migrate-v3

migrate-v3 is a command for Claude Code from yibie/SPEC-AGENTS.md. It costs 19 tokens per session (711 once invoked), scanned A, original, MIT.

A command for moving a legacy SPEC-AGENTS version 2 project to the version 3 structure, which uses the EDPP process.

In plain words
What is it for?
Use it when converting a SPEC-AGENTS v2 project to the EDPP-based v3 format.
Why use it?
It helps update an older project layout so it can follow the newer workflow.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

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 commands/yibie/spec-agents.md/migrate-v3
Clone the repo
git clone --depth 1 https://github.com/yibie/SPEC-AGENTS.md

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 migrate-v3

README.md
[![agentmods](https://agentmods.dev/badge/commands/yibie/spec-agents.md/migrate-v3.svg)](https://agentmods.dev/commands/yibie/spec-agents.md/migrate-v3)
Your own site
<a href="https://agentmods.dev/commands/yibie/spec-agents.md/migrate-v3"><img src="https://agentmods.dev/badge/commands/yibie/spec-agents.md/migrate-v3.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 711 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 5.1 $0.00019 $0.00711
Opus 5 $0.00010 $0.00356
Sonnet 5 $0.00004 $0.00142
Haiku 4.5 $0.00002 $0.00071

Measured 6d ago against content hash 5cd6817be4ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

migrate-v3 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 6d 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.

.spec-agents/archive/legacy-phrase/commands/migrate-v3.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/migrate-v3 — Migrate Legacy SPEC-AGENTS Projects

Use this command when a project already has the old static SPEC-AGENTS layout:

.phrase/phases/
  phase-*/
    spec_*
    plan_*
    task_*
    change_*
    issue_*

The migration goal is not to convert every old file into a new format. The goal is to archive historical detail, rebuild the active context, and promote only decision-relevant material into v3.

Target Structure

.phrase/
  decision.md
  roadmap.md
  current.md
  evidence.md
  archive/
    legacy-v2/

Steps

  1. Inventory legacy material. List existing .phrase/phases/, old spec_*, plan_*, task_*, change_*, issue_*, adr_*, and tech-refer_* files.

  2. Create v3 files if missing. Ensure these files exist:

    .phrase/decision.md
    .phrase/roadmap.md
    .phrase/current.md
    .phrase/evidence.md
    .phrase/archive/
    
  3. Archive old phase material. Move completed, stale, or legacy phase directories under:

    .phrase/archive/legacy-v2/
    

    Do not delete old material during migration unless the user explicitly asks.

  4. Promote durable rules. Extract long-lived constraints from old adr_*, tech-refer_*, and project notes into .phrase/decision.md, .phrase/adr/, or .phrase/protocol/.

  5. Compress roadmap. Extract phase-level direction from old plan_* or phase indexes into .phrase/roadmap.md. Do not copy detailed task lists.

  6. Rebuild current context. Extract only the active phase into .phrase/current.md:

    • goal
    • entry condition
    • scope
    • out of scope
    • acceptance gate
    • active task slice
    • verification plan
    • known blockers
  7. Promote evidence. Extract only decision-relevant facts into .phrase/evidence.md:

    • unresolved blockers
    • verified results
    • failed assumptions
    • rejected paths
    • next phase recommendation
  8. Write cutover note. Add an evidence entry named v3 migration cutover that records where old material was archived and which files now define active context.

Read the full file on GitHub · 120 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. 6d ago First seen · 120 lines · 19 tokens per session scan A 5cd6817be4ce

Subscribe to this mod's changes

migrate-v3 is a command published in the GitHub repository yibie/SPEC-AGENTS.md (126 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 711 once invoked, about $0.0001 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 2026-08-30.