rainman: Skill for Claude Code

.claude/skills/claude-migrate/SKILL.md

claude-migrate is a skill for Claude Code from yan-yanko/rainman. It costs 193 tokens per session (4,495 once invoked), scanned A, original, MIT.

A tool for checking and updating older repositories so they follow current Claude Code practices, while keeping their always-loaded instructions small.

In plain words
What is it for?
Auditing project instructions, checking verification steps and setup, and prescribing a smaller, more focused repository configuration.
Why use it?
It identifies missing guidance and unnecessary context, then recommends moving rather than blindly adding project instructions.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is yan-yanko/rainman's own configuration. It tells Claude Code how to work on rainman itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rainman configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yan-yanko/rainman. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/yan-yanko/rainman/main/.claude/skills/claude-migrate/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/yan-yanko/rainman

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 claude-migrate

README.md
[![agentmods](https://agentmods.dev/badge/skills/yan-yanko/rainman/claude-migrate/github.svg)](https://agentmods.dev/skills/yan-yanko/rainman/claude-migrate)
Your own site
<a href="https://agentmods.dev/skills/yan-yanko/rainman/claude-migrate"><img src="https://agentmods.dev/badge/skills/yan-yanko/rainman/claude-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 claude-migrate

Your own site · 80×15
<a href="https://agentmods.dev/skills/yan-yanko/rainman/claude-migrate"><img src="https://agentmods.dev/badge/skills/yan-yanko/rainman/claude-migrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 193 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,495 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Agent Snooping · line 101
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • high Agent Snooping · line 101
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • high Agent Snooping · line 104
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • high Agent Snooping · line 104
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • medium Excessive Agency · line 14
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Agent Snooping · line 231
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00193 $0.04495
Opus 5 $0.00097 $0.02247
Sonnet 5 $0.00039 $0.00899
Haiku 4.5 $0.00019 $0.00449

Measured 9d ago against content hash 6d4727638aae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claude-migrate scanned grade A with 1 finding 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 9d 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

row "web SessionStart hook" "$( grep -aqi 'SessionStart' "$root/.claude/settings.json" 2>/dev/null && echo configured || echo none )"

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.claude/skills/claude-migrate/SKILL.md · 356 lines

How it starts

The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claude-migrate

Bring an old repo up to how Claude Code actually works today — by removing, not adding. Most "Claude-readiness" audits are additive: they reward more commands, more MCP, more hooks, and score a bloated repo as "ready." This tool is subtractive: a lean CLAUDE.md, fewer always-on rules, a low token budget. It scores less higher — with one floor: the lean file must still be sufficient (hard rules + how-to-verify survive).

Two questions, one tool. "Is my project ready for today's Claude?" needs a complete answer — so the diagnosis reports on every readiness pillar, including what's missing (no verify loop, no web SessionStart hook, no commands). "How do I fix it without making it worse?" needs a disciplined answer — so the prescription stays subtractive: slim and relocate, and add only what's demonstrably needed. Comprehensive detection, restrained prescription.

The one idea this tool is built on

Being subtractive is only safe if the knowledge you strip has somewhere to go. Otherwise "subtractive" is just amnesia. So the core move is never delete — it's relocate: move content from always-on context (CLAUDE.md, paid every turn) to on-demand context (a skill, a hook, or memory — paid only when actually needed). Every step below is an instance of that move — including what happens to the old CLAUDE.md itself.

Safety model — READ THIS (the tool can rewrite CLAUDE.md)

This skill can overwrite your project's most important file. It is built so that it is never destructive and never silent:

  1. Diagnose mutates nothing that exists. The only write it makes is creating one new file — the plan (docs/claude-migrate-plan.md). It never edits, moves, or deletes anything: not CLAUDE.md, not settings.json, not memory. Plan-mode-compatible in spirit — the single new-file write is the deliverable, not a mutation of project state. (Non-mutating ≠ zero-write: a fresh advisory doc is fully discardable and changes nothing about existing project state.)
  2. Nothing mutates without one explicit approval of a complete plan that includes the verbatim proposed CLAUDE.md, the full relocation table, and the projected before/after numbers. Approving the plan = approving the exact bytes.
  3. Apply refuses to run on a dirty git tree. A clean tree is a precondition, so every change lands as a reviewable diff and git restore . (or a branch reset) is a complete undo. Git is the safety net, not the approval prompt.
  4. The old CLAUDE.md is archived, never deleted — moved to .claude/archive/ (and/or into memory) before the new one is written.
  5. settings.json is merged, never overwritten. Show the hook diff; abort on any conflict rather than clobbering existing hooks.
  6. Proof of no harm. Capture the verify-loop (tests + lint) result before apply; it must be no worse after. Green-before / red-after means the migration broke something → stop and surface it; the clean tree makes rollback one command.

Read the full file on GitHub · 356 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 356 lines · 193 tokens per session scan A 6d4727638aae

Subscribe to this mod's changes

claude-migrate is a skill published in the GitHub repository yan-yanko/rainman (21 stars, last pushed 16d ago), licensed MIT. It adds 193 tokens to every session and 4,495 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.