Decompose a large feature into single-round backlog items in docs/backlog.md.

Apache-2.0Auto-check passed

Install Plan Feature

skills CLI
$ npx skills add IcantFind-a-username/Sovereign-Founder-OS --skill plan-feature -a claude-code

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

GitHub CLI
$ gh skill install IcantFind-a-username/Sovereign-Founder-OS plan-feature --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/IcantFind-a-username/Sovereign-Founder-OS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/plan-feature .claude/skills/plan-feature && 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-feature
GitHub stars
105
Token cost
~422 tokens
SKILL.md length
212 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

Decompose a large feature into single-round backlog items in docs/backlog.md.

  • Works in 5 steps: Understand the ask. Restate the feature… → Scout the code. Identify the… → Slice. Cut the feature into items where… → …
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Plan Feature is an agent skill from IcantFind-a-username/Sovereign-Founder-OS. Decompose a large feature into single-round backlog items in docs/backlog.md. Planning only — implementation is forbidden in this skill. Every feature too big for one medium commit MUST pass through this step before any code is written.

Its SKILL.md is about 420 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: Build your AI company in minutes. Your data never leaves your machine. The licence is Apache-2.0.

Example prompts

  • “/plan-feature”

Workflow steps

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

  1. Understand the ask. Restate the feature in one paragraph: user-visible
  2. Scout the code. Identify the crates/directories involved. Use
  3. Slice. Cut the feature into items where each item
  4. Write the entries into docs/backlog.md in dependency order, using
  5. Report the slice list to the user for approval. Do not start

What it can do on your machine

Read from SKILL.md and the folder at commit 5b069d4. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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 Feature loads about 422 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 212 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~422

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 IcantFind-a-username/Sovereign-Founder-OS at commit 5b069d4, republished under its Apache-2.0 licence (© IcantFind-a-username). 212 words, ~422 tokens.

Download SKILL.mdSave it as .claude/skills/plan-feature/SKILL.md (or your agent's skills folder).
name
plan-feature
description
Decompose a large feature into single-round backlog items in docs/backlog.md. Planning only — implementation is forbidden in this skill. Every feature too big for one medium commit MUST pass through this step before any code is written.

Plan a feature into backlog items

This skill produces backlog entries, nothing else. Writing or editing any source file, test, or config during this skill is a violation — if you catch yourself implementing, stop and put it in the backlog instead.

Steps

  1. Understand the ask. Restate the feature in one paragraph: user-visible behavior, affected subsystems, what is explicitly out of scope.
  2. Scout the code. Identify the crates/directories involved. Use subagents for exploration and have them return conclusions only. Check rfcs/ and ARCHITECTURE.md — if the feature contradicts an accepted RFC, stop and surface that instead of planning around it.
  3. Slice. Cut the feature into items where each item:
    • is completable in ONE /iterate round (≈ one medium commit);
    • names its directory-level scope (crates/x, apps/cli/src/y);
    • has done criteria that a test can verify (name the test you expect);
    • leaves the workspace green when it lands — no item may depend on a future item to compile or pass tests. Order items so each builds on landed work.
  4. Write the entries into docs/backlog.md in dependency order, using the file's entry format, with priorities relative to the existing queue.
  5. Report the slice list to the user for approval. Do not start implementing any of it — the next /iterate session picks up item one.

© IcantFind-a-username, Apache-2.0. 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 .claude/skills/plan-feature of IcantFind-a-username/Sovereign-Founder-OS.

Open the folder on GitHubat commit 5b069d4

Compare with similar skills

Plan Feature 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 Feature compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Plan Feature this skillIcantFind-a-username/Sovereign-Founder-OS105—~422Automated safety check: PassApache-2.0
Action Items List Managerasgeirtj/system_prompts_leaks69k—~4.9kAutomated safety check: PassCC0-1.0
Backlogumputun/cc-thingz484—~3.4kAutomated safety check: NotesMIT
Document To Action ItemsNousResearch/hermes-agent252k—~976Automated safety check: PassMIT
Meeting Action ItemsNousResearch/hermes-agent252k—~950Automated safety check: PassMIT
Large Class Stylesgl-project/sglang37k2 repos~1.9kAutomated safety check: PassApache-2.0

Similar skills

  • Action Items List Manager

    asgeirtj/system_prompts_leaks

    Maintains a private to-do list stored as a JSON file in the assistant's notes: adding tasks, recording what is awaited, tracking blockers and closing finished items.

