A guide for coordinating multiple AI agents through hcom or hcom-mcp. It describes how one interactive agent can act as the hub while other agents work in the background.

Use it when spawning, routing, supervising, or handing work between agents. It covers agent discovery, launching workers, messaging, and cleaning up managed workers.

Delegating work across agents can become confusing without a clear owner and shared record. The guide keeps coordination, messages, and workflow decisions organized.

using-hcom — Skill by scchearn

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/scchearn/hcom-mcp/using-hcom

Any agent

npx skills add scchearn/hcom-mcp --skill using-hcom

Clone the repo

git clone --depth 1 https://github.com/scchearn/hcom-mcp

Made for: Claude Code, Codex.

Or install hcom-mcp, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,377 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.

Model	Per session	Once invoked
Fable 5	$0.00076	$0.04377
Opus 5	$0.00038	$0.02188
Sonnet 5	$0.00015	$0.00875
Haiku 4.5	$0.00008	$0.00438

Measured 2d ago against content hash db4000052722, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

using-hcom 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 2d 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.

skills/using-hcom/SKILL.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hcom

Overview

Use one visible hub and mostly headless workers. In OpenCode, the default hub is the current session. Do not launch another visible hcom opencode coordinator when the current session is already the hub. Workers may be opencode, codex, claude, or gemini, but they should usually run with --headless while the current session stays interactive.

Core principle: the hub owns the workflow, the thread is the source of truth, and workers only bypass the hub when the topology genuinely needs a peer handoff.

When hcom-mcp is available, use it for control-plane tasks such as discovery, launch, managed-fleet inspection, and cleanup. Keep raw hcom as the communication plane for send, thread seeding, peer handoff, and workflow reporting. Do not shell out to raw hcom for a control-plane task that already has an MCP equivalent.

Default rule: if prompted work might benefit from an agent, invoke this skill before deciding how to launch or coordinate one.

Scope boundary: This skill covers interactive current-session coordination only. If the user asks for a reusable script, workflow automation, hcom run script, or #!/usr/bin/env bash example, stop and redirect them to hcom-agent-messaging — do not write the script here. For installation or troubleshooting, also redirect to hcom-agent-messaging. For a full team topology or saved config, redirect to a planning skill such as do-agents.

When to Use

the user asks to spawn, launch, start, coordinate, or route agents or workers
the user wants practical hcom operating guidance, not a full agent-team design
the current session should remain the visible coordinator
most workers should stay in the background
workers may come from opencode, codex, claude, or gemini
the user asks for a quick pattern, practical commands, or the right defaults
workers may need to hand work directly to each other on the same thread
you need explicit defaults for --thread, --intent, tags, and reporting
hcom-mcp may be present and the agent needs a clear split between MCP bootstrap/control-plane tasks and raw hcom communication tasks

Read the full file on GitHub · 300 lines

Files

What ships with it

3 files 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.

2d ago First seen · 300 lines · 76 tokens per session scan A db4000052722

Subscribe to this mod's changes

using-hcom is a skill published in the GitHub repository scchearn/hcom-mcp (1 stars, last pushed 9d ago), licensed MIT. It adds 76 tokens to every session and 4,377 once invoked, about $0.0004 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 2026-08-31.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens