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.
npx agentmods add commands/syntaxway/agent-ready-repo/migrategit clone --depth 1 https://github.com/SyntaxWay/agent-ready-repoWrote 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/commands/syntaxway/agent-ready-repo/migrate)<a href="https://agentmods.dev/commands/syntaxway/agent-ready-repo/migrate"><img src="https://agentmods.dev/badge/commands/syntaxway/agent-ready-repo/migrate.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.03214 |
| Opus 5 | $0.00000 | $0.01607 |
| Sonnet 5 | $0.00000 | $0.00643 |
| Haiku 4.5 | $0.00000 | $0.00321 |
Grade A, and why
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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are converting THIS repository to the AI-ready monorepo template structure. Source template: https://github.com/SyntaxWay/agent-ready-repo
Work through the phases below in order. After Phase 2, pause and show me a summary before continuing.
───────────────────────────────────────────── PHASE 1 — DISCOVERY ─────────────────────────────────────────────
Read every file listed below that exists in this repo:
Project identity: README.md, README.rst, README.txt package.json, pyproject.toml, Cargo.toml, go.mod, build.gradle, pom.xml
AI tool files already present: CLAUDE.md, GEMINI.md, AGENTS.md, CODEX.md .cursorrules, .cursor/rules/ .github/copilot-instructions.md .windsurf/rules/, .windsurfrules .clinerules, .roo/ .aider.conf.yml, .aider.env .claude/, .gemini/, .continue/
Docs: docs/ (all files, up to 3 levels deep) CONTRIBUTING.md, CHANGELOG.md
CI / commands: .github/workflows/ (all files) Makefile, justfile, taskfile.yml
Summarise what you found: A) One paragraph: what does this project do, who uses it? B) Tech stack table: Language | Framework | Package manager | Runtime | Database | Test runner | CI C) Key commands: install, dev, build, test, lint (exact commands, not guesses) D) Monorepo map: every app/package path with a one-line description E) AI tool files found: list each file and its current content summary
───────────────────────────────────────────── PHASE 2 — AI TOOL DETECTION & CONFIRMATION ─────────────────────────────────────────────
Based on Phase 1, identify which AI tools are in use by checking these indicators:
Tool | Indicator files / dirs ───────────────────────────────────────────────────────────────────── Claude Code | CLAUDE.md · .claude/ Cursor | .cursorrules · .cursor/rules/ GitHub Copilot | .github/copilot-instructions.md Gemini CLI | GEMINI.md · .gemini/ Windsurf | .windsurfrules · .windsurf/rules/ Cline / Roo Code | .clinerules · .roo/ Aider | .aider.conf.yml · .aider.env Codex / Amp / | OpenCode / Jules | AGENTS.md (these read it natively — no pointer file needed)
Then ask the user:
"I detected these tools: [LIST].
- Any tools to ADD that aren't listed?
- Any tools to REMOVE (their files will be deleted)?
- Reply with the final list or say 'keep as-is'."
Wait for the user's reply before doing anything else.
───────────────────────────────────────────── PHASE 3 — CREATE / REWRITE AGENTS.md ─────────────────────────────────────────────
IMPORTANT: Re-read this file (.claude/commands/migrate.md) now to ensure you have the full template below — long Phase 1/2 conversations can compress it out of context.
Using the facts from Phase 1, write AGENTS.md at the repo root. If one already exists, rewrite it — don't merge stale content. Use this exact structure (keep all 10 sections, fill every placeholder):
────────────────────────────────────────────────────────────────────────
AGENTS.md — AI Agent Instructions (Root)
This file is the single entry point for AI coding agents (list confirmed tools from Phase 2). Read this FIRST before making any changes. Each app/package may have its own nested AGENTS.md — nearest one wins. Tool-specific pointer files all redirect here; shared rules belong here.
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.
- 3d ago First seen · 327 lines · 0 tokens per session scan A 64d3fff4c175
migrate is a command published in the GitHub repository SyntaxWay/agent-ready-repo (3 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,214 tokens. 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.