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.
curl -O https://raw.githubusercontent.com/yan-yanko/rainman/main/.claude/skills/claude-migrate/SKILL.mdgit clone --depth 1 https://github.com/yan-yanko/rainmanWrote 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.
[](https://agentmods.dev/skills/yan-yanko/rainman/claude-migrate)<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.
<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>- NVIDIA SkillSpector warn
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.
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 | $0.00193 | $0.04495 |
| Opus 5 | $0.00097 | $0.02247 |
| Sonnet 5 | $0.00039 | $0.00899 |
| Haiku 4.5 | $0.00019 | $0.00449 |
Grade A, and why
claude-migrate scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
row "web SessionStart hook" "$( 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.
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:
- 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.) - 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.
- 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. - The old CLAUDE.md is archived, never deleted — moved to
.claude/archive/(and/or into memory) before the new one is written. - settings.json is merged, never overwritten. Show the hook diff; abort on any conflict rather than clobbering existing hooks.
- 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.
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.
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.
- 9d ago First seen · 356 lines · 193 tokens per session scan A 6d4727638aae
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.
Other skills, from other repositories
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
init-workspace-context
Classify workspace mode.
handoff
Transfer the current coding, debugging, planning, or architecture session to AI Badger. Use for broad session continuation; use badger-review for an independent review.
semantic-search
Zero-dependency TF-IDF search across MUSE memory, roles, and skills. Use when user wants to find information across their project context.
badger-review
Prepare current-session guidance for an independent AI Badger review of recent repository work. Use only when the user wants a Badger review, not for generic review requests or session continuation.
sitrep
Situational awareness — where am I, what was I doing, what's next. Context recovery after compression, confusion, or mid-session reorientation.