tommymorgan:migrate-to-living-specs

tommymorgan:migrate-to-living-specs is a command for Claude Code from tommymorgan/claude-plugins. It costs 24 tokens per session (558 once invoked), scanned A, original, MIT.

A command that turns old project plans into living specifications: structured files describing expected software behavior. It writes these scenarios in Gherkin, a readable format used for behavior-driven tests.

In plain words
What is it for?
Use it to scan a project's plans/ directory, extract requirements and technical scenarios, group them by feature, and create .feature files in features/.
Why use it?
It saves developers from manually rebuilding current specifications from historical planning documents. The generated files keep user-facing and technical behavior organized by feature.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 tools/claude-plugins/tommymorgan/migration/commands/migrate.py ..

Part of the tommymorgan plugin — 10 skills, 14 commands, 13 agents, 4 hooks shipped together

Good fit Use it to scan a project's plans/ directory, extract requirements and technical scenarios, group them by feature, and create .feature files in features/.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/tommymorgan/claude-plugins
agentmods
npx agentmods add commands/tommymorgan/claude-plugins/migrate-to-living-specs

Made for: Claude Code.

Or install tommymorgan, the plugin that ships this one along with the rest of its 10 skills, 14 commands, 13 agents, 4 hooks.

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 tommymorgan:migrate-to-living-specs

README.md
[![agentmods](https://agentmods.dev/badge/commands/tommymorgan/claude-plugins/migrate-to-living-specs/github.svg)](https://agentmods.dev/commands/tommymorgan/claude-plugins/migrate-to-living-specs)
Your own site
<a href="https://agentmods.dev/commands/tommymorgan/claude-plugins/migrate-to-living-specs"><img src="https://agentmods.dev/badge/commands/tommymorgan/claude-plugins/migrate-to-living-specs/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 tommymorgan:migrate-to-living-specs

Your own site · 80×15
<a href="https://agentmods.dev/commands/tommymorgan/claude-plugins/migrate-to-living-specs"><img src="https://agentmods.dev/badge/commands/tommymorgan/claude-plugins/migrate-to-living-specs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 558 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00024 $0.00558
Opus 5 $0.00012 $0.00279
Sonnet 5 $0.00005 $0.00112
Haiku 4.5 $0.00002 $0.00056

Measured 10d ago against content hash eba53140bea5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tommymorgan:migrate-to-living-specs 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 10d 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.

tommymorgan/migration/commands/migrate-to-living-specs.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Migrate Historical Plans to Living Specifications

One-time migration that creates living .feature files from historical plan files.

Usage

/tommymorgan:migrate-to-living-specs [project-path]

If no path provided, uses current project (inferred from working directory).

What This Does

  1. Scans plans/ directory for historical plan files
  2. Extracts Gherkin scenarios from User Requirements and Technical Specifications
  3. Groups scenarios by feature area using semantic similarity
  4. Tags scenarios appropriately (@user, @technical)
  5. Creates .feature files in features/ directory
  6. Reports progress with success/failure counts

Process

cd $PROJECT_PATH

# Run migration tool
python3 tools/claude-plugins/tommymorgan/migration/commands/migrate.py .

# Results will be in features/ directory
ls features/*.feature

Output

Creates .feature files in <project>/features/ directory:

features/
  authentication.feature
  user-management.feature
  analytics.feature

Each .feature file contains:

Feature: <Feature Name>

  @user
  Scenario: User-facing behavior
    Given user context
    When user action
    Then user outcome

  @technical
  Scenario: Technical requirement
    Given system state
    When technical action
    Then technical outcome

Summary Report

After completion, shows:

Migration complete!

Processed: 15 plans
Successes: 12
Failures: 3
Created: 5 .feature files

Errors:
- plan-old.md: No scenarios found
- plan-broken.md: Parse error
- plan-incomplete.md: No Gherkin blocks

Check features/ directory for living specifications.

When to Use

Run this ONCE to bootstrap living documentation from historical plans.

After migration:

  • New plans will reference existing living specs (interactive reconciliation)
  • Work tool will automatically update living specs
  • Never run migration again (living specs are maintained going forward)

Important Notes

  • Historical plans remain unchanged (valuable record)
  • Semantic similarity groups related scenarios (0.8 threshold)
  • Processes in batches for memory efficiency
  • Continues on errors, reports all issues at end
  • Scenarios below 0.8 similarity flagged for manual review

Read the full file on GitHub · 108 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. 10d ago First seen · 108 lines · 24 tokens per session scan A eba53140bea5

Subscribe to this mod's changes

tommymorgan:migrate-to-living-specs is a command published in the GitHub repository tommymorgan/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 558 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 2026-08-31.