New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Blueprint Refactor Survey

by receptron in receptron/mulmoterminal

Find what is worth tidying in this repository, measure each candidate's value and risk, and write a plan the person approves — including what to leave alone and why.

MITAuto-check passedAgent Workflows

Install Blueprint Refactor Survey

skills CLI
$ npx skills add receptron/mulmoterminal --skill blueprint-refactor-survey -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install receptron/mulmoterminal blueprint-refactor-survey --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/receptron/mulmoterminal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/blueprints/refactor/skills/survey .claude/skills/blueprint-refactor-survey && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
blueprint-refactor-survey
GitHub stars
237
Token cost
~1.3k tokens
SKILL.md length
758 words
Files
1
Skills in repo
31
Repo updated
First seen
Licence
MIT

At a glance

Find what is worth tidying in this repository, measure each candidate's value and risk, and write a plan the person approves — including what to leave alone and why.

  • Works in 3 steps: .blueprint/spec.md, for the person, in… → .blueprint/open-questions.md: anything… → .blueprint/targets.json, the machine's…
  • Tasks that involve Refactoring
  • SKILL.md covers What to optimise for, Finding candidates, Measuring each candidate and Writing the plan, plus 1 more section
  • Calls gh and git

What it does

Blueprint Refactor Survey is an agent skill from receptron/mulmoterminal. Find what is worth tidying in this repository, measure each candidate's value and risk, and write a plan the person approves — including what to leave alone and why.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Refactoring and Planning. The repository describes itself as: Run multiple Claude Code and Codex sessions in parallel — a browser terminal grid that shows which agent needs you. Local, tmux-backed, MIT. The licence is MIT.

When your agent uses it

  • Tasks that involve Refactoring
  • Tasks that involve Planning

Example prompts

  • “/blueprint-refactor-survey”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. .blueprint/spec.md, for the person, in the language the build's prompt says they read (without one, in Japanese). It opens with what…
  2. .blueprint/open-questions.md: anything you could not decide. Empty is fine.
  3. .blueprint/targets.json, the machine's copy, in the order they will be done

What it can do on your machine

Read from SKILL.md and the folder at commit b3f6ff0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Blueprint Refactor Survey loads about 1.3k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 758 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from receptron/mulmoterminal at commit b3f6ff0, republished under its MIT licence (© receptron). 758 words, ~1,272 tokens.

Download SKILL.mdSave it as .claude/skills/blueprint-refactor-survey/SKILL.md (or your agent's skills folder).
name
blueprint-refactor-survey
description
Find what is worth tidying in this repository, measure each candidate's value and risk, and write a plan the person approves — including what to leave alone and why.

Choose what to touch

A campaign spends most of its risk here. A target chosen wrongly is a pull request, a CI run and a merge spent on something that did not need doing — and a change nobody asked for is a change that can break something. Read .blueprint/answers.json for the goals, the limit on changes, and what to avoid.

What to optimise for

In order, because they conflict:

a decision made testable > a block moved with its behaviour proved > a block moved with its behaviour argued > a costed no

The last beats the third. "A lint bound cleared" is not on the list: a bound tells you where to look, never what good looks like. Readable beats short.

Finding candidates

Use what the repository already measures, then read the code yourself:

  • Its own tools. Run the lint (max-lines-per-function, complexity and friends), and any knip / duplication / jscpd script it has. They point; they do not decide.
  • Untested exports. For each exported symbol, does any test name it? grep -oE "^export (const|function|class) [A-Za-z0-9_]+" f.ts then grep -rlw <name> test/ src/. A file with tests can still have untested exports — often the cheapest wins.
  • Pure logic trapped behind a heavy import — a database client, an SDK that initialises on import, a DOM API. The logic is untestable for a reason unrelated to the logic; the fix is a move, not a rewrite. This is the highest-value shape there is.
  • What breaks if it is wrong: money, a permission boundary, one user's data reaching another, anything printed on a receipt. Rank by this, not by line count.
  • One question answered in several places — grep for the concept, not the symbol. Unifying them (one module, one test asserting they agree) is a correctness change, not a size change.

Skip what is easy to test but worth nothing: style constants, presentation values, a comparator's exact magnitude. Pinning those buys a test that goes red when someone adjusts a layout.

