Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add jianzhichun/emerge/plugin install emergeWrote 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/commands/jianzhichun/emerge/cockpit)<a href="https://agentmods.dev/commands/jianzhichun/emerge/cockpit"><img src="https://agentmods.dev/badge/commands/jianzhichun/emerge/cockpit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/jianzhichun/emerge/cockpit"><img src="https://agentmods.dev/badge/commands/jianzhichun/emerge/cockpit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00865 |
| Opus 5 | $0.00000 | $0.00432 |
| Sonnet 5 | $0.00000 | $0.00173 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade C, and why
cockpit scanned grade C with 2 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 10d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s http://localhost:8789/api/assets | python3 -m json.tool Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:8789/api/assets | python3 -m json.tool How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/emerge:cockpit — Open Cockpit Dashboard
The cockpit server is started automatically by the daemon. This command opens it.
Always invoke the admin CLI via the Emerge plugin root (not the user's open project). Claude Code expands ${CLAUDE_PLUGIN_ROOT} to that path when this command runs.
Steps
-
Get cockpit URL: When the Emerge HTTP daemon is running (default from
SessionStart), Cockpit is on the same port as MCP — typicallyhttp://localhost:8789/(same host/port asplugin.jsonurlfor/mcp, but open the root/in a browser). If the daemon is not running (or you need a standalone cockpit without MCP):python3 "${CLAUDE_PLUGIN_ROOT}/scripts/repl_admin.py" serve --open --port 0Read output to extract
Cockpit running at http://localhost:PORT. -
Print URL to user: Report: "Cockpit running at " (prefer daemon URL
http://localhost:8789/when the daemon is up). -
Discover connector assets and inject controls: Cockpit's "Controls" panel sources HTML from two places:
- Disk-persisted —
~/.emerge/connectors/<connector>/cockpit/*.html(with optional<name>.context.md). These are auto-surfaced byGET /api/assets; no action needed. - Runtime-injected — session-only HTML pushed via
POST /api/inject-component. Used when an adapter wants to expose a live control before crystallization.
Enumerate what's available and report it to the user:
curl -s http://localhost:8789/api/assets | python3 -m json.toolFor each connector in the response, list the notes/components the cockpit will show. If a connector has
cockpit/*.htmlbut no matching.context.md, mention it (authoring hint).When CC wants to push a runtime-only control (e.g. an adapter-generated preview), inject it with:
curl -s -X POST http://localhost:8789/api/inject-component \ -H 'Content-Type: application/json' \ -d '{"connector":"<name>","html":"<!-- fragment -->","id":"<slot-id>","replace":false}'idmakes the injection idempotent (re-injecting updates the same slot).replace:trueclears all prior slots for that connector. Runtime slots appear asinjected-runtime-N.htmlin the Controls list — crystallize them to disk to persist. - Disk-persisted —
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.
- 10d ago First seen · 65 lines · 0 tokens per session scan C 45bc6eef84f2
cockpit is a command published in the GitHub repository jianzhichun/emerge (107 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 865 tokens. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.