A migration step that moves a repository from an older documentation layout to the current three-pillars-docs layout.

It is for previewing and applying the repository's documentation-layout migration.

It avoids manually moving and adapting the files needed for the newer structure, while requiring a clean working tree before changes are applied.

tp-migrate — Skill for Claude Code and Codex by CurtisThe: A migration step that moves a repository from an…

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 skills/curtisthe/three-pillars-plugin/tp-migrate

Any agent

npx skills add CurtisThe/three-pillars-plugin --skill tp-migrate

Clone the repo

git clone --depth 1 https://github.com/CurtisThe/three-pillars-plugin

Made for: Claude Code, Codex.

Or install three-pillars, the plugin that ships this one along with the rest of its 37 skills, 20 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/curtisthe/three-pillars-plugin/tp-migrate.svg)](https://agentmods.dev/skills/curtisthe/three-pillars-plugin/tp-migrate)

Your own site

<a href="https://agentmods.dev/skills/curtisthe/three-pillars-plugin/tp-migrate"><img src="https://agentmods.dev/badge/skills/curtisthe/three-pillars-plugin/tp-migrate.svg" alt="Measured on agentmods" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 822 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.

Model	Per session	Once invoked
Fable 5	$0.00041	$0.00822
Opus 5	$0.00020	$0.00411
Sonnet 5	$0.00008	$0.00164
Haiku 4.5	$0.00004	$0.00082

Measured 4d ago against content hash 6380d153439e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tp-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 4d 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.

skills/tp-migrate/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Migrate

Move a repo from the legacy docs/tdd-* layout to the current three-pillars-docs/tp-* layout. This skill is a thin wrapper around skills/_shared/migrate.py — it handles the dry-run preview and user confirmation, then delegates the actual work to migrate.py --apply.

Argument: --repo {path} (optional) — defaults to current working directory.

Prerequisites

The repo's working tree must be clean (no uncommitted changes). migrate.py --apply refuses to proceed otherwise.
Python 3 must be available (same dependency as release.sh).

Steps

Run first-run preflight per skills/_shared/first-run.md. Exception: this skill is the explicit exception to first-run's old-layout-detected refusal — the refusal does NOT apply when the calling skill is tp-migrate, since the whole point of this skill is to migrate. Branch-protection and release checks still apply normally.
Show the plan: run python3 "$TP_ROOT"/skills/_shared/migrate.py --dry-run --repo {repo} and print its output verbatim.
Branch on the dry-run output:
- If the output says the repo is already migrated: report and stop. No work needed.
- If the output says the repo is already on the current layout: report and stop. No work needed.
- Otherwise, the output is a list of moves and rewrites. Continue.
Confirm with the user: ask "Apply this migration plan? (yes/no)". Stop on no.
Apply the migration: run python3 "$TP_ROOT"/skills/_shared/migrate.py --apply --repo {repo}. This delegates everything to migrate.py — moves, rewrites, the new commit, and the config stamp. This skill itself must not stamp the migration field; ownership of that field belongs to migrate.py alone.
Read back and report:
- Read .three-pillars/config.json and confirm migration.completed_at is non-null and migration.from_layout is "docs+tdd".
- Print the MEMORY.md advisory that migrate.py emitted, plus a one-line summary: "Migrated repo in commit {sha}. Run /tp-guide to see what's next."

Read the full file on GitHub · 41 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.

4d ago First seen · 41 lines · 41 tokens per session scan A 6380d153439e

Subscribe to this mod's changes

tp-migrate is a skill published in the GitHub repository CurtisThe/three-pillars-plugin (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 822 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.

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens