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/2026-04-04-multi-surface-bash-command-addressinggit 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/2026-04-04-multi-surface-bash-command-addressing)<a href="https://agentmods.dev/agents/longbkit/clisbot/2026-04-04-multi-surface-bash-command-addressing"><img src="https://agentmods.dev/badge/agents/longbkit/clisbot/2026-04-04-multi-surface-bash-command-addressing.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 | $0.00000 | $0.00243 |
| Opus 5 | $0.00000 | $0.00121 |
| Sonnet 5 | $0.00000 | $0.00049 |
| Haiku 4.5 | $0.00000 | $0.00024 |
Grade A, and why
2026-04-04-multi-surface-bash-command-addressing 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 4d 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.
What it actually says
Multi-Surface Bash Command Addressing
Goal
Extend agent-scoped bash commands beyond the one default reusable shell surface.
Why This Exists
The current model keeps one reusable bash window per agent session.
That is the right default for now, but later the command surface should support explicit routing such as:
!1:!bash:- one-off shell execution when isolation is preferred
- multiple named shell surfaces inside one agent session
Scope
- define the user-facing command grammar for explicit shell-surface addressing
- define how shell surface names or indices map to tmux runner targets
- define when a command should reuse an existing shell versus create a one-off shell
- keep runner-specific target resolution out of channel code
Out Of Scope
- changing the current default single-shell behavior
- generic operator attach or inspect workflows
Acceptance Criteria
- the command grammar for default, indexed, named, and one-off shell execution is defined
- the default behavior remains one reusable shell surface per agent session
- the mapping between agent commands and runner shell surfaces is unambiguous
- docs and tests explain how shell-surface routing should 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.
- 4d ago First seen · 36 lines · 0 tokens per session scan A 42545fda7ad4
2026-04-04-multi-surface-bash-command-addressing is an agent published in the GitHub repository longbkit/clisbot (114 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 243 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
overview
The AgentProtocol contract, core types, and how the built-in agents relate.
interceptors
Executable skill interceptors turn passive markdown skills into deterministic behavioral guardrails. When the agent proposes a tool call, registered interceptors inspect the action, read the agent's current state (hormonal, GCCRF, channel, recent turns), and may modify, inject context into, require a prerequisite for…
query_optimizer_agent_plan
Query Optimizer Agent 是一个专门用于在 RAG (Retrieval-Augmented Generation) 流程中优化用户查询的智能体。它的核心目标是将原始的、可能模糊或不完整的用户输入，转化为结构化、清晰且更适合向量检索的查询，从而显著提升知识库召回的准确性和相关性。.
Zhin Frontend Optimizer
Use when improving Zhin.js console pages, plugin frontend pages, React UI structure, page information architecture, responsiveness, rendering performance, and visual hierarchy. 适用于前端页面优化、控制台界面改进、React 交互与布局优化。.
draw
You are draw: text-to-image only. No chat, code, file edits, or vision analysis.
overview
Understanding Hivekeep's persistent AI agents.