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 xvirobotics/metabot --skill metabot-teamgit clone --depth 1 https://github.com/xvirobotics/metabotWrote 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/xvirobotics/metabot/metabot-team)<a href="https://agentmods.dev/skills/xvirobotics/metabot/metabot-team"><img src="https://agentmods.dev/badge/skills/xvirobotics/metabot/metabot-team/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/xvirobotics/metabot/metabot-team"><img src="https://agentmods.dev/badge/skills/xvirobotics/metabot/metabot-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.00643 |
| Opus 5.5 | $0.00013 | $0.00257 |
| Sonnet 5.5 | $0.00007 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
metabot-team 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 1mo 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.
MetaBot Agent Teams CLI
This Skill documents the metabot teams command surface and its durable-state
semantics. It does not define Agent execution policy.
Core Model
Team = Agents + Messages + Tasks + Runs.
- Agents retain a stable Team identity across engine Sessions.
- Messages are the normal conversational handoff surface.
- Tasks record durable assignment, dependencies, status, and result.
- Runs record individual executions, output, failure, retry, cancellation, and card state.
- Multiple dispatches to the same Agent create independent Tasks and Runs.
Inspect A Team
metabot teams status <team> --summary
metabot teams agents list <team>
metabot teams tasks list <team> --summary
metabot teams runs list <team> --summary
metabot teams next <team> <member> --summary
--summary or --plain selects concise output. The default output is JSON.
Create And Dispatch
metabot teams create <team> --description "..."
metabot teams agents spawn <team> <member> --role <role> --prompt "..."
metabot teams dispatch <team> <member> "<subject>" --description "..." --plain
metabot teams send <team> <member> "<message>" --from <sender>
metabot teams inbox <team> <member> --summary
dispatch creates the Task/message/Run projection used by the supervisor. A
teammate's final response returns through Team state and the configured display
destination.
The default maximum parallel Runs per Agent is 4, configurable with
METABOT_AGENT_TEAM_MAX_PARALLEL_PER_AGENT.
Tasks And Runs
metabot teams tasks get <team> <taskId>
metabot teams tasks claim <team> <taskId> <member>
metabot teams tasks done <team> <taskId> "<result>"
metabot teams tasks block <team> <taskId> "<reason>" --blocked-by <id,id>
metabot teams runs list <team>
metabot teams runs output <team> <runId>
metabot teams runs stop <team> <runId>
Run statuses are running, completed, failed, and stopped. Stopping a
supervisor-owned Run asks the bridge to stop the execution and prevents late
output from replacing terminal state. Assigned in-progress Tasks may return to
pending for retry.
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.
- 1mo ago First seen · 77 lines · 33 tokens per session scan A f4470478e305
metabot-team is a skill published in the GitHub repository xvirobotics/metabot (997 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 643 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
debug
Use when encountering any bug, test failure, or unexpected behavior. Enforces systematic root-cause investigation before proposing fixes. Prevents guess-and-check debugging.
review
Use when a branch, pull request or diff should be checked before it merges: a review, a bug hunt against a spec, a last look before shipping. Reviews the diff against the plan and reports the findings with a merge verdict.
atlas
Generate or update a semantic domain map (ATLAS.md) for the project. Maps where to look, entry points, module purposes, key symbols, and integration points. Complements codemap's structural index with the domain knowledge layer.
plan
Use when you have stories or clear requirements that need to become an implementation plan — lean tasks grouped into lanes, with decisions, exact file paths, test assertions, and verification commands.
ship
Use when implementation and review are complete and you need to integrate the work, or to triage a pull request's review comments saved to a file or pasted (verifies each, fixes the valid ones, drafts the replies). Verifies tests, presents options to merge, open a PR, or keep the branch; discards only on explicit…
wrap
Use when ending a session, taking a break, or context is getting full. Captures session state, decisions, and generates a resume prompt for the next session. Critical for multi-session continuity.