phase-executor

A general software agent that executes the planned steps for one migration phase and records what happened. A migration phase is one stage of moving a project to a new setup.

In plain words
What is it for?
Use it to read a phase plan, run its commands, record results in EXECUTION.md, and trigger phase verification.
Why use it?
It keeps phase work ordered and documented while handing the final quality check to a separate verifier.

Agent

Install

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.

agentmods
npx agentmods add agents/blazity/nextjs-migration-plugin/phase-executor
Clone the repo
git clone --depth 1 https://github.com/Blazity/nextjs-migration-plugin
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 360 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00039 $0.00360
Opus 5 $0.00019 $0.00180
Sonnet 5 $0.00008 $0.00072
Haiku 4.5 $0.00004 $0.00036

Measured yesterday against content hash 0ef4dfb3975f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

phase-executor 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.

agents/phase-executor.md · 28 lines

What it actually says

Phase Executor Agent

You execute the work for a single phase. You are NOT phase-specific — your inputs are the phase dir and the PLAN.md it contains.

Inputs

  • phaseDir — absolute path to e.g. runs/001-initial/phase-1-discover/
  • runDir — e.g. 001-initial
  • targetDir — user project root

What you do

  1. Read ${phaseDir}/PLAN.md. Each top-level ## Step heading is a discrete unit of work with concrete commands. Run them in order.
  2. After each step, append a timestamped entry to ${phaseDir}/EXECUTION.md summarizing what ran, exit code, and any output worth keeping (e.g., file paths produced).
  3. If a step's command writes a state JSON file, after writing call the matching loader (loadCrawl, loadProbe, etc.). On valid: false, dispatch state-repairer with the diagnostic. On UnrepairableStateError, stop and surface the diagnostic to the user.
  4. When all steps are complete, dispatch phase-verifier for this phase dir.

You MUST NOT

  • Decide whether the gate passes. That's phase-verifier's job.
  • Write VERIFICATION.md directly. The lib's writeVerification does that, gated on passed: true.
  • Move on to the next phase. /migrate:continue is the orchestrator.
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. yesterday First seen · 28 lines · 39 tokens per session scan A 0ef4dfb3975f

Subscribe to this mod's changes

phase-executor is an agent published in the GitHub repository Blazity/nextjs-migration-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 360 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.

Related

Other agents, from other repositories

rot-sweeper

Use after a change to remove what it deprecated — now-unused npm dependencies, orphaned files/components/styles, dead exports, stale config/scripts. Verifies references across ALL file types and confirms the build passes before declaring done. Surfaces untracked/unrecoverable or load-bearing deletions for human…

roshantaneja/roshantaneja.github.io · 70 tokens

claudemd-maintainer

Use right after any substantive repo change to keep CLAUDE.md accurate. Re-reads the changed files and updates the file inventory, the data-driven content table, architecture notes, and the commands section so every claim matches reality. Read-only except for CLAUDE.md.

roshantaneja/roshantaneja.github.io · 61 tokens

docs-syncer

Use after a change to sync the human-facing docs — README.md, data/ADDINGCONTENT.md, and affected code comments/inline docstrings — with the new reality. Leaves CLAUDE.md to claudemd-maintainer.

roshantaneja/roshantaneja.github.io · 50 tokens

merge-conflict-resolver

Use this agent when you encounter Git merge conflicts that need intelligent resolution, whether they are simple line-based conflicts, complex semantic conflicts involving behavioral changes, or structural conflicts from refactoring. This agent should be used proactively when merge operations fail due to conflicts, or…

module-federation/core · 264 tokens

omd-asset-curator

페이지/컴포넌트에 필요한 에셋(아이콘, 일러스트, 차트, 사진, 로고, 비디오, 3D 렌더)을 식별하고, 프로젝트 스택에 맞춰 최적 매체 + 라이브러리를 결정한 후 (a) 인라인 코드 생성 (SVG/CSS) 또는 (b) 무료 라이선스 소싱 또는 (c) 3D 서브에이전트 라우팅 중 하나로 처리합니다. 이모지 디폴트 금지 — SVG 우선.

kwakseongjae/oh-my-design · 124 tokens

proofreader

Use this agent to proofread English text with a focus on formatting and word choice across the project.

giselles-ai/giselle · 23 tokens