claude-ai-dangerous: Command for Claude Code

.claude/commands/ai/migration.md

AI: Migration is a command for Claude Code from hlop3z/claude-ai-dangerous. It costs 26 tokens per session (1,403 once invoked), scanned C, original, MIT.

A migration command that condenses an OpenSpec project workflow into one committed PROJECT.md file. OpenSpec is a system for managing project specifications, planned changes, and implementation tasks.

In plain words
What is it for?
Use it when retiring OpenSpec and replacing its project-specific information with a self-contained PROJECT.md at the repository root.
Why use it?
It lets you remove OpenSpec without losing the project’s durable decisions, capability requirements, or useful context. The engineering rules in .canon/ remain in their existing location.

Command for Claude Code

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

This is hlop3z/claude-ai-dangerous's own configuration. It tells Claude Code how to work on claude-ai-dangerous 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 claude-ai-dangerous configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hlop3z/claude-ai-dangerous. 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/hlop3z/claude-ai-dangerous/main/.claude/commands/ai/migration.md
Clone the repo
git clone --depth 1 https://github.com/hlop3z/claude-ai-dangerous

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 AI: Migration

README.md
[![agentmods](https://agentmods.dev/badge/commands/hlop3z/claude-ai-dangerous/migration/github.svg)](https://agentmods.dev/commands/hlop3z/claude-ai-dangerous/migration)
Your own site
<a href="https://agentmods.dev/commands/hlop3z/claude-ai-dangerous/migration"><img src="https://agentmods.dev/badge/commands/hlop3z/claude-ai-dangerous/migration/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 AI: Migration

Your own site · 80×15
<a href="https://agentmods.dev/commands/hlop3z/claude-ai-dangerous/migration"><img src="https://agentmods.dev/badge/commands/hlop3z/claude-ai-dangerous/migration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,403 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00026 $0.01403
Opus 5 $0.00013 $0.00701
Sonnet 5 $0.00005 $0.00281
Haiku 4.5 $0.00003 $0.00140

Measured 9d ago against content hash 109d0bf712fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

AI: Migration scanned grade C 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- Every build-vs-adopt decision that shaped the system. -->
.claude/commands/ai/migration.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Distill everything that matters from the OpenSpec workflow into one self-contained file (PROJECT.md at the project root) so the user can delete openspec/ — config, specs, changes, tasks — and still retain the core of what the project is, why, and how it was decided. This is a consolidation, not a snapshot: OpenSpec is going away, so the output must stand on its own with zero pointers back into openspec/.

The canon is not in scope. .canon/ is ours and survives OpenSpec's removal untouched — so PROJECT.md must NOT absorb, duplicate, or condense the engineering rules and guidelines. Pointing at .canon/ is correct here; copying it in would create a second home for rules that already have one.

This is the inverse of /ai:handoff. Handoff references canonical homes and stays gitignored. Migration absorbs those homes into a single committed file that becomes the new canonical home once OpenSpec is removed.

What to keep (the things that matter most)

Include only durable essence. When in doubt, ask: "if OpenSpec were deleted tomorrow, would losing this hurt?" If no, drop it.

  • Capability contracts — for each capability in openspec/specs/, its purpose and its core requirements/invariants (the MUST/SHOULD behavior that must hold). Condense scenarios to the invariant they protect; drop exhaustive WHEN/THEN tables.
  • Architecture — the structural shape: core vs adapters, inward-only dependency direction, workspace/crate layout, where composition wiring lives. The HOW that outlives any single change.
  • Decisions (ADRs) — every recorded build-vs-adopt decision from the design.md ADR blocks across all changes (active and archived): the concern, the choice (Rent/Adopt/Extend/Fork/Build), the chosen tool, and the one-line why. This is the highest- value content — decisions and their rationale are the least recoverable from code.
  • Chosen tech stack — the concrete tools/vendors actually selected (languages, backends, libraries), each tied to the decision that picked it.

Read the full file on GitHub · 122 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. 9d ago First seen · 122 lines · 26 tokens per session scan C 109d0bf712fc

Subscribe to this mod's changes

AI: Migration is a command published in the GitHub repository hlop3z/claude-ai-dangerous (2 stars, last pushed 23d ago), licensed MIT. It adds 26 tokens to every session and 1,403 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.