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.
npx agentmods add commands/alleneubank/claude-code/brbgit clone --depth 1 https://github.com/alleneubank/claude-codeWhat 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 | $0.00038 | $0.01048 |
| Opus 5 | $0.00019 | $0.00524 |
| Sonnet 5 | $0.00008 | $0.00210 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade C, and why
brb 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 2d 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.
- Sub-agents (Explore, code-reviewer, etc.) — **subagents start in a fresh context and won't see this skill**. When delegating during /brb, prepend the AFK constraint to the delegation prompt, e.g.: `User is AFK. Do not Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- Sub-agents (Explore, code-reviewer, etc.) — **subagents start in a fresh context and won't see this skill**. When delegating during /brb, prepend the AFK constraint to the delegation prompt, e.g.: `User is AFK. Do not How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BRB Mode
The user is stepping away and cannot approve interactive prompts (1Password, SSH agent, Touch ID, sudo, browser dialogs). Keep working autonomously, then leave a /handoff so they can pick up when back.
Treat this as a standing behavioral mode for the rest of the session. Exit the mode when the user sends any new message, unless they explicitly extend it ("still afk, keep going"). A new prompt is the signal they're back.
The rules below apply to every tool invocation in this session — bash commands, MCP tool calls, sub-agent delegations, browser automation. Do not silently exempt a category just because it isn't enumerated.
Extra context from the user
$ARGUMENTS
Rules while AFK
Keep doing
- Edit files, read files, grep, run tests, run builds, run typecheckers
git add,git status,git diff,git log,git branchgit commit— the user does not sign commits, so this won't prompt. Make multiple small commits at natural checkpoints; easier to review later.gh pr view,gh pr diff,gh issue view,gh run view, anythingghread-only (uses HTTPS token, no SSH)gh pr create,gh pr comment,gh issue comment— fine, HTTPS token-based- Background tasks that don't need approval
- Sub-agents (Explore, code-reviewer, etc.) — subagents start in a fresh context and won't see this skill. When delegating during /brb, prepend the AFK constraint to the delegation prompt, e.g.:
User is AFK. Do not run any command that requires 1Password / SSH agent / Touch ID / sudo approval. If you hit one, note it and stop.
Do NOT do
Any command that triggers 1Password / SSH agent / Touch ID / interactive prompt. Skip these proactively — don't attempt and time out.
git push,git push --force— SSH agent approvalgit fetch,git pull— SSH agent approval (remotes are SSH)op read,op item get,op signin, anythingopthat touches a vaultssh-add,ssh <host>for new connections needing keysgh auth login,gh auth refresh,gh auth setup-gitnpm login,npm publish,yarn publish,cargo publishsudo <anything>if the sudo timestamp isn't already cached- Browser dialogs /
alert()/confirm()via Claude-in-Chrome — these freeze the session - Any new MCP
authenticateflow
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.
- 2d ago First seen · 76 lines · 38 tokens per session scan C 6a034d7faa13
brb is a command published in the GitHub repository alleneubank/claude-code (52 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,048 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, unrestricted tool access). 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.