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 iammrduncan/fxbot --skill room-handoffgit clone --depth 1 https://github.com/iammrduncan/fxbotWrote 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/iammrduncan/fxbot/room-handoff)<a href="https://agentmods.dev/skills/iammrduncan/fxbot/room-handoff"><img src="https://agentmods.dev/badge/skills/iammrduncan/fxbot/room-handoff/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/iammrduncan/fxbot/room-handoff"><img src="https://agentmods.dev/badge/skills/iammrduncan/fxbot/room-handoff.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 | $0.00038 | $0.00381 |
| Opus 5.5 | $0.00015 | $0.00152 |
| Sonnet 5.5 | $0.00008 | $0.00076 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade A, and why
room-handoff 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 today.
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
Handing work to another bot
Tag a bot when part of the work is better done by it, and it's not yours to do.
One bot per step
Give each step to one bot. When two bots work on the same thing at once, they duplicate the work and contradict each other. If the work has steps, hand the next one on when the first comes back.
What the ask holds
The bot you tag hasn't seen your work. It has only the room's messages. Put everything it needs in the ask:
- the task, in a sentence
- what you know that it doesn't: the facts, the files, and what you've tried
- its limits: what not to change, and how far to go
- what you expect back, and in what shape
After you ask
- Don't wait for an answer in the same reply. Say whom you asked, and for what, and stop.
- Don't repeat what the other bot will say.
- When it answers, check its work before you pass it on.
- If its answer is wrong, say so plainly and ask again. If it's still wrong, ask the owner.
When to ask the owner instead
Ask the owner instead of a bot when:
- the step needs the owner's judgement: a choice, a preference, or a risk
- it needs the owner's permission: to send, buy, sign in, or delete
- no bot in the room fits
Ask the owner without tagging a bot, so the round ends and the owner speaks next.
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.
- today First seen · 38 lines · 38 tokens per session scan A 3156dc0475fe
room-handoff is a skill published in the GitHub repository iammrduncan/fxbot (11 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 381 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 2026-11-06.
room-handoff compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| room-handoffiammrduncan/fxbot | Skill | 11 | today | Apache-2.0 | A | 38 | Claude Code |
| compare-harnessesruvnet/metaharness | Skill | 738 | yesterday | MIT | A | 66 | Claude Code |
| oia-manifestruvnet/metaharness | Skill | 738 | yesterday | MIT | A | 79 | Claude Code |
| create-harnessruvnet/metaharness | Skill | 738 | yesterday | MIT | A | 89 | Claude Code |
| diag-harnessruvnet/metaharness | Skill | 738 | yesterday | MIT | A | 85 | Claude Code |
| example-harnessruvnet/metaharness | Skill | 738 | yesterday | MIT | A | 90 | Claude Code |
| repo-genomeruvnet/metaharness | Skill | 738 | yesterday | MIT | A | 73 | Claude Code |