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

Aster Planning

by Zfinix in Zfinix/aster

Create and execute structured plans for multi-step tasks. An agent skill from Zfinix/aster.

Apache-2.0Auto-check passed

Install Aster Planning

skills CLI
$ npx skills add Zfinix/aster --skill aster-planning -a claude-code

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

GitHub CLI
$ gh skill install Zfinix/aster aster-planning --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/Zfinix/aster.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/aster-planning .claude/skills/aster-planning && 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
aster-planning
GitHub stars
112
Token cost
~1k tokens
SKILL.md length
560 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
Apache-2.0

At a glance

Create and execute structured plans for multi-step tasks. An agent skill from Zfinix/aster.

  • Works in 4 steps: Create → Present → Execute → …
  • The user gives a complex task spanning multiple files
  • SKILL.md covers When to plan, The plan file, The planning loop and Handling deviations, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Aster Planning is an agent skill from Zfinix/aster. Create and execute structured plans for multi-step tasks. Use when the user gives a complex task spanning multiple files, asks for a plan or roadmap, says "break this down", or when a task cannot be completed in a single turn. Also use when the task touches several subsystems or the user wants to review the approach before you act.

Its SKILL.md is about 1k 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: An open-source agent harness for software work. The licence is Apache-2.0.

When your agent uses it

  • The user gives a complex task spanning multiple files
  • Asks for a plan
  • Says break this down
  • A task cannot be completed in a single turn

Example prompts

  • “break this down”
  • “/aster-planning”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Create
  2. Present
  3. Execute
  4. Complete

What it can do on your machine

Read from SKILL.md and the folder at commit 3fbb67c. 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 (its code samples are markdown).

    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

Aster Planning loads about 1k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 560 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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 Zfinix/aster at commit 3fbb67c, republished under its Apache-2.0 licence (© Zfinix). 560 words, ~1,036 tokens.

Download SKILL.mdSave it as .claude/skills/aster-planning/SKILL.md (or your agent's skills folder).
name
aster-planning
description
Create and execute structured plans for multi-step tasks. Use when the user gives a complex task spanning multiple files, asks for a plan or roadmap, says "break this down", or when a task cannot be completed in a single turn. Also use when the task touches several subsystems or the user wants to review the approach before you act.

Planning and executing multi-step tasks

When a task is too large for a single turn, break it into a plan, get approval, then execute step by step, marking progress as you go.

When to plan

Plan when any of these are true:

  • The task spans three or more files.
  • The user asks for a plan, roadmap, or breakdown.
  • The user says "how would you approach" or similar.
  • The task has dependencies between steps.
  • You are unsure of the approach and want confirmation before acting.
  • A prior attempt failed and you need to regroup.

Do not plan for single-file, single-step changes. Just do them.

The plan file

Plans live at .aster/plans/<slug>.md. The slug is a short kebab-case description: add-rate-limiting, split-app-component. If .aster/plans/ does not exist, create it with edit_file (the directory is created automatically).

Format
markdown
---
status: draft
created: <ISO 8601>
updated: <ISO 8601>
---

# Plan: <one-line goal>

## 1. <phase name>
- [ ] <concrete, verifiable task>
- [ ] <another task>

## 2. <next phase>
- [ ] <task>
Rules
  • status: draft (not yet approved), active (approved, executing), done (all tasks complete), abandoned (no longer pursuing).
  • Phases are ordered groups of related tasks. Most plans have 2–5 phases.
  • Tasks are concrete and verifiable. "Refactor the auth module" is vague; "Extract validate_token from auth.rs into auth/validation.rs" is concrete. Every task should produce a visible change: a file exists, a test passes, a function is extracted.
  • Checkboxes: [ ] pending, [~] in progress, [x] done, [!] blocked. Only one task in progress at a time.

The planning loop

1. Create

Write the plan file with status: draft. Include enough detail that the user can judge the approach without reading your mind. Keep it at the level of "what changes and in what order," not "which key I'll press."

2. Present

Show the plan to the user in a few lines: the goal, the phases, and one sentence on the approach. Ask whether to proceed. Do not begin executing until they confirm.

3. Execute

For each task, in order:

  1. Mark it [~] (in progress). Update updated in frontmatter.
  2. Do the work. Keep changes scoped to the task.
  3. When the task is done and verifiable, mark it [x] and report what changed in one line.
  4. Move to the next task.

After each phase completes, pause briefly to report: "Phase N done: <summary>. Continuing to phase N+1." This gives the user a natural place to intervene.

Show full SKILL.md (195 more words)Show less
4. Complete

When every task is [x], set status: done, update updated, and report a one-paragraph summary: what was done, what files changed, any follow-ups the user should know about.

Handling deviations

  • A task turns out to be unnecessary. Mark it [x] with a strikethrough and a note: ~~extract the parser~~ — parser is already reusable.
  • A task needs more work than expected. Add sub-tasks under it, indented. Keep the parent as [~] until all sub-tasks are done.
  • The plan is wrong. Stop. Explain what you learned and propose a revised plan (a new phase, reordered tasks, or a different approach). Do not silently deviate.
  • Something is blocked. Mark it [!] with the reason and continue with the next unblocked task. Return to blocked tasks when the blocker clears.

Abandoning a plan

If the user changes direction or the plan no longer makes sense, set status: abandoned, add a one-line reason at the top of the body, and stop. Do not delete the file — it is a record of what was considered.

