slack-construct-agents

slack-construct-agents is a skill for Claude Code from nanocoai/nanoclaw. It costs 53 tokens per session (269 once invoked), scanned A, original, MIT.

Standing instructions for agents that work with sibling agents in Slack, a team chat platform. They describe how agents share rooms, introduce themselves, and limit bot-to-bot exchanges.

In plain words
What is it for?
Use them when creating sibling agents, setting up team rooms, posting introductions, and managing agent-to-agent communication.
Why use it?
They provide consistent rules for coordinating multiple agents in shared Slack conversations.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

About the project

NanoClaw is an AI assistant that runs agents inside separate Linux containers, isolating their files and execution environments. People use it to connect agents to messaging services and run assistants with memory and scheduled jobs. The catalogue contains skills and instructions for extending or operating NanoClaw.

nanocoai/nanoclaw · 30,703 stars · on GitHub · nanoclaw.dev

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 skills/nanocoai/nanoclaw/slack-construct-agents
Any agent
npx skills add nanocoai/nanoclaw --skill slack-construct-agents
Clone the repo
git clone --depth 1 https://github.com/nanocoai/nanoclaw

Made for: Claude Code.

Wrote 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.

agentmods badge for slack-construct-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/nanocoai/nanoclaw/slack-construct-agents.svg)](https://agentmods.dev/skills/nanocoai/nanoclaw/slack-construct-agents)
Your own site
<a href="https://agentmods.dev/skills/nanocoai/nanoclaw/slack-construct-agents"><img src="https://agentmods.dev/badge/skills/nanocoai/nanoclaw/slack-construct-agents.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 269 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.00269
Opus 5 $0.00026 $0.00134
Sonnet 5 $0.00011 $0.00054
Haiku 4.5 $0.00005 $0.00027

Measured 3d ago against content hash 103f6d49635d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

slack-construct-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 3d 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.

.claude/skills/slack-agent-flow/container/skills/slack-construct-agents/SKILL.md · 23 lines

What it actually says

Slack construct — sibling agents

This skill is a carrier for standing context, not an on-demand workflow. Its payload is instructions.md in this directory: the rules an agent needs when it shares Slack with sibling agents it can create (create_agent) and room with (create_room / add_to_room) — team-room shape, who posts the introduction, and the bot-to-bot self-limit.

The host composes every container skill's instructions.md into each group's CLAUDE.md at spawn (src/project-doc-compose.ts), so if you are reading this from inside a session, those rules are already part of your standing instructions. There is nothing further to load or run here.

The room-and-canvas half of the Slack standing context (mention engagement, canvas discipline, access rules) ships separately with the Slack channel payload as the slack-construct skill; this fragment layers the sibling-agent rules on top and arrives with the slack-agent-flow skill.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 3d ago First seen · 23 lines · 53 tokens per session scan A 103f6d49635d

Subscribe to this mod's changes

slack-construct-agents is a skill published in the GitHub repository nanocoai/nanoclaw (30,703 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 269 once invoked, about $0.0003 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 2026-09-02.