A command for reporting the status of tracked agents working in Git worktrees. A worktree is a separate working copy of a repository.

Use it to query agents in the current repository or selected worktrees, optionally including all projects, JSON output, or Git information.

It provides one view of agent state and can include Git changes, instead of checking each worktree separately.

status — Command by raine

Install

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.

agentmods

npx agentmods add commands/raine/workmux/status

Clone the repo

git clone --depth 1 https://github.com/raine/workmux

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,111 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00007	$0.01111
Opus 5	$0.00003	$0.00556
Sonnet 5	$0.00001	$0.00222
Haiku 4.5	$0.00001	$0.00111

Measured yesterday against content hash bcbe1bcb8425, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

status 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 yesterday.

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.

docs/src/content/docs/reference/commands/status.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reports tracked agents in the current repository or in explicitly requested worktrees.

workmux status [WORKTREE ...] [--all] [--json] [--git]

Options

--all: Include tracked agents across every repository in the current multiplexer instance. This option conflicts with explicit worktree arguments.
--json: Emit a machine-readable observation object.
--git: Include staged, unstaged, and unmerged commit information for each returned agent.

Worktree arguments support project:handle syntax for cross-project queries.

JSON output

{
  "context": {
    "backend": "tmux",
    "instance": "/private/tmp/tmux-501/default"
  },
  "scope": {
    "repository": "/Users/user/code/project",
    "all": false,
    "targets": []
  },
  "state_files_total": 3,
  "state_files_invalid": 1,
  "state_files_invalid_unattributed": 0,
  "state_files_invalid_matching_context": 0,
  "state_files_matching_context": 2,
  "reconciled_agent_count": 1,
  "agents": [],
  "target_errors": []
}

The counts describe successive stages of the observation.

state_files_total: JSON state files found in the workmux agents directory, including files that cannot be decoded. Atomic-write temporary files are excluded.
state_files_invalid: State files that cannot be decoded across all multiplexer contexts.
state_files_invalid_unattributed: Invalid state files whose filenames do not unambiguously identify a backend and instance.
state_files_invalid_matching_context: Invalid state files attributed to the selected backend and instance. A nonzero value in either this field or state_files_invalid_unattributed makes the command fail.
state_files_matching_context: Readable state files whose backend and instance exactly match context.
reconciled_agent_count: Agents accepted by live multiplexer reconciliation before repository and target filtering.
agents: Reconciled agents inside the declared scope.
target_errors: Requested worktrees that could not be resolved. Each error contains the original target, a stable code, and a human-readable message.

Read the full file on GitHub · 126 lines

Changes

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.

yesterday First seen · 126 lines · 7 tokens per session scan A bcbe1bcb8425

Subscribe to this mod's changes

status is a command published in the GitHub repository raine/workmux (2,284 stars, last pushed 2d ago), licensed MIT. It adds 7 tokens to every session and 1,111 once invoked, about $0.0000 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.

Git and workflow Writing and docs

status

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Options

JSON output

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement