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 allemaar/open-skills --skill multi-agent-modegit clone --depth 1 https://github.com/allemaar/open-skillsWrote 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/allemaar/open-skills/multi-agent-mode)<a href="https://agentmods.dev/skills/allemaar/open-skills/multi-agent-mode"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/multi-agent-mode/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/allemaar/open-skills/multi-agent-mode"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/multi-agent-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 35 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00069 | $0.01144 |
| Opus 5 | $0.00034 | $0.00572 |
| Sonnet 5 | $0.00014 | $0.00229 |
| Haiku 4.5 | $0.00007 | $0.00114 |
Grade A, and why
multi-agent-mode 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 10d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/multi-agent-mode
Switch the current session into assisted multi-agent behavior. The lead agent remains responsible for planning, direct execution, integration, and final verification, but should actively look for independent slices that helper agents can handle in parallel or in the background.
Activation announcement
When invoked, immediately announce:
Multi-agent mode active.
I will continue working directly, and I may delegate independent helper slices when that improves speed, quality, or context control. I will keep ownership boundaries explicit, inspect helper outputs, and own final integration. Max 3 helpers without confirmation; no recursive subagents.
Then continue with the user's work item if provided.
Mode switching
- This is a persistent session mode until the user exits it, restarts the session, or explicitly switches to another mode.
- If the user invokes
orchestrate-mode, announce the switch: the lead agent is now dispatch-only and must not execute concrete work directly. - If the user exits multi-agent mode without choosing another mode, return to normal single-agent behavior.
- Latest explicit mode wins. Do not maintain a hidden mode stack.
Core behavior
The lead agent should do the first decomposition pass locally:
- Identify the immediate critical-path work the lead should do directly.
- Identify independent helper slices that do not block the next lead action.
- Delegate only slices with clear ownership and acceptance criteria.
- Resolve whether helpers have isolated workspaces or share the lead's filesystem. Keep working locally only on work that cannot collide with their reads, writes, branch selection, staging, or cleanup.
- Inspect helper outputs before integrating or relying on them.
- Run or request final verification for the integrated result.
When to delegate
Delegate when a slice is independent and materially useful, such as:
- Separate failing test files or unrelated failures.
- Independent subsystem investigations.
- Bounded implementation work in disjoint files.
- A focused review or research question that can run while the lead continues.
- UI, backend, docs, or migration slices with clear non-overlapping ownership.
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.
- 10d ago First seen · 112 lines · 69 tokens per session scan A 184c812592ba
multi-agent-mode is a skill published in the GitHub repository allemaar/open-skills (14 stars, last pushed 23d ago), licensed Apache-2.0. It adds 69 tokens to every session and 1,144 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
polis-protocol
Set up and run a self-improving, multi-vendor AI agent team with the Polis Protocol — a markdown polis/ folder where each agent is a citizen with a capability card, tasks are contracts routed to whoever has the best track record by a learning router, settled work files lessons that compound into team memory, and…
media
Skill "media" from ymxlx/polis-protocol, covering polis protocol: a self-optimizing city of agents, the core idea, when this skill is active, structure of a polis and the first thing to do every session.
_data
Skill "_data" from ymxlx/polis-protocol, covering polis protocol: a self-optimizing city of agents, the core idea, when this skill is active, structure of a polis and the first thing to do every session.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.