Agent skill

Plan Crafting

by tmdgusya in tmdgusya/engineering-discipline

A skill your agent uses when a task's scope is clear and multi-step implementation is needed, before touching code.

No licenceAuto-check passed

Install Plan Crafting

skills CLI
$ npx skills add tmdgusya/engineering-discipline --skill plan-crafting -a claude-code

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

GitHub CLI
$ gh skill install tmdgusya/engineering-discipline plan-crafting --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/tmdgusya/engineering-discipline.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/plan-crafting .claude/skills/plan-crafting && 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
plan-crafting
GitHub stars
125
Token cost
~4k tokens
SKILL.md length
1,770 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
None found

At a glance

A skill your agent uses when a task's scope is clear and multi-step implementation is needed, before touching code.

  • Works in 4 steps: Every step must be executable.… → Task conflicts must be prevented. Tasks… → Self-Review is mandatory. After writing… → …
  • A tasks scope is clear and multi-step implementation is needed
  • SKILL.md covers Core Principle, Hard Gates, When To Use and Input, plus 9 more sections
  • Calls go, cargo and pytest

What it does

Plan Crafting is an agent skill from tmdgusya/engineering-discipline. Use when a task's scope is clear and multi-step implementation is needed, before touching code. Triggered after clarification is complete, or when the user explicitly requests plan creation with a clear prompt.

Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: SKILL for engineering-discipline.

When your agent uses it

  • A tasks scope is clear and multi-step implementation is needed
  • Before touching code
  • Explicitly requests plan creation with a clear prompt

Example prompts

  • “/plan-crafting”

Requirements

  • Python 3

Workflow steps

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

  1. Every step must be executable. Placeholders (TBD, TODO, "implement later") are never allowed.
  2. Task conflicts must be prevented. Tasks modifying the same file must not run in parallel. Tasks with dependencies must wait for…
  3. Self-Review is mandatory. After writing the plan, verify its completeness yourself.
  4. Tasks decompose to minimal feature units. One task produces one clear deliverable.

What it can do on your machine

Read from SKILL.md and the folder at commit 137dead. 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:

    • go
    • cargo
    • pytest

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

  • Network

    No URLs in SKILL.md.

    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

Plan Crafting loads about 4k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 1,770 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~4k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,770 words (~3,966 tokens).

“Writes an executable plan document from a clearly defined work scope. Designed so tasks can be spawned as "worker-validator" pairs in parallel.”

— opening of SKILL.md by tmdgusya
name
plan-crafting

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/plan-crafting of tmdgusya/engineering-discipline.

Open the folder on GitHubat commit 137dead

Compare with similar skills

Plan Crafting 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.

Plan Crafting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Plan Crafting this skilltmdgusya/engineering-discipline125—~4kAutomated safety check: PassNone
CraftLeoYeAI/openclaw-master-skills2.2k—~4.3kAutomated safety check: PassMIT
Craft Documentationonyx-dot-app/onyx32k1 repos~420Automated safety check: PassCustom licence
Craftsundial-org/awesome-openclaw-skills663—~539Automated safety check: PassNone
Ccb ClearSeemSeam/claude_codex_bridge3.6k—~354Automated safety check: PassCustom licence
Ccb ClearSeemSeam/claude_codex_bridge3.6k—~151Automated safety check: PassCustom licence

Similar skills

  • Craft

    LeoYeAI/openclaw-master-skills

    Read and write Craft documents via the Craft Connect API. An agent skill from LeoYeAI/openclaw-master-skills.

    2.2k GitHub stars~4.3k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed
  • Craft Documentation

    onyx-dot-app/onyx

    Answer questions about how Onyx and Onyx Craft work using the official documentation at docs.onyx.app.

    32k GitHub starsUsed in 1 repo~420 tokens
    Auto-check passed
  • Craft

    sundial-org/awesome-openclaw-skills

    Manage Craft notes, documents, and tasks via CLI. An agent skill from sundial-org/awesome-openclaw-skills.

    663 GitHub stars~539 tokensUpdated 7 mo ago
    Knowledge ManagementAuto-check passed
  • Ccb Clear

    SeemSeam/claude_codex_bridge

    Clear CCB managed agent conversation context with ccb clear.

