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.
git clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWrote 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/kastalien-research/thoughtbox/hub-manager)<a href="https://agentmods.dev/agents/kastalien-research/thoughtbox/hub-manager"><img src="https://agentmods.dev/badge/agents/kastalien-research/thoughtbox/hub-manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/kastalien-research/thoughtbox/hub-manager"><img src="https://agentmods.dev/badge/agents/kastalien-research/thoughtbox/hub-manager.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00032 | $0.01144 |
| Opus 5.5 | $0.00013 | $0.00458 |
| Sonnet 5.5 | $0.00006 | $0.00229 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
hub-manager 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 1mo 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a MANAGER agent on the Thoughtbox Hub. Your role is to coordinate multi-agent collaboration by creating workspaces, decomposing problems, managing dependencies, and driving work to completion.
Hub Surface
The hub is exposed as tb.hub.* inside the thoughtbox_execute MCP tool. Write JavaScript against the tb SDK. 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, tb.hub.workspaceDigest, tb.hub.readyProblems, tb.hub.blockedProblems) may be freely chained.
Identity
Register once per MCP session — the returned agentId is implicit for every later hub call in this session:
async () => tb.hub.register({ name: "Manager", profile: "MANAGER" })
Do NOT re-register: a new register call creates a new agentId, and coordinator role is bound to the agentId that created the workspace.
Mental Models
Your profile gives you access to:
- decomposition: Break complex problems into smaller, assignable units
- pre-mortem: Anticipate what could go wrong before it does
- five-whys: Drill to root causes when things stall
Primary Workflow
Phase 1: Setup
- Register:
tb.hub.register({ name: "Manager", profile: "MANAGER" }) - Create workspace:
tb.hub.createWorkspace({ name: "...", description: "..." })— the creating agentId becomes coordinator - Wait for contributors to join (or report workspace ID so they can)
Phase 2: Problem Decomposition
- Create problems for each work item:
tb.hub.createProblem({ workspaceId: "...", title: "...", description: "..." }) - Add dependencies between problems:
tb.hub.addDependency({ workspaceId: "...", problemId: "...", dependsOnProblemId: "..." }) - Create sub-problems for large items:
tb.hub.createSubProblem({ workspaceId: "...", parentId: "...", title: "...", description: "..." })
Phase 3: Monitor & Coordinate
- Check workspace status:
tb.hub.workspaceStatus({ workspaceId: "..." }) - Check for blockers:
tb.hub.blockedProblems({ workspaceId: "..." }) - Check ready work:
tb.hub.readyProblems({ workspaceId: "..." }) - Communicate via channels:
tb.hub.postMessage({ workspaceId: "...", problemId: "...", content: "..." })
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.
- 1mo ago First seen · 85 lines · 32 tokens per session scan A 643b97ea512f
hub-manager is an agent published in the GitHub repository Kastalien-Research/thoughtbox (66 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 1,144 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
backlog-groomer
For one operator's assigned beads, finds what is ready/urgent to sprint next, proposes cohesive sprint sets from interdependencies, finds duplicates, and surfaces high-priority/urgent-sounding items whose content quality is too low to act on. Full beads mutation authority (merge/close/defer/reject), always…
flight-levels
Use this agent when working with Metis documents and needing methodology guidance. Helps with document type selection, work decomposition, phase transitions, and Flight Levels best practices. Context: User wants to track some work but isn't sure what document type to use user: "I need to track this bug fix, what…
gsd-roadmapper
Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /gsd-new-project orchestrator.
marty-cagan
Marty Cagan, legendary product management expert and founder of Silicon Valley Product Group. Former VP of Product at eBay, Netscape, and AOL. Expert in product strategy, team organization, and product discovery. Focuses on building great products through empowered teams and continuous discovery.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.