Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/KevinZai/commandernpx agentmods add commands/kevinzai/commander/ccc-openclawWrote 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/kevinzai/commander/ccc-openclaw)<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-openclaw"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-openclaw/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/kevinzai/commander/ccc-openclaw"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-openclaw.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 | $0.00044 | $0.01096 |
| Opus 5.5 | $0.00018 | $0.00438 |
| Sonnet 5.5 | $0.00009 | $0.00219 |
| Haiku 4.5 | $0.00004 | $0.00110 |
Grade A, and why
ccc-openclaw 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 23d 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ccc-openclaw — OpenClaw integration
CC Commander · /ccc-openclaw · integrates Commander with an OpenClaw gateway you already run.
Action: $ARGUMENTS (default status).
OpenClaw is an optional third-party agent runtime; the integration is off by default. It is driven by hooks/openclaw-sync.js and these environment variables:
| Variable | Meaning |
|---|---|
CC_OPENCLAW_ENABLED=1 |
Turns on the SessionStart skill sync |
CC_OPENCLAW_URL |
Gateway base URL (the hook falls back to the gateway's local default) |
CC_OPENCLAW_TIMEOUT |
Request timeout in ms |
Start every subcommand by checking command -v openclaw. If the CLI is missing, report that and stop.
status
-
Run:
openclaw gateway status openclaw status echo "sync enabled: ${CC_OPENCLAW_ENABLED:-0} url: ${CC_OPENCLAW_URL:-default}" -
Report gateway state and version, connected channels, recent sessions, and whether Commander sync is enabled. Report numbers exactly as the commands print them.
sync
-
Confirm the gateway answers:
openclaw health --json -
Run the sync hook once, enabled for this invocation only:
echo '{}' | CC_OPENCLAW_ENABLED=1 node hooks/openclaw-sync.jsThe hook discovers skills under
~/.claude/skills/and posts them to the gateway's Commander webhook. It prints a synced count or "Skill sync failed (gateway may not support registry)". -
Report the line the hook printed. A failure line means the gateway did not accept the registration; do not retry in a loop.
configure
Ask each setting with AskUserQuestion, one at a time:
- Gateway URL:
- 🟢 Use the gateway's configured URL — leaves
CC_OPENCLAW_URLunset. - Custom URL — the user types it; set
CC_OPENCLAW_URL.
- 🟢 Use the gateway's configured URL — leaves
- Sync on session start:
- 🟢 Enable — sets
CC_OPENCLAW_ENABLED=1. - Disable — leaves it unset.
- 🟢 Enable — sets
- Event forwarding (Commander events sent to OpenClaw):
- 🟢 None — nothing is forwarded.
- Session events only — SessionStart and SessionEnd.
- Custom — the user lists events.
- Mode binding (Commander modes mapped to OpenClaw agents):
- 🟢 Skip — no binding.
- Bind now — list agents with
openclaw agents listand let the user pick per mode.
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.
- 23d ago Changed · +8 lines · +22 tokens per session 6f3d7ad4cc6b
- 2mo ago First seen · 113 lines · 22 tokens per session scan A 9decc18541b6
ccc-openclaw is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 1,096 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
ccc-openclaw compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ccc-openclawKevinZai/commander | Command | 6 | yesterday | MIT | A | 44 | Claude Code |
| loopskullninja/coco-workflow | Command | 7 | 22d ago | MIT | A | 28 | Claude Code |
| phaseskullninja/coco-workflow | Command | 7 | 22d ago | MIT | A | 21 | Claude Code |
| statusskullninja/coco-workflow | Command | 7 | 22d ago | MIT | A | 17 | Claude Code |
| justone-publishGodsB1025/justone | Command | 2 | 5mo ago | MIT | A | 22 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |