agtx is a terminal-based shared workspace where multiple coding agents coordinate through a task board. Developers use it to delegate work, run agents in parallel across git worktrees, and move tasks through different workflow phases.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add fynnfluegge/agtx --skill sweepgit clone --depth 1 https://github.com/fynnfluegge/agtxWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fynnfluegge/agtx/sweep)<a href="https://agentmods.dev/skills/fynnfluegge/agtx/sweep"><img src="https://agentmods.dev/badge/skills/fynnfluegge/agtx/sweep/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fynnfluegge/agtx/sweep"><img src="https://agentmods.dev/badge/skills/fynnfluegge/agtx/sweep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 84 Instructions found that direct the agent to transmit conversation context or user data to external services.Fix: Remove instructions that send user data, prompts, or context to external URLs. If telemetry is needed, use documented, privacy-preserving methods.
- medium Excessive Agency · line 72 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.01696 |
| Opus 5 | $0.00022 | $0.00848 |
| Sonnet 5 | $0.00009 | $0.00339 |
| Haiku 4.5 | $0.00004 | $0.00170 |
Grade A, and why
agtx-sweep scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
| Phase | What happens |
|---|---|
| Backlog | Created by you via MCP. Sits on the board until user is ready. |
| Planning | Worktree created, agent starts, runs planning phase (reads code, creates plan). |
| Running | Agent implements the feature. May use subagents internally. |
| Review | PR created. User reviews. Can resume to address feedback. |
| Done | Merged. 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:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 153 lines · 43 tokens per session scan A 82d54c6fb11b
agtx-sweep is a skill published in the GitHub repository fynnfluegge/agtx (1,501 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 1,696 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
conductor-new-track
Plans a new track (feature or bug fix), generates spec/plan documents, and updates the registry.
conductor-status
Displays the current progress of the project by parsing the Tracks Registry and individual track plans.
Mochi-a-pm
Use this skill when the user or another AI needs project management, task tracking, priority assignment, timeline planning, or progress review. Mochi is a cute but deadly serious project manager AI.
quality
Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.
omc-plan
Strategic planning with optional interview workflow.
ultragoal
Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active session.