amplifthq/openmeld
The open-source collaboration system for people and AI agents. Share context, coordinate tasks, and work in parallel with your team, cloud agents, Codex, Claude Code, Grok, Grok Bot, OpenCode, Antigravity, and Cursor.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
GUARDRAILS
3/5
Blocks destructive commands · Pre-tool screening hook · No YOLO mode · details
Quality 25/100 Guardrails v2
Copy this rig
# review before running: this installs third-party code
$ npx degit amplifthq/openmeld/.claude ./rig-openmeld # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit amplifthq/openmeld/.agents/skills/debugging-ci-failures .claude/skills/debugging-ci-failures $ npx degit amplifthq/openmeld/.agents/skills/fixing-flaky-tests .claude/skills/fixing-flaky-tests $ npx degit amplifthq/openmeld/.agents/skills/openmeld-changelog .claude/skills/openmeld-changelog $ npx degit amplifthq/openmeld/.agents/skills/postgresql-planning .claude/skills/postgresql-planning $ npx degit amplifthq/openmeld/.agents/skills/react-doctor .claude/skills/react-doctor $ npx degit amplifthq/openmeld/.agents/skills/verify-remote-agent-execution .claude/skills/verify-remote-agent-execution $ npx degit amplifthq/openmeld/.agents/skills/verify-runtime-coordinator-liveness .claude/skills/verify-runtime-coordinator-liveness $ npx degit amplifthq/openmeld/.agents/skills/verify-service-connection .claude/skills/verify-service-connection $ npx degit amplifthq/openmeld/.agents/skills/verify-wake-progress .claude/skills/verify-wake-progress $ npx degit amplifthq/openmeld/.agents/skills/writing-tests .claude/skills/writing-tests $ npx degit amplifthq/openmeld/.claude/skills/docs-lifecycle-scan .claude/skills/docs-lifecycle-scan $ npx degit amplifthq/openmeld/.claude/skills/release-runbook .claude/skills/release-runbook $ npx degit amplifthq/openmeld/.claude/skills/wake-trace .claude/skills/wake-trace $ npx degit amplifthq/openmeld/clients/openmeld-cli/skills/openmeld-cli .claude/skills/openmeld-cli
$ curl -fsSL --create-dirs -o .claude/agents/repo-auditor.md https://raw.githubusercontent.com/amplifthq/openmeld/main/.claude/agents/repo-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/verdict-reviewer.md https://raw.githubusercontent.com/amplifthq/openmeld/main/.claude/agents/verdict-reviewer.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "node \"$CLAUDE_PROJECT_DIR/scripts/agents/claude-bash-guard.mjs\""
}
]
}
]
}
} Skills (14)
debugging-ci-failuresfixing-flaky-testsopenmeld-changelogpostgresql-planningreact-doctorverify-remote-agent-executionverify-runtime-coordinator-livenessverify-service-connectionverify-wake-progresswriting-testsdocs-lifecycle-scanrelease-runbookwake-traceopenmeld-cli
Subagents (2)
| repo-auditor model: sonnet | Read-only evidence collector for fan-out audits — doc health sweeps, dead-code hunts, contract-drift checks, multi-file inventories. Use PROACTIVELY when a question needs facts gathered across many fi |
| verdict-reviewer | Adversarial final reviewer for a completed work order or diff — checks the change against its acceptance criteria and the scoped developing/ owner documents, hunting for ship-blockers. Use when a batc |
Hooks (1)
| event | matcher | runs |
|---|---|---|
| PreToolUse | Bash | node "$CLAUDE_PROJECT_DIR/scripts/agents/claude-bash-guard.mjs" |
Similar rigs
rileyhilliard/claude-essentials
—
Skill Collector 4.4k tok · · Q0
hotovo/aider-desk
Platform for AI-powered software engineers
Minimalist 2.2k tok · · Q0
alexpricedev/Billet
⚒️ Guardrails for your AI coding agents — a full-stack TypeScript starter on Bun
Pragmatist 6.0k tok · · Q38
wondping0/wondev
Write your AI agent knowledge once. Compile it to every agent config format - CLAUDE.md, AGENTS.md, .cursor/rules and more.
Pragmatist 229 tok · · Q0