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 abel30567/fermi-mcp --skill grok-bot-handoffgit clone --depth 1 https://github.com/abel30567/fermi-mcpWrote 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/abel30567/fermi-mcp/grok-bot-handoff)<a href="https://agentmods.dev/skills/abel30567/fermi-mcp/grok-bot-handoff"><img src="https://agentmods.dev/badge/skills/abel30567/fermi-mcp/grok-bot-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/abel30567/fermi-mcp/grok-bot-handoff"><img src="https://agentmods.dev/badge/skills/abel30567/fermi-mcp/grok-bot-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 | $0.00040 | $0.00519 |
| Opus 5.5 | $0.00016 | $0.00208 |
| Sonnet 5.5 | $0.00008 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
grok-bot-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 3d 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.
What it actually says
Grok Bot handoff (sender side)
Grok Bot reads the grok-bot queue directly and runs each task on its own
inference, splitting it across its own sub-agents. Hand it the WHOLE ask.
1. Enqueue one task per ask
task_enqueue({
channel: "cloud", queue: "grok-bot", chat_id: "grok-bot",
sender: "cc:<host>/<session>",
payload: JSON.stringify({ v: 1, ask, context, repo, expected_output, deadline_min: 30 })
})
- Queue is
grok-bot, nevermain(the Mac drain workers claimmain). - Do NOT pre-split a job into many grok-bot tasks. Grok Bot decomposes and
parallelizes better than a sender can; give it full context and one clear
expected_output. Separate unrelated asks may be separate tasks. repois optional (owner/name). Raisedeadline_minfor big jobs.
2. Wait
Loop task_wait({ id, timeout_seconds: 120 }) until done/failed or
deadline_min passes. timeout only means "not yet": call again.
3. Read the result
If the result starts with fs:, the full output is a file: fs_read({ path })
with the rest of the string (e.g. fs:handoff/<id>.md → handoff/<id>.md).
4. On deadline
Report "Grok Bot hasn't finished " to your user and stop. Do not
re-enqueue; task_list({ queue: "grok-bot" }) shows whether it was claimed.
Rules
- No secrets in payloads; reference a Fermi secret by name if needed.
- Grok Bot drafts anything outward-facing (email, posts) for the owner's approval instead of sending it.
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.
- 3d ago First seen · 42 lines · 40 tokens per session scan A 961e59d83c80
grok-bot-handoff is a skill published in the GitHub repository abel30567/fermi-mcp (1 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 519 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 2026-10-13.
Other skills, from other repositories
tesla-command
Tesla write commands: lock/unlock, climate, charge, honk/flash, trunk, windows, sentry, media, navigation, software update, schedules, valet, speed limit, guest mode, remote start, PIN clears, erase, and wake. Use when the user asks to change the car. Call only after explicit user confirmation. Extra confirm for…
tesla-status
Read Tesla vehicle list, cheap online/asleep state, battery, charge state, location, alerts, service data, release notes, and energy site status. Use when the user asks how the car is, range, SOC, plugged in, charging, where the car is, or Powerwall/solar live status. Do not wake the vehicle unless the user asked.…
tesla
Tesla Fleet MCP bootstrap. Use when the user mentions Tesla, the car, Model 3/Y/S/X, Cybertruck, VIN, charging, cabin climate, lock/unlock, sentry, media, navigation, software update, valet, guest mode, energy/Powerwall, or vehicle location. Route status reads to tesla-status and writes to tesla-command. Trigger even…
nexfade
Create one-time NexFade encrypted links for attached files or sensitive notes, check link status, and revoke links.
bug-fixer
A bug reproduces, the expected behaviour is clear, and the fix stands apart from the current work.
test-pruner
Tests in a named area duplicate stronger tests, re-assert the implementation, or keep test-only seams alive, and need pruning.