Cleanup

When a plan is done or abandoned, leave the file in place. The user can delete .aster/plans/ whenever they want; do not do it unprompted.

© Zfinix, 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 skills/aster-planning of Zfinix/aster.

Open the folder on GitHubat commit 3fbb67c

Compare with similar skills

Aster Planning 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.

Aster Planning compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Aster Planning this skillZfinix/aster112—~1kAutomated safety check: PassApache-2.0
Executing Plans Inlineobra/superpowers296k2 repos~5.1kAutomated safety check: PassMIT
Execute Planbrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~2.1kAutomated safety check: PassCustom licence
Inline Plan ExecutionjnMetaCode/superpowers-zh8.3k—~2.5kAutomated safety check: PassMIT
Plancodewhale-hq/Codewhale41k—~213Automated safety check: PassMIT
Execute Plan With Status Trackingtailcallhq/forgecode7.6k1 repos~426Automated safety check: PassApache-2.0

Similar skills

  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    296k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed

  • Execute Plan

    brycewang-stanford/Auto-Empirical-Research-Skills

    A skill your agent uses when a research implementation plan exists in docs/superpapers/plans/ and the user is ready to execute it — collecting data, running analysis, producing outputs, writing the…

    4.5k GitHub stars~2.1k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

  • Inline Plan Execution

    jnMetaCode/superpowers-zh

    Executes a written implementation plan task by task in the current session, with a progress ledger, test-first gates and one fresh-context review at the end.

    8.3k GitHub stars~2.5k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed

  • Plan

    codewhale-hq/Codewhale

    Turn a sufficiently understood task into an ordered implementation plan with dependencies and verification.

    41k GitHub stars~213 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Execute Plan With Status Tracking

    tailcallhq/forgecode

    Works through a plan file task by task, updating each task's status inside the file, then re-reads it at the end to confirm nothing was left undone.

    7.6k GitHub starsUsed in 1 repo~426 tokens
    Agent WorkflowsAuto-check passed

  • Executing Plans

    mohitagw15856/pm-claude-skills

    Execute a written plan with discipline — verify each step before advancing, surface deviations instead of improvising around them, and keep a visible execution log.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from Zfinix/aster

All 19 skills in this repo

  • Artifact Design

    Zfinix/aster

    Designing and building any user-facing surface: a web page, landing page, dashboard, report, HTML document, email, or a component inside an existing app.

    112 GitHub stars~2.8k tokensUpdated 2 days ago
    Auto-check passed

  • Aster Chat Sessions

    Zfinix/aster

    Drive aster chat programmatically and manage sessions and memory: one-shot --print/--json answers, --messages-json for caller-owned history, --continue and --session persistence, --allow-edits…

    112 GitHub stars~591 tokensUpdated 2 days ago
    Auto-check passed

  • Aster CLI

    Zfinix/aster

    Guidance for using the aster CLI to work in a codebase with an AI agent: chat and edit code, run AI code reviews, apply fixes, and manage sessions, memory, and skills.

    112 GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed

  • Aster Config

    Zfinix/aster

    Reference for aster.yaml, covering review models, analyzers, focus areas, include/exclude globs, minconfidence, and the permissions block that gates edits.

    112 GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed

  • Aster Fix Workflow

    Zfinix/aster

    Pipe aster review findings into aster fix to generate and apply patches safely, using review --json, fix --findings-json, dry-run inspection, --apply, and permission gating.

    112 GitHub stars~534 tokensUpdated 2 days ago
    Auto-check passed

  • Aster Review CI

    Zfinix/aster

    Run aster code reviews non-interactively in CI, GitHub Actions, or from another agent.

    112 GitHub stars~640 tokensUpdated 2 days ago
    Auto-check passed

Questions about Aster Planning

What does Aster Planning do?

Create and execute structured plans for multi-step tasks. An agent skill from Zfinix/aster. Aster Planning is an agent skill from Zfinix/aster. Create and execute structured plans for multi-step tasks.

When should I use Aster Planning?

Aster Planning fits situations like: the user gives a complex task spanning multiple files; asks for a plan; says break this down; A task cannot be completed in a single turn.

How do I install Aster Planning in Claude Code?

Run `npx skills add Zfinix/aster --skill aster-planning -a claude-code`. Or copy the skill folder (skills/aster-planning in Zfinix/aster) into .claude/skills/aster-planning in your project. Claude Code loads it when a task matches its description.

How do I install Aster Planning in Codex?

Run `npx skills add Zfinix/aster --skill aster-planning -a codex`. Or copy the skill folder (skills/aster-planning in Zfinix/aster) into .agents/skills/aster-planning in your project. Codex loads it when a task matches its description.

Can I use Aster Planning 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 Zfinix/aster --skill aster-planning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/aster-planning, .gemini/skills/aster-planning, .github/skills/aster-planning and .opencode/skills/aster-planning in your project.

What does Aster Planning need to run?

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

Does Aster Planning 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 Aster Planning 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 Aster Planning use?

Aster Planning 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 Aster Planning use?

About 1k tokens (SKILL.md is roughly 4.1k 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 Aster Planning?

Skills that share tags, products or a category with Aster Planning: Executing Plans Inline (obra/superpowers, 296k stars), Execute Plan (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars), Inline Plan Execution (jnMetaCode/superpowers-zh, 8.3k stars) and Plan (codewhale-hq/Codewhale, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Aster Planning?

Zfinix (a GitHub user) maintains it in Zfinix/aster, which has 112 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 6, 2026.

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