hub-collab

hub-collab is a skill for Claude Code from Kastalien-Research/thoughtbox. It costs 46 tokens per session (2,081 once invoked), scanned A, original, MIT.

A demonstration workflow for coordinating three AI agents—a manager, an architect, and a debugger—through Thoughtbox Hub, a shared workspace for agent communication and task state.

In plain words
What is it for?
Use it to run a multi-agent collaboration demo, provided the Thoughtbox server and project configuration are available.
Why use it?
It shows how multiple agents can share problems, proposals, channels, and workspace status while working on one task.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions Codex.

Good fit Use it to run a multi-agent collaboration demo, provided the Thoughtbox server and project configuration are available.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kastalien-research/thoughtbox/hub-collab
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.

Any agent
npx skills add Kastalien-Research/thoughtbox --skill hub-collab
Clone the repo
git clone --depth 1 https://github.com/Kastalien-Research/thoughtbox

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 hub-collab

README.md
[![agentmods](https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/hub-collab.svg)](https://agentmods.dev/skills/kastalien-research/thoughtbox/hub-collab)
Your own site
<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/hub-collab"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/hub-collab.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,081 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00046 $0.02081
Opus 5 $0.00023 $0.01040
Sonnet 5 $0.00009 $0.00416
Haiku 4.5 $0.00005 $0.00208

Measured 8d ago against content hash 173f93889c7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

hub-collab scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:1731/mcp | head -c 100
.agents/skills/hub-collab/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hub Collaboration Demo

Orchestrate a multi-agent demo showing 3 agents (MANAGER, ARCHITECT, DEBUGGER) collaborating on the Thoughtbox Hub.

Hub Surface

The hub is exposed as tb.hub.* inside the thoughtbox_execute MCP tool (the only registered Thoughtbox MCP tools are thoughtbox_search, thoughtbox_execute, and thoughtbox_peer_notebook). Submit at most ONE state-mutating hub call per thoughtbox_execute invocation; read-only calls (tb.hub.whoami, tb.hub.listWorkspaces, tb.hub.readChannel, tb.hub.workspaceStatus) may be freely chained.

Prerequisites

Before running, verify:

  1. Docker is running and the Thoughtbox server is accessible at http://localhost:1731/mcp
  2. The thoughtbox MCP server is configured in .mcp.json

Check with:

curl -s http://localhost:1731/mcp | head -c 100

MCP Session Behavior (Empirically Verified 2026-02-07; tb.hub semantics per PR #374)

Sub-agents spawned via the Task tool share the parent's MCP HTTP connection but each tb.hub.register call creates a separate agentId. The hub keeps a per-MCP-session identity registry: the first registration becomes the session's implicit default agentId, and an explicit agentId override is only accepted if that agentId was registered in the SAME session. Key findings:

  1. Session isolation works: Each sub-agent gets a unique agentId on the hub
  2. Cross-workspace visibility works: Sub-agents see workspaces created by other agents
  3. Cross-agent review works: A Debugger sub-agent can review an Architect's proposal
  4. Coordinator role caveat: Re-registering creates a new identity, losing coordinator role. The orchestrator must create workspace + problems BEFORE spawning sub-agents, and not re-register afterward if merge is needed — tb.hub.mergeProposal must run from the coordinator's own session.
  5. Explicit agentId required in sub-agents: Because all sub-agents share the parent's MCP session, the FIRST registration (normally the Orchestrator's) is the implicit default identity. Any tb.hub.* mutation that omits agentId is attributed to that default — silently breaking cross-agent attribution and review. Each sub-agent must capture the agentId returned by its own tb.hub.register/tb.hub.quickJoin and pass it as an explicit top-level agentId field in every subsequent hub call (e.g. tb.hub.claimProblem({ agentId, workspaceId, problemId })). Explicit agentId is accepted only for identities registered in the same session.
  6. Sequential spawning recommended: Run sub-agents sequentially (not in parallel). Each agent should complete registration → join → claim → propose before the next starts, which keeps the demo's ordering deterministic (e.g. the Architect's proposal exists before the Debugger reviews it).

Read the full file on GitHub · 129 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.

  1. 8d ago First seen · 129 lines · 46 tokens per session scan A 173f93889c7e

Subscribe to this mod's changes

hub-collab is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 2,081 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories