heterogeneous-agent SKILL.md skillA

heterogeneous-agent from lobehub/lobehub is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add lobehub/lobehub/heterogeneous-agent@git:20261009.4241061

Pins git:20261009.4241061 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
lobehub/lobehub
Path
.agents/skills/heterogeneous-agent/SKILL.md
Versions recorded
5
Latest version
git:20261009.4241061, committed Oct 9, 2026
First version recorded
Jun 19, 2026
Size
8,423 bytes
Repository stars
85,580
License
a license file GitHub does not identify

Use for external-agent launchers and execution identity, Claude Code/Codex adapters, IPC, event mapping, sessions, persistence and tool-call chains.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Heterogeneous Agent Development

Use this skill when the bug or feature lives in the external CLI agent pipeline, not the normal server-side agent runtime.

## Use This Skill For

- Adding or changing a driver under `apps/desktop/src/main/modules/heterogeneousAgent/drivers/`
- Editing an adapter under `packages/heterogeneous-agents/src/adapters/`
- Changing CLI/Desktop dispatch launchers, including OpenClaw/Hermes, or debugging task-comment authorship
- Debugging `heteroAgentRawLine` transport, `window.__HETERO_AGENT_TRACE`, or `executeHeterogeneousAgent`
- Fixing Claude Code stream-json bugs such as duplicate partial/full chunks, broken `message.id` boundaries, missing `tool_result`, TodoWrite state drift, or subagent thread routing
- Fixing Codex JSONL bugs such as mixed multi-tool messages, broken turn boundaries, or missing tool-result mapping
- Fixing step-boundary, tool persistence, subagent thread, or resume bugs in Claude Code / Codex flows
- Reproducing multi-tool mixing, orphan tool messages, or stuck tool-result loading

## Pipeline Map

1. CLI raw stdout / JSONL
2. Electron main spawns the CLI and broadcasts `heteroAgentRawLine`
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_6cdb3vunzmbbpfpl/f2460b0b428b177aa4001ba837d1a6faa6f5858f6d1a04115a6c3b9a3f679aa5.json

Then /plugin install heterogeneous-agent@markdownregistry-6cdb3vunzmbbpfpl in Claude Code. It installs git:20261009.4241061, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add lobehub/lobehub/heterogeneous-agent@sha256:f2460b0b428b177a

The line at the top of this page pins the label git:20261009.4241061, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_6cdb3vunzmbbpfpl.svg)](https://markdownregistry.com/a/art_6cdb3vunzmbbpfpl)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in lobehub/lobehub/heterogeneous-agent since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of heterogeneous-agent from somewhere else? Ask it: where did my heterogeneous-agent come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 5 versions of this file, between Jun 19, 2026 and Oct 9, 2026, about one every 28 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261009.4241061 latest2026-10-09 4241061 8,423 BA view · diff
git:20260907.25bf2312026-09-07 25bf231 5,882 BA view · diff
git:20260905.ae9199d2026-09-05 ae9199d 5,959 BA view · diff
git:20260710.191f3fe2026-07-10 191f3fe 5,628 BA view · diff
git:20260619.ec40f7e2026-06-19 ec40f7e 5,606 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8423 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

lobehub/lobehub · 85,580 stars · license a license file GitHub does not identify · pushed 2026-11-16 · branch canary

API

GET https://markdownregistry.com/api/v1/artifacts/art_6cdb3vunzmbbpfpl
GET https://markdownregistry.com/api/v1/resolve?ref=lobehub/lobehub/heterogeneous-agent
GET https://markdownregistry.com/api/v1/blob/f2460b0b428b177aa4001ba837d1a6faa6f5858f6d1a04115a6c3b9a3f679aa5

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from lobehub/lobehub

acceptance SKILL.md skill
lobehub/lobehub · .agents/skills/acceptance/SKILL.md · Verify delivery outcomes on the real product, capture inspected evidence, and deliver an acceptance report with the lh…
v0.10.0 · audit A · 85,580 stars
add-model-provider SKILL.md skill
lobehub/lobehub · .agents/skills/add-model-provider/SKILL.md · Add an AI model provider to LobeHub, including runtime integration, model cards, configuration, branding…
git:20260926.70a3d94 · audit A · 85,580 stars
add-setting-env SKILL.md skill
lobehub/lobehub · .agents/skills/add-setting-env/SKILL.md · Add server-side environment variables that control default values for user settings.
git:20260710.191f3fe · audit A · 85,580 stars
agent-runtime-hooks SKILL.md skill
lobehub/lobehub · .agents/skills/agent-runtime-hooks/SKILL.md · Use for agent lifecycle hooks, tool mocks, intervention, sub-agent calls and context compression.
git:20261018.bbeefe6 · audit A · 85,580 stars
agent-signal SKILL.md skill
lobehub/lobehub · .agents/skills/agent-signal/SKILL.md · Use for Agent Signal sources, actions, policies, middleware, workflow handoff and deduplication.
git:20260907.25bf231 · audit A · 85,580 stars
agent-testing-bot SKILL.md skill
lobehub/lobehub · .agents/skills/agent-testing-bot/SKILL.md · Use for real bot-channel acceptance in Discord, Slack, Telegram, WeChat/Weixin, Lark/Feishu, QQ or iMessage on macOS…
git:20260922.3be8e4d · audit A · 85,580 stars
agent-tracing SKILL.md skill
lobehub/lobehub · .agents/skills/agent-tracing/SKILL.md · Use for agent traces by operation ID (拉线上 tracing): failed tools, arguments/results, available tools, execution…
git:20261018.8c89420 · audit A · 85,580 stars
agent-work SKILL.md skill
lobehub/lobehub · .agents/skills/agent-work/SKILL.md · Use for the Agent Work output registry: registration, deduplication, cards, skill providers, CLI scanners and Work…
git:20261104.86a436a · audit A · 85,580 stars
alint-ruleset SKILL.md skill
lobehub/lobehub · .agents/skills/alint-ruleset/SKILL.md · Maintain LobeHub's model-backed alint rule set in packages/alint: author a rule, calibrate its false positives against…
git:20261112.248ebbc · audit A · 85,580 stars
builtin-tool SKILL.md skill
lobehub/lobehub · .agents/skills/builtin-tool/SKILL.md · Use for LobeHub builtin agent tools: manifests, executors, runtimes, inspectors, renders, streaming and intervention.
git:20260926.70a3d94 · audit A · 85,580 stars
chat-sdk SKILL.md skill
lobehub/lobehub · .agents/skills/chat-sdk/SKILL.md · Use for multi-platform bots built with chat SDK: webhooks, mentions, slash commands, cards, modals and streaming.
git:20261115.7fe12d7 · audit A · 85,580 stars
cleanup-git-worktrees SKILL.md skill
lobehub/lobehub · .agents/skills/cleanup-git-worktrees/SKILL.md · Use for stale-worktree, Git registration and branch audits. Managed removal uses the repo lifecycle.
git:20261110.faed524 · audit A · 85,580 stars

Every file in lobehub/lobehub

Browse by kind, by grade A, or by owner.

Kept in .agents/skills, the folder Codex reads. More agent skills for Codex.