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/kastalien-research/thoughtbox/hub-managergit clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWhat 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 | $0.00032 | $0.01144 |
| Opus 5 | $0.00016 | $0.00572 |
| Sonnet 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 today.
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.
- today First seen · 85 lines · 32 tokens per session scan A 643b97ea512f
hub-manager is an agent published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,144 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
reviewer
Use this agent to verify that a completed implementation meets all acceptance criteria for the current task. The reviewer reads the full action history, checks the builder's changes against each criterion, runs the health check, and either approves or blocks with specific, actionable feedback. Invoke only after the…
gsd-research-synthesizer
Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by /gsd-new-project after 4 researcher agents complete.
gsd-roadmapper
Creates project roadmaps with phase breakdown, requirement mapping, success criteria derivation, and coverage validation. Spawned by /gsd-new-project orchestrator.
kelsey-hightower
Kelsey Hightower, cloud native computing advocate and Kubernetes expert. Former Principal Developer Advocate at Google Cloud. Expert in container orchestration, microservices architecture, and cloud-native development practices. Focuses on making complex cloud technologies accessible and practical for real-world…
Demonstrate
Agent for demonstrating VS Code features.