Measuring each candidate

  • Reachable? Find the caller or renderer, not just an import (a type-only import or a test-only reader keeps a file "used"). For a branch that cannot fire today, git log -S "<symbol>" -- <file that would supply it> tells dead since birth (delete) from broken later (fix) — opposite changes.
  • Cost of a move = the mutable cells it writes that are read afterwards, not its length. A region that writes none lifts as-is; one that writes four needs four write-backs, and dropping one still type-checks.
  • Adjacency invariants. What holds only because two pieces of code sit next to each other — an order, a shared answer, no await between a write and its reader? Those have no home after a move.
  • Someone else in the file? gh pr list --state open and git log --oneline -20 -- <file>.
Show full SKILL.md (316 more words)Show less

Writing the plan

  1. .blueprint/spec.md, for the person, in the language the build's prompt says they read (without one, in Japanese). It opens with what approving it means: this build will create a branch, commit, push and open a pull request per target, and — if merge in the answers says so — merge each one once CI is green. Then, per target: what it is, why it is worth doing, how the change will be proved to behave the same, and what could go wrong. Then what you chose not to do and why (a costed no each), and what you did not look at.
  2. .blueprint/open-questions.md: anything you could not decide. Empty is fine.
  3. .blueprint/targets.json, the machine's copy, in the order they will be done:
    json
    { "targets": [
  { "id": "split-parse-order", "kind": "decompose", "title": "注文の解析を関数に分ける",
    "files": ["src/order.ts"], "why": "...", "proof": "replica differential over generated orders",
    "status": "todo" }
] }
    kind is one of ci, decompose, dedupe, test, dead-code, types, other. Every target starts todo. No more targets than maxChanges.
    • If .blueprint/ci.json lists gaps, the first target is a ci one that closes them: every later change is merged on CI's word, so CI has to be checking the gates before anything else moves.
    • Put a test target before a later target that needs a guard the code does not have yet.

One target is one region and one pull request — anything that could be reverted on its own is a separate target.

Change nothing in the repository in this step.

Done when the check passes: the plan parses, every target is still to do, and there are no more than the agreed number.

Always

  • Read .blueprint/answers.json. Do not plan anything in the places it says to avoid.
  • When you need a decision, ask it through the blueprint question tool and stop. Do not guess.
  • Say you are done by stopping; the executor runs the check. Do not claim success yourself.

© receptron, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in blueprints/refactor/skills/survey of receptron/mulmoterminal.

Open the folder on GitHubat commit b3f6ff0

Compare with similar skills

Blueprint Refactor Survey next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Blueprint Refactor Survey compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Blueprint Refactor Survey this skillreceptron/mulmoterminal237—~1.3kAutomated safety check: PassMIT
Improvefossasia/eventyay-interpretation1.6k10 repos~3.7kAutomated safety check: WarnMIT
One Three One RuleTommy-yw/RunbookHermes5463 repos~1.3kAutomated safety check: PassMIT
Designsynnaxlabs/synnax128—~4.5kAutomated safety check: PassCustom licence
Speckdlbs/kandev912—~2.1kAutomated safety check: PassAGPL-3.0
Workflow Orchestrationvxcozy/workflow-orchestration116—~1kAutomated safety check: PassMIT

Similar skills

  • Improve

    fossasia/eventyay-interpretation

    Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute.

    1.6k GitHub starsUsed in 10 repos~3.7k tokens
    Agent WorkflowsAuto-check: warnings

  • One Three One Rule

    Tommy-yw/RunbookHermes

    Structured decision-making framework for technical proposals and trade-off analysis.

    546 GitHub starsUsed in 3 repos~1.3k tokens
    Agent WorkflowsAuto-check passed

  • Design

    synnaxlabs/synnax

    Process and hard rules for designing and planning complex new features, refactors, and re-architectures.

    128 GitHub stars~4.5k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Spec

    kdlbs/kandev

    Create or update Kandev product requirements and system-design documents before implementation.

    912 GitHub stars~2.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Workflow Orchestration

    vxcozy/workflow-orchestration

    Disciplined task execution with planning, verification, and self-improvement loops.

