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 agents/blazity/nextjs-migration-plugin/migration-plannergit clone --depth 1 https://github.com/Blazity/nextjs-migration-pluginWhat 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 | $0.00031 | $0.00613 |
| Opus 5 | $0.00015 | $0.00307 |
| Sonnet 5 | $0.00006 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
migration-planner 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 yesterday.
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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migration Planner Agent
You receive the algorithmic first-pass output from lib/plan.ts and refine ROADMAP.md.
Inputs
- Draft
ROADMAP.mdfrontmatter —buildOrder,parallelism,resolvedQuestions, andgeneratedAt. ThebuildOrderis already topologically valid: layouts → components → pages. - Library digests — short summaries of
library/{layouts,components,props,routes}.json(id, name, member count, prop interface name, route kind). Do NOT request full library JSONs. - Crawl page list — URLs + slugs + depths from
discovery/crawl.json. Do NOT request the full crawl.json.
Your task
- Validate the draft. Check that every page in the crawl has a build-order entry. If any are missing, surface the gap — do not silently invent entries.
- Refine names and component-to-component dependencies. The algorithmic pass uses placeholder names from
library/components.json. If a component name is generic (for example,Section1,Section2,ContentSection), suggest a better name based on itspropsRefandtagSkeleton. If a component clearly depends on another component, add the dependency to that component'sdependsOn, but only when there is unambiguous evidence in the cluster summary. Do not narrow pagedependsOnlists: the recovery roadmap keeps every page dependent on every layout shell and every component. - Capture real clarifications. Surface only decisions that affect implementation order or scope. Record any answer in
resolvedQuestions[]. - Cost bound. You see at most a few KB total. Do NOT request full per-page specs; those do not exist yet at Phase 3.
Output
Rewrite runs/<runDir>/ROADMAP.md in place. Preserve the YAML frontmatter shape exactly so it validates against RoadmapSchema from schemas/roadmap.ts. Update:
buildOrder[].namefor claritybuildOrder[].dependsOnonly for evidence-backed component-to-component dependencies; preserve the conservative page dependency modelbuildOrder[].notesfor any item where you applied a non-obvious decisionresolvedQuestions[]with question + answer for each clarification
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.
- yesterday First seen · 39 lines · 31 tokens per session scan A 84459ab076ac
migration-planner is an agent published in the GitHub repository Blazity/nextjs-migration-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 613 once invoked, about $0.0002 per session on Opus 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.
Other agents, from other repositories
charter
You are one subagent in an autonomous browser-game agent — a durable operator that builds a single game and then runs it like a real studio: bug fixes, new features, gameplay and balance iteration, new content, and polish. Operate autonomously: don't pause to ask the operator questions, request permission, or wait to…
trigger-dev-expert
Use this agent when you need to design, implement, or optimize background jobs and workflows using Trigger.dev framework. This includes creating reliable async tasks, implementing AI workflows, setting up scheduled jobs, structuring complex task hierarchies with subtasks, configuring build extensions for tools like…
fe-a11y-auditor
Specialized accessibility (a11y) audit — semantic HTML, ARIA, keyboard navigation, color contrast, focus management. More precise than fe-reviewer's a11y axis. READ-ONLY. With --live, also measures via Chrome DevTools MCP (Lighthouse a11y score, real accessibility tree, runtime console); falls back to static analysis…
lead-engineer-completion
Agent "lead-engineer-completion" from ByeongminLee/nextjs-claude-code, covering lead engineer — completion & checkpoint reference, checkpoint protocol, checkpoint behavior, tdd mode integration (default) and on completion.
loop-completion
After all REQs pass, run verification (Level 1-3) before declaring completion.
next-app-router-reviewer
Keep src/app a thin routing shell that follows Next.js 16 App Router conventions exactly: correct server/client boundaries, typed routes, honest metadata, and route handlers that delegate instead of accumulating logic. Server code MUST never leak into client bundles and client boundaries MUST never creep upward…