Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/aaronnat23/disp8chnpx agentmods add skills/aaronnat23/disp8ch/team-coordinationWrote 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/skills/aaronnat23/disp8ch/team-coordination)<a href="https://agentmods.dev/skills/aaronnat23/disp8ch/team-coordination"><img src="https://agentmods.dev/badge/skills/aaronnat23/disp8ch/team-coordination.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.01188 |
| Opus 5 | $0.00000 | $0.00594 |
| Sonnet 5 | $0.00000 | $0.00238 |
| Haiku 4.5 | $0.00000 | $0.00119 |
Grade A, and why
team-coordination 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Coordination Skill (Disp8chTeam-style)
Inspired by the Disp8chTeam multi-agent coordination framework — enables you to organize AI agents into collaborative crews with workspace isolation, P2P messaging, and dependency-aware task management.
Core Capabilities
1. Agent Inbox — Point-to-Point Messaging
Agents can send and receive structured messages to coordinate work without polling or shared state.
Actions:
send— deliver a message to another agentreceive— pop the oldest unread message from your inboxpeek— read without consuminglist— show unread counts for all inboxesbroadcast— send the same message to all known agents
Example: Orchestrator sends task to analyst
agent_inbox(action="send", to="analyst-agent", from="orchestrator",
subject="Research task", content="Please analyze NVIDIA's technical moat. Write output to ./crew-output/cto.md")
Example: Worker signals completion
agent_inbox(action="send", to="orchestrator", from="cto-agent",
subject="Done", content="CTO analysis complete. File: ./crew-output/cto.md")
Example: Orchestrator collects results
agent_inbox(action="receive", recipient="orchestrator")
Messages persist to data/inbox/<agentId>/ and survive server restarts.
2. Workspace Isolation (Git Worktrees)
Each spawned coding agent can run in its own isolated git worktree — a separate branch so parallel agents don't conflict on the same files.
Usage in sessions_spawn:
sessions_spawn(task="Implement OAuth2 module", agent="claude",
worktree=true, cleanup="delete")
- Creates a branch:
disp8chteam/session/<uuid> - Agent runs in
/tmp/disp8ch-wt-<id>/ - On
cleanup=delete, worktree is removed automatically - Output appears in the worktree directory; merge back manually
When to use: When 3+ agents are working on different files in the same repo simultaneously. Prevents git conflicts.
3. Task Dependencies (blocked_by)
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 · 128 lines · 0 tokens per session scan A e340f324adc1
team-coordination is a skill published in the GitHub repository aaronnat23/disp8ch (99 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,188 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 2026-09-03.
Other skills, from other repositories
agentlas-operations
A set of operating procedures for running Agentlas, a system for coordinating agents, reusable workforces, automation graphs, and shared agent resources. It covers candidate selection, graph creation, asset discovery, and memory rules.
todo-tracker
Persistent TODO scratch pad for tracking tasks across sessions. Use when the user asks to add, list, complete, remove, or summarize tasks in a portable workspace Markdown file. Uses stable task IDs and exact matching; heartbeat reporting is opt-in and count-only.
prd
A guide for writing a PRD, or Product Requirements Document, which explains what a product or feature should achieve and who it is for. It covers goals, users, success measures, limits, prior work, and excluded scope.
linear
Manage Linear teams, projects, cycles, issues, comments, workflow state, and documents from a terminal through Linear's public GraphQL API. Use when a user asks to list, search, inspect, create, update, move, or comment on Linear work, or to find Linear documents. Do not use to embed a live agent inside Linear or to…
duduclaw-platform
Use the DuDuClaw MCP tools (persistent memory, shared wiki, task board, channel messaging) when the user asks to remember something across sessions, share knowledge with their team's AI employees, manage tasks, or message someone on LINE/Telegram/Discord/Slack. Requires a running DuDuClaw gateway (npx duduclaw onboard…
incident-learning
Convert operational incident and near-miss evidence into durable product, engineering, test, evaluation, and governance improvements with verified closure. Separate observed facts from causal hypotheses and unresolved uncertainty; map follow-up work across code, tests, skills, operations, product, and governance…