Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/bvdr/claude-pluginsWrote 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/bvdr/claude-plugins/control)<a href="https://agentmods.dev/commands/bvdr/claude-plugins/control"><img src="https://agentmods.dev/badge/commands/bvdr/claude-plugins/control/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/bvdr/claude-plugins/control"><img src="https://agentmods.dev/badge/commands/bvdr/claude-plugins/control.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 | $0.00046 | $0.03286 |
| Opus 5.5 | $0.00018 | $0.01314 |
| Sonnet 5.5 | $0.00009 | $0.00657 |
| Haiku 4.5 | $0.00005 | $0.00329 |
Grade A, and why
control scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/control
Stand up the cmux control-center pattern: this conversation becomes the orchestrator that watches every claude/codex/opencode session running inside cmux and surfaces only the events that need a human (questions, plan-mode, idle, done). Routine work is handled silently in each sub-session.
When to use
User invokes /control to start (or re-start) supervising sub-agents. The command:
- Discovers what's running across cmux right now
- Asks the user which sessions to focus on today
- Asks what they're working on (one sentence — used as a "north star" while routing decisions back)
- Spawns / restarts the background watcher
- Switches the rest of the conversation into orchestrator mode
Pre-flight
- Locate cmux — try
command -v cmux; fall back to/Applications/cmux.app/Contents/Resources/bin/cmux. Cache asCMUX=. If neither exists, tell the user cmux isn't installed and stop. - Verify daemon —
"$CMUX" ping. If it returnsBroken pipe (errno 32), see thecmuxcommand's pre-flight notes (socketControlMode). Stop until resolved. - Ensure config dir —
mkdir -p ~/.config/cmux-control. - Ensure watcher script — if
~/.config/cmux-control/filter.pyis missing, write it from the source in this repo (plugins/bvdr/scripts/cmux-control-filter.py), or fail loudly and tell the user where to install it from.
Step 1 — Discover sessions
Read three sources and join them:
| Source | What you get |
|---|---|
cmux list-workspaces |
Workspace refs and names |
~/Library/Application Support/cmux/session-com.cmuxterm.app.json |
Per-workspace cwd, customColor, panel sessionIds (panels[].terminal.agent.sessionId) |
~/.cmuxterm/claude-hook-sessions.json |
Per-session lastSubtitle (Waiting/Working), lastBody, cwd |
~/.cmuxterm/workstream.jsonl |
Per-session activity history; tail to derive last user prompt + recent tool descriptions |
For each workspace with a claude/codex/opencode panel, build a one-line summary:
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.
- 1mo ago First seen · 245 lines · 46 tokens per session scan A f3572dd13e8e
control is a command published in the GitHub repository bvdr/claude-plugins (4 stars, last pushed 4mo ago), licensed MIT. It adds 46 tokens to every session and 3,286 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 2026-08-31.
Other commands, from other repositories
review-resume
Comprehensive PM resume review against 10 best practices — structure, impact metrics, keywords, and actionable feedback.
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
reminders
Manage macOS reminders - list, search, create, complete, update, delete with filtering and batch operations.
contacts
Manage macOS contacts - list, search, get details, create, update, delete.
claude-tracker
List recent Claude Code sessions with live status.
quote
Capture a notable phrase or excerpt from the current session with optional tags. Stored in tracker.db and searchable via /quote-search.