Every DashClaw governance artifact in one place. Skills and platform-intelligence bundles ship as zips you can drop into ~/.claude/skills/; plugins, hooks, and the MCP server install from a single command against the source repo.
All downloads are generated from this DashClaw instance. The two zips below are regenerated on every npm run livingcode:refresh so the SKILL.md content tracks the live runtime shape.
Skill bundles
Self-contained skill directories Claude Code, Claude Desktop, Codex, and Hermes Agent can load directly. Each zip contains a SKILL.md plus any references and scripts the skill needs.
SKILL.md + references
Teaches an agent how to use DashClaw correctly — risk thresholds, decision handling (allow / warn / block / require_approval), action recording, session lifecycle, plus six new sections for handoffs, secret hygiene, skill safety, open loops, learning, and in-session retrospection.
unzip dashclaw-governance.zip -d ~/.claude/skills/
SKILL.md + references + scripts
Live reference to DashClaw's API surface, governance vocabulary, integration patterns, and troubleshooting playbooks. Regenerated from the codebase on every livingcode refresh — no manual maintenance, no drift from the runtime.
unzip dashclaw-platform-intelligence.zip -d ~/.claude/skills/
Auto-installed when you install any of the agent plugins below. Source mirrors live in public/downloads/ and plugins/dashclaw/skills/ in the repo.
Agent plugins
One DashClaw plugin source, three ecosystems. Each plugin ships the MCP server config, both skills above, and an agent identity used by Mission Control to separate sessions by host (claude-code, codex, hermes).
manifests + skills + MCP configs
Full plugin bundle in one zip — the three plugin manifests (Claude Code / Codex / Hermes), MCP configs, both skills, assets, and PLUGIN_PARITY.md. Drop into your agent's plugin directory or extract for inspection. Manifest version v2.14.0.
unzip dashclaw-governance-plugin.zip # produces a dashclaw/ tree you can drop into ~/.claude/plugins/, ~/.codex/plugins/, etc.
plugins/dashclaw/.claude-plugin/plugin.jsonMCP server + governance skill + platform-intelligence skill, plus a hooks installer for PreToolUse / PostToolUse / Stop guards over Bash, Edit, Write, and MultiEdit.
# From the DashClaw repo root: npm run hooks:install # Then link or copy the plugin source: ln -s "$(pwd)/plugins/dashclaw" ~/.claude/plugins/dashclaw
plugins/dashclaw/.codex-plugin/plugin.jsonSame governance surface DashClaw ships for Claude Code, wired into Codex's ~/.codex/config.toml — MCP server config, PreToolUse / PostToolUse / Stop hooks, governance protocol in AGENTS.md. Idempotent; re-run after every git pull.
node cli/bin/dashclaw.js install codex \ --project /path/to/your/project # Optional: opt in to legacy notify config node cli/bin/dashclaw.js install codex \ --project /path/to/your/project --include-notify
plugins/dashclaw/.hermes-plugin/plugin.yamlEight lifecycle hooks: pre/post tool, pre/post LLM call with per-turn governance context injection, on-session start/end with live ingest finalize, secret redaction in tool output, and subagent_stop ROI tracking. Wires handoffs end-to-end across sessions.
# macOS / Linux bash scripts/install-hermes-plugin.sh # Windows powershell -File scripts/install-hermes-plugin.ps1 # Sanity check hermes dashclaw doctor
Model Context Protocol
23 governance tools across 7 groups plus 4 read-only resources. Ships inside every plugin above as the on-disk path mcp-server/bin/dashclaw-mcp.js. Also reachable as Streamable HTTP at /api/mcp on any DashClaw deployment, no install required.
{
"mcpServers": {
"dashclaw": {
"command": "node",
"args": [
"/path/to/DashClaw/mcp-server/bin/dashclaw-mcp.js",
"--agent-id", "claude-code"
],
"env": {
"DASHCLAW_URL": "https://your-instance.vercel.app",
"DASHCLAW_API_KEY": "oc_live_..."
}
}
}
}mcp_servers=[{
"type": "url",
"url": "https://your-instance.vercel.app/api/mcp",
"headers": {"x-api-key": "oc_live_..."},
"name": "dashclaw"
}]Full tool catalogue and resource list: /docs#mcp-server.
Claude Code hooks
Govern Claude Code tool calls without per-call SDK code. Installs three hooks (PreToolUse, PostToolUse, Stop) plus the tool-classification module into .claude/hooks/, then merges the relevant blocks into .claude/settings.json. Idempotent — re-run after every git pull to upgrade.
hooks + agent_intel + tests
The four hook scripts (pretool, posttool, stop, code-session reporter), the dashclaw_agent_intel/ tool-classification module, default settings.json, and the test suite. Drop the unzipped hooks/ directory into your project's .claude/hooks/.
unzip dashclaw-claude-code-hooks.zip -d <your-project>/.claude/ # Then merge .claude/hooks/settings.json snippets into your .claude/settings.json
npm run hooks:install
node /path/to/DashClaw/scripts/install-hooks.mjs --target=.
The Stop hook captures per-turn LLM token usage from the session transcript and PATCHes it onto the action records the pretool opened during the turn — cost analytics light up without per-agent instrumentation. Required env: DASHCLAW_BASE_URL, DASHCLAW_API_KEY, optional DASHCLAW_HOOK_MODE=enforce.
Programmatic surface
For custom agents and frameworks. The 4-step governance loop and full method catalogue live in /docs. Versions current as of this build.
Canonical 87-method surface across core governance, durable finality, scoring, learning, messaging, handoffs, scanning, threads, sessions, and the execution-studio domains.
npm install dashclaw
Broader Python surface (235 methods) with framework integrations: LangChain callback handler, CrewAI task instrumentation, AutoGen conversation monitoring.
pip install dashclaw
Full integration reference, API method tables, OpenAPI spec, and self-host runbook live in /docs. Source code on GitHub.