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 skills add TallyUp-Engineering/chat-room --skill room-cleanupgit clone --depth 1 https://github.com/TallyUp-Engineering/chat-roomWrote 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/skills/tallyup-engineering/chat-room/room-cleanup)<a href="https://agentmods.dev/skills/tallyup-engineering/chat-room/room-cleanup"><img src="https://agentmods.dev/badge/skills/tallyup-engineering/chat-room/room-cleanup/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/skills/tallyup-engineering/chat-room/room-cleanup"><img src="https://agentmods.dev/badge/skills/tallyup-engineering/chat-room/room-cleanup.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 | $0.00113 | $0.00808 |
| Opus 5 | $0.00056 | $0.00404 |
| Sonnet 5 | $0.00023 | $0.00162 |
| Haiku 4.5 | $0.00011 | $0.00081 |
Grade A, and why
room-cleanup 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 8d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Room cleanup
Establish the rules a project runs under, and settle worktrees against them.
This writes nothing to Git and interrupts nobody. Every answer lands in the local option index, and each worker picks it up on its next hook injection.
Observe before asking
Run these first. They are cheap and they decide which questions are worth the operator's attention:
chat-room rules # the catalog, the rung each sits at, and what nobody has decided
chat-room alerts # what the current rules already surface
chat-room projects # every project and its worktrees
Ask only about rules where decided is false. A rule already answered is settled;
re-asking it is the interruption this skill exists to avoid. If every rule is decided, say
so and go straight to disposition.
Ask
One question per undecided rule, in the operator's terms, not the schema's. Offer the rungs as plain choices and say what each would do to their actual room:
stale-worktrees— "How long should a worktree sit with no active agent and no branch commit before I call it idle?" Then: should that advise, warn, or be treated as binding? The threshold is a separate value; ask for a number of days.one-actor-per-worktree— "Two agents are in#release-trainright now. Is one actor per worktree a preference or a rule?"advisereports it,warncarries it into every session,refusestates it as binding.file-overlap— "Two worktrees are editingapp/ui.tsx. Should that just be visible, or should it stop work until someone owns it?"
Use the room's real numbers in the question. "Two agents are in #release-train" earns an
answer; "how should shared worktrees be handled" does not.
Record
chat-room option-set --namespace rules --key one-actor-per-worktree --value refuse
chat-room option-set --namespace notification_policy --key stale-worktree-days --value 14
Then read it back with chat-room rules and show the operator what changed.
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.
- 8d ago First seen · 77 lines · 113 tokens per session scan A 4eb1a27edbb8
room-cleanup is a skill published in the GitHub repository TallyUp-Engineering/chat-room (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 113 tokens to every session and 808 once invoked, about $0.0006 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 skills, from other repositories
ghx
Guidance for safe, reliable GitHub CLI workflows across issues, pull requests, and reviews.
github-pr-fix
Fix a GitHub pull request by addressing feedback or CI failures, pushing changes, and publishing replies.
github-issue-solve
Solve a GitHub issue by collecting context, implementing a fix, and opening or updating a pull request.
open-code-review
Use Alibaba Open Code Review (ocr) to review git diffs, staged changes, branches, or scan a workspace, then summarize findings and optionally fix high-confidence issues.
Release Readiness
Review a change against release gates, rollback safety, validation evidence, and operational risk.
shiploop
Self-improving multi-agent harness: wraps N git sub-repos as one workspace, dispatches named tickets to cheap-floor headless agents that escalate once on failure, promoting lessons into CLAUDE.md. Use when working in or scaffolding a meta-repo workspace (sub-folders each own .git; root has scripts/ + queue/tickets.md…