Agent skill

Agtx Task Sweep

by fynnfluegge in fynnfluegge/agtx

Breaks a conversation's results into feature-level tasks and pushes them to the agtx kanban board, where each task gets its own worktree and agent session.

Apache-2.0Auto-check passedAgent Workflows

Install Agtx Task Sweep

skills CLI
$ npx skills add fynnfluegge/agtx --skill agtx-sweep -a claude-code

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

GitHub CLI
$ gh skill install fynnfluegge/agtx agtx-sweep --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/fynnfluegge/agtx.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/sweep .claude/skills/agtx-sweep && 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
agtx-sweep
GitHub stars
1.7k
Token cost
~1.7k tokens
SKILL.md length
764 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
Apache-2.0

At a glance

Breaks a conversation's results into feature-level tasks and pushes them to the agtx kanban board, where each task gets its own worktree and agent session.

  • Works in 5 steps: Think in PRs — each task = one… → Use dependencies — if task B needs task… → Keep tasks atomic — "Add OAuth + rate… → …
  • Turning a planning conversation into board tasks
  • SKILL.md covers How It Works, Task Lifecycle, Decomposition Strategy and What Makes a Good Task, plus 4 more sections
  • Calls claude

What it does

agtx is a terminal kanban board that manages parallel coding agent sessions, giving each task its own git worktree, branch, tmux window and agent session so every task ends as one reviewable pull request. In this skill the agent acts as orchestrator: it decomposes the work discussed in the conversation into tasks, creates them through MCP tools such as create_tasks_batch, and monitors progress.

Decomposition rules are to think in PRs, keep tasks atomic, wire dependencies with depends_on when one task needs another's code, group tasks only when they must ship together and leave implementation planning to each task's agent. Tasks move from backlog through planning, running and review to done, advanced by you on the board or by an autonomous coordinator. You can step into any task's tmux session to course-correct.

When your agent uses it

  • Turning a planning conversation into board tasks
  • Splitting a large feature into independently mergeable PRs
  • Handing work to parallel coding agents with dependencies
  • Capturing decisions from a chat as backlog items

Example prompts

  • “Sweep this conversation into agtx tasks.”
  • “Break the notifications feature into PR-sized tasks and mark which depend on each other.”
  • “Push the plan we just agreed on to the kanban board as backlog tasks.”

Requirements

  • The agtx kanban tool with its MCP tools available
  • git and tmux, for per-task worktrees and sessions

Workflow steps

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

  1. Think in PRs — each task = one reviewable, independently mergeable PR
  2. Use dependencies — if task B needs task A's code, wire it via depends_on
  3. Keep tasks atomic — "Add OAuth + rate limiting + caching" = 3 tasks, not 1
  4. Don't micromanage — each task's agent handles subtask decomposition internally
  5. Group only if must ship together — otherwise, separate PRs

What it can do on your machine

Read from SKILL.md and the folder at commit 8ae6868. 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:

    • claude

    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

Agtx Task Sweep loads about 1.7k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 764 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~46
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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 fynnfluegge/agtx at commit 8ae6868, republished under its Apache-2.0 licence (© fynnfluegge). 764 words, ~1,731 tokens.

Download SKILL.mdSave it as .claude/skills/agtx-sweep/SKILL.md (or your agent's skills folder).
name
agtx-sweep
description
Sweep this conversation into agtx tasks and push them to the kanban board. Use when the user wants to capture, decompose, or hand off conversation results to the agtx board.
disable-model-invocation
true

agtx — Terminal Kanban for Coding Agents

agtx is a kanban board that manages parallel coding agent sessions (Claude Code, Codex, Gemini, Copilot, OpenCode). Each task gets its own git worktree, branch, tmux window, and agent session — producing one reviewable PR per task.

You are an orchestrator. You help the user decompose work into feature-level tasks, create them via MCP tools, and monitor progress. The user can enter any task's agent session via tmux to course-correct.