    69k GitHub stars~4.9k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Backlog

    umputun/cc-thingz

    Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item.

    484 GitHub stars~3.4k tokensUpdated 4 days ago
    DevelopmentAuto-check: notes
  • Document To Action Items

    NousResearch/hermes-agent

    Extract cited obligations, deadlines, tasks from documents. An agent skill from NousResearch/hermes-agent.

    252k GitHub stars~976 tokensUpdated today
    Documents & OfficeAuto-check passed
  • Meeting Action Items

    NousResearch/hermes-agent

    Turn meeting notes into cited decisions, owners, tickets. An agent skill from NousResearch/hermes-agent.

    252k GitHub stars~950 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Large Class Style

    sgl-project/sglang

    Code style for SGLang large classes Scheduler, TokenizerManager, and ModelRunner: frozen-code conventions and init orchestration style.

    37k GitHub starsUsed in 2 repos~1.9k tokens
    AI & LLM EngineeringAuto-check passed
  • Architect large or state-heavy Langfuse frontend features. An agent skill from langfuse/langfuse.

    36k GitHub stars~1.4k tokensUpdated today
    Frontend & DesignAuto-check passed

More from IcantFind-a-username/Sovereign-Founder-OS

  • Iterate

    IcantFind-a-username/Sovereign-Founder-OS

    Run exactly one iteration round from docs/backlog.md — claim one task, write a failing test first, implement, pass all gates, commit, update the books.

    105 GitHub stars~709 tokensUpdated 23 days ago
    Auto-check passed

Questions about Plan Feature

What does Plan Feature do?

Decompose a large feature into single-round backlog items in docs/backlog.md. Plan Feature is an agent skill from IcantFind-a-username/Sovereign-Founder-OS.md.

How do I install Plan Feature in Claude Code?

Run `npx skills add IcantFind-a-username/Sovereign-Founder-OS --skill plan-feature -a claude-code`. Or copy the skill folder (.claude/skills/plan-feature in IcantFind-a-username/Sovereign-Founder-OS) into .claude/skills/plan-feature in your project. Claude Code loads it when a task matches its description.

How do I install Plan Feature in Codex?

Run `npx skills add IcantFind-a-username/Sovereign-Founder-OS --skill plan-feature -a codex`. Or copy the skill folder (.claude/skills/plan-feature in IcantFind-a-username/Sovereign-Founder-OS) into .agents/skills/plan-feature in your project. Codex loads it when a task matches its description.

Can I use Plan Feature 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 IcantFind-a-username/Sovereign-Founder-OS --skill plan-feature -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-feature, .gemini/skills/plan-feature, .github/skills/plan-feature and .opencode/skills/plan-feature in your project.

What does Plan Feature need to run?

SKILL.md names no scripts, command-line tools or credentials: Plan Feature is instructions for the agent only.

Does Plan Feature 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 Feature 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 Feature use?

Plan Feature is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Plan Feature use?

About 422 tokens (SKILL.md is roughly 1.7k 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 Feature?

Skills that share tags, products or a category with Plan Feature: Action Items List Manager (asgeirtj/system_prompts_leaks, 69k stars), Backlog (umputun/cc-thingz, 484 stars), Document To Action Items (NousResearch/hermes-agent, 252k stars) and Meeting Action Items (NousResearch/hermes-agent, 252k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Plan Feature?

IcantFind-a-username (a GitHub user) maintains it in IcantFind-a-username/Sovereign-Founder-OS, which has 105 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 16, 2026.

Source: IcantFind-a-username/Sovereign-Founder-OS on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.