A command that reads Claude Code's saved subagent records and shows which background agents are running or finished, what they were assigned, and how long they ran.

Use it to check the status of native Claude Code subagents and review their assigned tasks, durations, and rough completion counts.

It gives you one view of work started in other Claude Code windows, including work from sessions that are rate-limited. It also avoids needing special hooks to track the agents.

agents — Command by rhan1

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/rhan1/crewline/agents

Clone the repo

git clone --depth 1 https://github.com/rhan1/crewline

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 452 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	$0.00023	$0.00452
Opus 5	$0.00012	$0.00226
Sonnet 5	$0.00005	$0.00090
Haiku 4.5	$0.00002	$0.00045

Measured 2d ago against content hash 06380f2d1583, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agents 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 2d 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.

commands/agents.md · 38 lines

What it actually says

Show the status of native Claude Code subagents across all recent sessions — which are running, which finished, what each was tasked with, and a rough completion count. This reads the subagent transcripts Claude Code maintains at ~/.claude/projects/<project>/<sessionId>/subagents/agent-<id>.jsonl, so it works even for agents launched from another window and even when a session is rate-limited. No hooks required.

Procedure

Run the scanner, passing through any arguments:

python3 ~/.claude/scripts/agents-status.py $ARGUMENTS

Present its output to the user as-is (it is already a formatted table). Do not re-summarize unless the user asks — the table is the deliverable.
If the user wants a true per-task completion percentage (not just running/done counts), remind them that native subagents are opaque — the reliable way to get done/total % is the manager-mode convention: the orchestrator calls TaskCreate once per work-item before fanning out, and each worker calls TaskUpdate (in_progress → completed). That populates the native bottom task tracker with a live done/total.

Notes

"RUNNING" = a transcript written within the last --run-window secs (default 90). A long-thinking agent that hasn't written a tool call recently may show as idle — the "last write … ago" column makes this transparent.
The bold name (e.g. graceful-skipping-galaxy) is Claude Code's auto-generated friendly handle, not the agent type. The task line conveys purpose.
--lookback controls how far back finished agents are listed (mins; default 720).

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.

2d ago First seen · 38 lines · 23 tokens per session scan A 06380f2d1583

Subscribe to this mod's changes

agents is a command published in the GitHub repository rhan1/crewline (2 stars, last pushed 8d ago), licensed MIT. It adds 23 tokens to every session and 452 once invoked, about $0.0001 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 2026-08-31.

Building agents

agents

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Procedure

Notes

What this file has done since we first saw it

Other commands, from other repositories

execute

vibe-agents

advisor

bootstrap

review-sdk-app

brainstorm