDE.md, and docs/README.md. Never deletes. Never runs git commands.

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. 1mo ago First seen · 28 lines · 21 tokens per session scan A a5cc14b0175c

Subscribe to this mod's changes

docs-migrate is a command published in the GitHub repository JOndarza/loadout (3 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 609 once invoked, about $0.0001 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 2026-08-31.

Claude Codeclaudeclaude-code-skillsclaude-skillsextensionextensions
Related

Other commands, from other repositories

README

Git workflow and quality assurance commands for the claude-skills repository.

alirezarezvani/claude-skills · 0 tokens

benchmark

Design and coordinate a reproducible Java performance test.

jabrena/plinth · 10 tokens

profile

Coordinate a reproducible Java profiling and optimization lifecycle.

jabrena/plinth · 10 tokens

update-issue

Update an issue description with structured, evidence-backed content.

jabrena/plinth · 11 tokens

psql-query

Run ad-hoc PostgreSQL analytics queries against dev/test database.

oliver-kriska/claude-elixir-phoenix · 16 tokens

earnings

Post-earnings analysis for a stock — fast in-chat summary card by default, full Markdown research report on request.

longbridge/skills · 23 tokens