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 cyrus-cai/claude-cobrain/plugin install claude-cobrainWrote 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/cyrus-cai/claude-cobrain/cobrain)<a href="https://agentmods.dev/commands/cyrus-cai/claude-cobrain/cobrain"><img src="https://agentmods.dev/badge/commands/cyrus-cai/claude-cobrain/cobrain/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/cyrus-cai/claude-cobrain/cobrain"><img src="https://agentmods.dev/badge/commands/cyrus-cai/claude-cobrain/cobrain.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 | $0.00022 | $0.00420 |
| Opus 5 | $0.00011 | $0.00210 |
| Sonnet 5 | $0.00004 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
cobrain 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 9d 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.
What it actually says
cobrain
Route /claude-cobrain:cobrain $ARGUMENTS to the appropriate skill.
Routing
| Argument | Skill | Description |
|---|---|---|
| (empty) | — | If not installed → install; otherwise → status |
install |
install | Full installation flow |
status |
status | Show daemon status |
start |
startstop | Start daemon |
stop |
startstop | Stop daemon |
restart |
restart | Restart with foreground permission check |
logs |
logs | View daemon logs |
today |
today | Review and summarize today's memory |
hourly |
hourly | View hourly activity reports |
uninstall |
uninstall | Remove daemon runtime files |
Dispatch Rules
- Normalize
$ARGUMENTSto a single lower-case action token. - If no action is provided:
- Check whether daemon script exists:
test -f ${OUTPUT_DIR:-$HOME/.claude/cobrain}/cobrain.py. - If script does not exist, invoke the
installskill. - If script exists, invoke the
statusskill.
- Check whether daemon script exists:
- For
install, invoke theinstallskill and explicitly pass${CLAUDE_PLUGIN_ROOT}as absolute path context. - For
startorstop, invoke thestartstopskill and pass the action. - For all other known actions, invoke the matching skill directly.
- For unknown actions, show supported actions:
install,status,start,stop,restart,logs,today,hourly,uninstall.
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.
- 9d ago First seen · 36 lines · 22 tokens per session scan A 573389a83c3f
cobrain is a command published in the GitHub repository cyrus-cai/claude-cobrain (5 stars, last pushed 6mo ago), licensed MIT. It adds 22 tokens to every session and 420 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other commands, from other repositories
valuation-methods
Valuation methods analysis — multiples, DCF inputs, PEG integration, valuation assumption extraction.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
design-form
Design a form with the fewest fields that works, clear labels, and errors that help.
enum-udp
UDP scan + service follow-up — top ports first, full sweep only when justified.
claude-recall
Update project context using the local LLM (Qwen2.5 0.5B).
review
Submit a story for verification (In Progress → In Review, no PR yet).