How It Works

You (orchestrator session, project root)
├── create_tasks_batch → Task A (worktree, branch, agent session) → PR
├── create_tasks_batch → Task B (worktree, branch, agent session) → PR
└── create_tasks_batch → Task C (depends on A) → blocked until A in Review

Tasks are like subagents, but with superpowers:

  • Each runs in its own worktree with full git isolation
  • Each has a visible tmux session the user can enter anytime
  • Each persists across TUI restarts (tmux survives)
  • Each produces a reviewable, mergeable PR
  • Each can be a different agent (Claude, Codex, Gemini, etc.)

The task agent handles its own internal planning — it can use /plan, spawn subagents, or use any workflow. You don't micromanage implementation details.

Task Lifecycle

Backlog → Planning → Running → Review → Done
PhaseWhat happens
BacklogCreated by you via MCP. Sits on the board until user is ready.
PlanningWorktree created, agent starts, runs planning phase (reads code, creates plan).
RunningAgent implements the feature. May use subagents internally.
ReviewPR created. User reviews. Can resume to address feedback.
DoneMerged. Worktree cleaned up, branch kept.

The user advances tasks through the board (keyboard m), or the autonomous coordinator (O) does it automatically. You create and organize tasks — the board handles execution.

Decomposition Strategy

When asked to plan or break down work:

  1. Think in PRs — each task = one reviewable, independently mergeable PR
  2. Use dependencies — if task B needs task A's code, wire it via depends_on
  3. Keep tasks atomic — "Add OAuth + rate limiting + caching" = 3 tasks, not 1
  4. Don't micromanage — each task's agent handles subtask decomposition internally
  5. Group only if must ship together — otherwise, separate PRs

Ask strategic questions ("should auth come before the DB migration?"), not tactical ones ("should we use a factory pattern?"). The task agent handles tactical decisions.

What Makes a Good Task

Title: short imperative phrase, ≤ 8 words

"Add streaming CSV export endpoint"

Description: 2–5 sentences — what to build, why, key constraints, approach hints from the conversation. Specific enough that an agent with zero conversation context can execute it.

Plugin: agtx (default) for most tasks. gsd for structured spec-driven work. void for plain sessions with no prompting.

MCP Tools

You have access to these tools via the agtx MCP server. Tool parameters are self-documented — call any tool to see its schema.

ToolPurpose
list_tasksList all tasks, optionally filter by status
get_taskGet task details + allowed_actions
create_taskCreate a single backlog task
create_tasks_batchBatch create with index-based dependencies
update_taskModify backlog task (title, description, deps)
delete_taskDelete backlog task
move_taskAdvance task (move_forward, escalate_to_user)
read_pane_contentRead agent's tmux output (last N lines)
send_to_taskSend message to agent's tmux pane
check_conflictsCheck merge conflicts for Review tasks
Batch Creation Example
json
create_tasks_batch({
  "tasks": [
    { "title": "Add users table migration", "description": "Create users table with email, password_hash, created_at" },
    { "title": "Add user API endpoints", "description": "CRUD endpoints for /api/users", "depends_on": [0] },
    { "title": "Add auth middleware", "description": "JWT-based auth middleware", "depends_on": [0] },
    { "title": "Add integration tests", "description": "Test auth flow end-to-end", "depends_on": [1, 2] }
  ]
})

Tasks 1 and 2 run in parallel (both depend on 0). Task 3 waits for both.

Show full SKILL.md (319 more words)Show less

Sweep — Push Conversation to Board

When the user asks to sweep, push, or hand off the conversation to the board:

  1. Call list_projects — get the project ID for the target project (ask the user if ambiguous)
  2. Call list_tasks with project_id — check for duplicates
  3. Extract every actionable work item from the conversation
  4. Stop and present the proposed task list to the user. Do NOT call any MCP write tools yet. Show each task with a checkmark, title, description, and dependencies:
    ✓ [0] Add streaming CSV export endpoint
          Implement GET /export/csv with streaming response
          depends on: none
    
    ✓ [1] Add date range filter to export
          Query params ?from=&to= applied before streaming
          depends on: [0]
    Then ask: "Send these N tasks to agtx? (yes / edit / cancel)"
  5. Handle the response:
    • yes → proceed with all tasks
    • edit → ask which task to modify and what to change, update it in the list, re-show the full list, ask to confirm again
    • cancel → stop, do nothing
  6. Only after final confirmation: use create_tasks_batch (with project_id) for multiple tasks, create_task for one
  7. Report created IDs:
    ✓ a1b2c3  Add streaming CSV export endpoint
    ✓ d4e5f6  Add date range filter to export

Setup Verification

Before creating tasks, verify the MCP connection:

  1. Call list_projects — if it works, you're connected
  2. If it fails, the user needs to install agtx and register the MCP server:
    bash
    claude mcp add agtx -- agtx mcp-serve
    See the agtx README for full installation instructions.

Rules

  • Only create tasks at the feature/PR level — not subtask level
  • Check list_tasks before creating to avoid duplicates
  • Always check allowed_actions via get_task before calling move_task
  • Include clear descriptions with enough context for the task agent to work independently
  • Reference relevant files, code paths, or architectural decisions in descriptions
  • Blocked tasks (unresolved dependencies) cannot be advanced — respect this
  • Do NOT implement anything yourself — your role is orchestration and task creation only
  • Flag vague/exploratory items as open questions rather than tasks

© fynnfluegge, 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/sweep of fynnfluegge/agtx.

Open the folder on GitHubat commit 8ae6868

Compare with similar skills

Agtx Task Sweep 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.

Agtx Task Sweep compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agtx Task Sweep this skillfynnfluegge/agtx1.7k—~1.7kAutomated safety check: PassApache-2.0
Agent Manager Fleet TUIYoanWai/agent-manager582—~1kAutomated safety check: PassApache-2.0
Agent Deckasheshgoplani/agent-deck1.1k—~1.8kAutomated safety check: PassMIT
Clawteamwin4r/ClawTeam-OpenClaw1.5k—~3.1kAutomated safety check: PassMIT
Huashu Agent Swarmalchaincyf/huashu-skills1.7k—~576Automated safety check: PassMIT
Puppetmaster Agent Orchestrationprofessorpalmer/Puppetmaster467—~3.2kAutomated safety check: PassMIT

Similar skills

  • Agent Manager Fleet TUI

    YoanWai/agent-manager

    Runs several coding-agent CLIs as real tmux sessions in one terminal UI, color-coded by whether each is working, waiting, idle or blocked.

    582 GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Agent Deck

    asheshgoplani/agent-deck

    agent-deck, the terminal session manager for AI coding agents.

    1.1k GitHub stars~1.8k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Clawteam

    win4r/ClawTeam-OpenClaw

    Multi-agent swarm orchestration. An agent skill from win4r/ClawTeam-OpenClaw.

    1.5k GitHub stars~3.1k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed
  • Huashu Agent Swarm

    alchaincyf/huashu-skills

    多Agent蜂群并行协作,纯git自组织,适合大型项目开发。当用户提到"蜂群模式"、"多agent"、"并行开发"、"agent swarm"时使用。

    1.7k GitHub stars~576 tokensUpdated 18 days ago
    Agent WorkflowsAuto-check passed
  • Puppetmaster Agent Orchestration

    professorpalmer/Puppetmaster

    Operates and supervises Puppetmaster, a multi-agent orchestrator, through its MCP tools or CLI, picking the right verb for edits, reviews, audits and long-running jobs.

    467 GitHub stars~3.2k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • GSD Quick Batch

    open-gsd/gsd-core

    Runs several small /gsd-quick tasks as one batch, with a single coordinator that plans them, dispatches workers per item and owns all shared writes and worktree merges.

    10k GitHub stars~1.4k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes

More from fynnfluegge/agtx

  • Runs a whole project unattended on an agtx kanban board, decomposing the goal, starting tasks, unblocking workers and merging each result.

    1.7k GitHub stars~3.8k tokensUpdated 9 days ago
    Auto-check passed
  • agtx Execute Phase

    fynnfluegge/agtx

    Carries out an approved plan for an agtx-managed task: implements the changes, runs tests, commits, writes a summary to .agtx/execute.md and then stops.

    1.7k GitHub stars~439 tokensUpdated 9 days ago
    Auto-check passed
  • agtx Task Planning

    fynnfluegge/agtx

    Analyzes the codebase for an agtx task, writes a plan with analysis, steps and risks to .agtx/plan.md, then stops and waits for approval before any change.

    1.7k GitHub stars~439 tokensUpdated 9 days ago
    Auto-check passed
  • Agtx Research

    fynnfluegge/agtx

    Explore the codebase to understand a task before planning. An agent skill from fynnfluegge/agtx.

    1.7k GitHub stars~399 tokensUpdated 9 days ago
    Auto-check passed
  • Agtx Brainstorm Mode

    fynnfluegge/agtx

    Puts the agent in a discussion-only mode for exploring a feature idea, asking questions and probing trade-offs without planning or writing code.

    1.7k GitHub stars~497 tokensUpdated 9 days ago
    Auto-check passed
  • agtx Review Phase

    fynnfluegge/agtx

    Self-reviews completed work in an agtx-managed task for correctness, edge cases and code quality, fixes issues, commits and writes .agtx/review.md with a status.

    1.7k GitHub stars~475 tokensUpdated 9 days ago
    Auto-check passed

Questions about Agtx Task Sweep

What does Agtx Task Sweep do?

Breaks a conversation's results into feature-level tasks and pushes them to the agtx kanban board, where each task gets its own worktree and agent session. agtx is a terminal kanban board that manages parallel coding agent sessions, giving each task its own git worktree, branch, tmux window and agent session so every task ends as one reviewable pull request. In this skill the agent acts as orchestrator: it decomposes the work discussed in the conversation into tasks, creates them through MCP tools such as create_tasks_batch, and monitors progress.

When should I use Agtx Task Sweep?

Agtx Task Sweep fits situations like: turning a planning conversation into board tasks; splitting a large feature into independently mergeable PRs; handing work to parallel coding agents with dependencies; capturing decisions from a chat as backlog items.

How do I install Agtx Task Sweep in Claude Code?

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

How do I install Agtx Task Sweep in Codex?

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

Can I use Agtx Task Sweep 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 fynnfluegge/agtx --skill agtx-sweep -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agtx-sweep, .gemini/skills/agtx-sweep, .github/skills/agtx-sweep and .opencode/skills/agtx-sweep in your project.

What does Agtx Task Sweep need to run?

Going by SKILL.md and its folder, Agtx Task Sweep needs the command-line tools its instructions call (claude). Our summary lists: The agtx kanban tool with its MCP tools available; git and tmux, for per-task worktrees and sessions.

Does Agtx Task Sweep 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 Agtx Task Sweep 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 Agtx Task Sweep use?

Agtx Task Sweep 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 Agtx Task Sweep use?

About 1.7k tokens (SKILL.md is roughly 6.9k 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 Agtx Task Sweep?

Skills that share tags, products or a category with Agtx Task Sweep: Agent Manager Fleet TUI (YoanWai/agent-manager, 582 stars), Agent Deck (asheshgoplani/agent-deck, 1.1k stars), Clawteam (win4r/ClawTeam-OpenClaw, 1.5k stars) and Huashu Agent Swarm (alchaincyf/huashu-skills, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agtx Task Sweep?

fynnfluegge (a GitHub user) maintains it in fynnfluegge/agtx, which has 1,713 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 2, 2026.

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