    3.6k GitHub stars~354 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Ccb Clear

    SeemSeam/claude_codex_bridge

    Clear CCB managed agent conversation context with ccb clear.

    3.6k GitHub stars~151 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Ccb Clear

    SeemSeam/claude_codex_bridge

    Clear conversation context for one or more mounted CCB agents using ccb clear.

    3.6k GitHub stars~381 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from tmdgusya/engineering-discipline

All 11 skills in this repo
  • Clarification

    tmdgusya/engineering-discipline

    A skill your agent uses when a user's request is vague, ambiguous, or underspecified.

    125 GitHub stars~3.4k tokensUpdated 3 mo ago
    Auto-check passed
  • Clean AI Slop

    tmdgusya/engineering-discipline

    Corrective cleanup of AI-generated code — removes LLM-specific patterns while preserving behavior.

    125 GitHub stars~1.9k tokensUpdated 3 mo ago
    Auto-check passed
  • Karpathy

    tmdgusya/engineering-discipline

    Behavioral guardrails to prevent common LLM coding mistakes — enforces surgical changes, assumption verification, and scope discipline before and during implementation.

    125 GitHub stars~2k tokensUpdated 3 mo ago
    Auto-check passed
  • Review Work

    tmdgusya/engineering-discipline

    Use after run-plan completes to independently verify the implementation.

    125 GitHub stars~2.5k tokensUpdated 3 mo ago
    Auto-check passed
  • Run Plan

    tmdgusya/engineering-discipline

    A skill your agent uses when you have a written implementation plan to execute.

    125 GitHub stars~4.6k tokensUpdated 3 mo ago
    Auto-check passed
  • Systematic Debugging

    tmdgusya/engineering-discipline

    A skill your agent uses when encountering any bug, test failure, or unexpected behavior.

    125 GitHub stars~2k tokensUpdated 3 mo ago
    Auto-check passed

Questions about Plan Crafting

What does Plan Crafting do?

A skill your agent uses when a task's scope is clear and multi-step implementation is needed, before touching code. Plan Crafting is an agent skill from tmdgusya/engineering-discipline. Use when a task's scope is clear and multi-step implementation is needed, before touching code.

When should I use Plan Crafting?

Plan Crafting fits situations like: A tasks scope is clear and multi-step implementation is needed; before touching code; explicitly requests plan creation with a clear prompt.

How do I install Plan Crafting in Claude Code?

Run `npx skills add tmdgusya/engineering-discipline --skill plan-crafting -a claude-code`. Or copy the skill folder (skills/plan-crafting in tmdgusya/engineering-discipline) into .claude/skills/plan-crafting in your project. Claude Code loads it when a task matches its description.

How do I install Plan Crafting in Codex?

Run `npx skills add tmdgusya/engineering-discipline --skill plan-crafting -a codex`. Or copy the skill folder (skills/plan-crafting in tmdgusya/engineering-discipline) into .agents/skills/plan-crafting in your project. Codex loads it when a task matches its description.

Can I use Plan Crafting 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 tmdgusya/engineering-discipline --skill plan-crafting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/plan-crafting, .gemini/skills/plan-crafting, .github/skills/plan-crafting and .opencode/skills/plan-crafting in your project.

What does Plan Crafting need to run?

Going by SKILL.md and its folder, Plan Crafting needs the command-line tools its instructions call (go, cargo and pytest). Our summary lists: Python 3.

Does Plan Crafting access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Plan Crafting 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 Plan Crafting use?

No licence was found for Plan Crafting or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Plan Crafting use?

About 4k tokens (SKILL.md is roughly 16k 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 Plan Crafting?

Skills that share tags, products or a category with Plan Crafting: Craft (LeoYeAI/openclaw-master-skills, 2.2k stars), Craft Documentation (onyx-dot-app/onyx, 32k stars), Craft (sundial-org/awesome-openclaw-skills, 663 stars) and Ccb Clear (SeemSeam/claude_codex_bridge, 3.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Plan Crafting?

tmdgusya (a GitHub user) maintains it in tmdgusya/engineering-discipline, which has 125 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on July 3, 2026.

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