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 agentmods add commands/fynnfluegge/agtx/add-plugingit 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/commands/fynnfluegge/agtx/add-plugin)<a href="https://agentmods.dev/commands/fynnfluegge/agtx/add-plugin"><img src="https://agentmods.dev/badge/commands/fynnfluegge/agtx/add-plugin.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00040 | $0.00946 |
| Opus 5 | $0.00020 | $0.00473 |
| Sonnet 5 | $0.00008 | $0.00189 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
add-plugin 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 6d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add agtx Plugin
Integrate a spec-driven development framework or skill library as a bundled agtx plugin.
Input
Optionally, a GitHub repository URL is provided as the argument (e.g. https://github.com/org/repo).
If no URL is given, ask the user which framework they want to integrate and gather the necessary details interactively.
Steps
1. Gather information about the framework
If a GitHub URL was provided, use the GitHub CLI to inspect the repo:
gh repo view <owner>/<repo> --json name,description
gh api repos/<owner>/<repo>/git/trees/HEAD?recursive=1 | jq '[.tree[].path]'
gh api repos/<owner>/<repo>/contents/README.md | jq -r '.content' | base64 -d
If no URL was provided, ask the user:
- Framework name and slash command namespace (e.g.
gsd,opsx) - Which phases it covers and what commands it uses
- How it is installed (npm, git clone, shell script)
- Which agents it supports
In either case, look for:
- The slash command namespace and per-phase commands
- Installation method: npm package, clone-and-run library, or shell installer
- Agent compatibility: Claude-only (hooks/skills), multi-agent (npm flags), or prompt-only (all agents)
- Artifact files that signal phase completion
- Directories/files that need to be propagated to each worktree (
copy_dirs,copy_files,copy_back) - A one-time project setup step (
preresearch+ artifact) - Interactive CLI prompts at startup that need
auto_dismissorprompt_triggers - Multi-milestone iteration (
cyclic = true)
2. Study existing bundled plugins as reference
Read plugins/*/plugin.toml and pick the closest analog to use as a starting point.
Key patterns:
init_scriptwith--{agent}placeholder when the tool has per-agent flagscopy_backso artifacts produced in one worktree are visible to others{task}in a command or prompt → phase is accessible directly from Backlog; omit{task}→ phase requires a prior artifactcyclic = trueonly when the framework supports multi-milestone iteration (Review → Planning loop)
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.
- 6d ago First seen · 103 lines · 40 tokens per session scan A 274903b50e13
add-plugin is a command published in the GitHub repository fynnfluegge/agtx (1,472 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 946 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 commands, from other repositories
release
Ship a stable cmux release built by CI: bump version, update changelog, open a PR, merge, tag, then GitHub Actions builds, signs, and publishes.
release-local
Release straight from main with no PR, built and published locally.
sync-branch
Get the current branch ready: update all submodules to their latest remote main, merge from main, and rebase.
cleanup-builds
Reclaim disk taken by tagged dev artifacts from ./scripts/reload.sh --tag . Each tagged build is multi-GB of DerivedData plus per-tag sockets and logs.
release-nightly
Release through the PR flow, then build and publish locally instead of waiting on the CI release workflow.
pull
Pull latest main and update all submodules to their latest remote main. No commits, no pushes.