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 agents/longbkit/clisbot/2026-04-28-agent-managed-queue-workflow-and-queues-cligit clone --depth 1 https://github.com/longbkit/clisbotWrote 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/agents/longbkit/clisbot/2026-04-28-agent-managed-queue-workflow-and-queues-cli)<a href="https://agentmods.dev/agents/longbkit/clisbot/2026-04-28-agent-managed-queue-workflow-and-queues-cli"><img src="https://agentmods.dev/badge/agents/longbkit/clisbot/2026-04-28-agent-managed-queue-workflow-and-queues-cli.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 | $0.00000 | $0.04770 |
| Opus 5 | $0.00000 | $0.02385 |
| Sonnet 5 | $0.00000 | $0.00954 |
| Haiku 4.5 | $0.00000 | $0.00477 |
Grade A, and why
2026-04-28-agent-managed-queue-workflow-and-queues-cli 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 — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Queue Workflow And Queues CLI
Summary
Add a first-class queue creation/control surface similar to managed loops, but for one-shot follow-up prompts in the same routed session.
The key product goal is to make one-shot follow-up work durable and inspectable through the same routed-session control model as loops:
human chat command or operator CLI creates queued prompt entries
-> clisbot runs them one by one in the same session
-> each queued prompt rebuilds the current prompt envelope at start time
Unlike loop creation, queue creation does not need a new-thread mode. A queue is session-local follow-up work, not a new conversation anchor.
Status
Done
Priority
P0
Why
/queue already lets a human stack one follow-up message behind the active run.
/loop already has a stronger control-plane shape: persisted state, CLI
creation, scoped list/status/cancel, and agent prompt guidance that tells future
agents to inspect clisbot loops --help.
The missing piece is the same leverage for queues:
- the user should not have to babysit every continuation prompt
- queued work should survive the same operational boundaries as the rest of the session model where practical
- queue control should be inspectable and clearable from chat and CLI
This belongs in agents because queueing is part of the backend-agnostic agent
session operating model. channels should only own command parsing, prompt
envelope rendering, and visible queue notifications. control should own the
operator CLI surface.
Pre-Implementation Baseline
- Chat
/queue <message>and\q <message>enqueue one prompt in memory for the current session. /queue listand/queue clearinspect or clear pending in-memory items for the current session.additionalMessageMode: "queue"can route later human messages into the same queue path while a session is busy.- Queue-start notifications already exist through
surfaceNotifications.queueStart. - Queue entries preserve the sender/surface context and rebuild the prompt envelope when the queued item starts.
- There is no durable one-shot queue store.
- There is no
clisbot queuesCLI comparable toclisbot loops.
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 · 491 lines · 0 tokens per session scan A 3e0224f7c81c
2026-04-28-agent-managed-queue-workflow-and-queues-cli is an agent published in the GitHub repository longbkit/clisbot (114 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,770 tokens. 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 agents, from other repositories
response-agent
Sen ResponseAgent'sın. Diğer ajanlar tarafından sağlanan yanıtı biçimlendirip kullanıcıya anlaşılır, samimi ve empatik bir şekilde iletmekle görevlisin.
planning-agent
Sen bir planlama ajanısın. Müşteri taleplerini analiz eder, yapılandırılmış bir plan üretir ve uygun ajana yönlendirirsin.
complaint-agent
Sen ComplaintAgent'sın. Şikayetleri complaintregistrationtool ile kaydedersin.
human-handoff-agent
Sen HumanHandoffAgent'sın. Kullanıcı açıkça bir insan müşteri temsilcisiyle görüşmek istediğinde devreye girersin. Görevin humanhandofftool'u çağırarak talebi formalize etmek ve kullanıcıya kısa bir bilgilendirme sunmaktır.
order-inquiry-agent
Sen OrderInquiryAgent'sın. Sipariş sorgularını işlersin.
order-placement-agent
Sen OrderPlacementAgent'sın. Siparişleri orderplacementtool ile oluşturursun.