    116 GitHub stars~1k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed

  • Plan Writing

    xenitV1/Antigravity-Workflows

    Structured task planning with clear breakdowns, dependencies, and verification criteria.

    130 GitHub starsUsed in 8 repos~994 tokens
    DevelopmentAuto-check passed

More from receptron/mulmoterminal

All 31 skills in this repo

  • Mulmoterminal Bug Report

    receptron/mulmoterminal

    Help desk for "MulmoTerminal is broken". An agent skill from receptron/mulmoterminal.

    238 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Mulmoterminal Decisions

    receptron/mulmoterminal

    Check what this project's humans have already been asked, and how they answered, before asking them something similar.

    238 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Mulmoterminal Help

    receptron/mulmoterminal

    Help desk for questions about MulmoTerminal itself — what it can do, how a feature or a part of the screen works, how to set something up, what is new in this version or in the latest one.

    238 GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • Mulmoterminal Notify

    receptron/mulmoterminal

    Decide which moments MulmoTerminal beeps or pushes for, and what each one plays — soundKinds, sounds and pushKinds in ~/.mulmoterminal/config.json, plus a per-project sound / sounds in…

    238 GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Mulmoterminal Theme

    receptron/mulmoterminal

    Build a colour scheme of your own for MulmoTerminal — one that joins Midnight, Nord, Daylight and Solarized in Settings' theme picker and can then be pinned per project.

    238 GitHub stars~2.5k tokensUpdated today
    Auto-check passed

  • Blueprint Ask Answer

    receptron/mulmoterminal

    Answer each question from the named documents only, quoting where the answer is written, or saying plainly that the documents do not say — changing nothing yet.

    238 GitHub stars~780 tokensUpdated today
    Auto-check passed

Categories

Questions about Blueprint Refactor Survey

What does Blueprint Refactor Survey do?

Find what is worth tidying in this repository, measure each candidate's value and risk, and write a plan the person approves — including what to leave alone and why. Blueprint Refactor Survey is an agent skill from receptron/mulmoterminal. Find what is worth tidying in this repository, measure each candidate's value and risk, and write a plan the person approves — including what to leave alone and why.

When should I use Blueprint Refactor Survey?

Blueprint Refactor Survey fits situations like: tasks that involve Refactoring; tasks that involve Planning.

How do I install Blueprint Refactor Survey in Claude Code?

Run `npx skills add receptron/mulmoterminal --skill blueprint-refactor-survey -a claude-code`. Or copy the skill folder (blueprints/refactor/skills/survey in receptron/mulmoterminal) into .claude/skills/blueprint-refactor-survey in your project. Claude Code loads it when a task matches its description.

How do I install Blueprint Refactor Survey in Codex?

Run `npx skills add receptron/mulmoterminal --skill blueprint-refactor-survey -a codex`. Or copy the skill folder (blueprints/refactor/skills/survey in receptron/mulmoterminal) into .agents/skills/blueprint-refactor-survey in your project. Codex loads it when a task matches its description.

Can I use Blueprint Refactor Survey in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add receptron/mulmoterminal --skill blueprint-refactor-survey -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/blueprint-refactor-survey, .gemini/skills/blueprint-refactor-survey, .github/skills/blueprint-refactor-survey and .opencode/skills/blueprint-refactor-survey in your project.

What does Blueprint Refactor Survey need to run?

Going by SKILL.md and its folder, Blueprint Refactor Survey needs the command-line tools its instructions call (gh and git).

Does Blueprint Refactor Survey access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Blueprint Refactor Survey safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Blueprint Refactor Survey use?

Blueprint Refactor Survey is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Blueprint Refactor Survey use?

About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Blueprint Refactor Survey?

Skills that share tags, products or a category with Blueprint Refactor Survey: Improve (fossasia/eventyay-interpretation, 1.6k stars), One Three One Rule (Tommy-yw/RunbookHermes, 546 stars), Design (synnaxlabs/synnax, 128 stars) and Spec (kdlbs/kandev, 912 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Blueprint Refactor Survey?

receptron (a GitHub organization) maintains it in receptron/mulmoterminal, which has 237 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on October 10, 2026.

Source: receptron/mulmoterminal on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.