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/TerryCM/vibegroupWrote 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/terrycm/vibegroup/allow-channel)<a href="https://agentmods.dev/commands/terrycm/vibegroup/allow-channel"><img src="https://agentmods.dev/badge/commands/terrycm/vibegroup/allow-channel.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.00414 |
| Opus 5 | $0.00010 | $0.00207 |
| Sonnet 5 | $0.00004 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade B, and why
allow-channel scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
vibegroup allowlist-json | sudo tee "$(vibegroup allowlist-path)" >/dev/null What it actually says
Make vibegroup runnable as a Claude Code channel on this machine, then add a room. The vibegroup CLI is on your PATH (provided by this plugin). Run these steps and report the result.
1. Allow the channel (one-time per machine, needs sudo)
Channels are admin-gated, so this merges the vibegroup entry into Claude Code's managed settings (channelsEnabled: true + allowedChannelPlugins) without clobbering existing keys:
vibegroup allowlist-json | sudo tee "$(vibegroup allowlist-path)" >/dev/null
The user is prompted for their password. If they decline, tell them they can instead launch with --dangerously-load-development-channels and skip this step.
2. Add a room
Ask the user whether to create a new room or join an existing one, and what short label to use (default: this repo's folder name). The room is bound to the current directory and recorded in the registry (~/.claude/vibegroup/rooms.json), so it activates automatically whenever a session runs here.
- New room:
vibegroup add <label>— mints a room and prints a room + token to share with the crew. - Existing:
vibegroup add <label> --room <room> --token <token>
3. Finish
Tell the user to relaunch the session as a channel (no dev flag needed once step 1 is done):
claude --channels plugin:vibegroup@vibegroup
Then they can ask a peer: "use vibegroup_peers, then ask 's agent what they're working on." Remind them to share the room + token from step 2 with their crew out-of-band.
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.
- 7d ago First seen · 33 lines · 21 tokens per session scan B 13cde2720a88
allow-channel is a command published in the GitHub repository TerryCM/vibegroup (11 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 414 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
announce
Post an announcement to a crew bus channel.
ask
Ask a teammate's agent a question and wait for the answer.
standup
Team standup summary from the bus (messages, tasks, presence).
project-audit
Audit software engineering practices in a repository — check ADR health, GitHub config, CODEOWNERS coherence, project ways alignment, and documentation state. Use when verifying a project is still up to standards.
ways-tests
Score way matching, analyze vocabulary, and validate frontmatter.
gemini
When analyzing large codebases or multiple files that might exceed context limits, use the Gemini CLI with its massive context window. Use gemini -p to leverage Google Gemini's large context capacity.