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 aAAaqwq/AGI-Super-Team --skill native-agent-swarmsgit clone --depth 1 https://github.com/aAAaqwq/AGI-Super-TeamWrote 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/aaaaqwq/agi-super-team/native-agent-swarms)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/native-agent-swarms"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/native-agent-swarms/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/aaaaqwq/agi-super-team/native-agent-swarms"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/native-agent-swarms.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 | $0.00070 | $0.00835 |
| Opus 5 | $0.00035 | $0.00417 |
| Sonnet 5 | $0.00014 | $0.00167 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
native-agent-swarms 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 13d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Native Agent Swarms
Use Codex-native collaboration instead of Claude TeamCreate, TaskCreate, SendMessage, tmux, or shared team-state conventions. Keep orchestration in the parent agent and use specialists as leaf workers.
Gate delegation
Delegate only when the user or applicable project instructions authorize subagents. Delegation never expands the user's requested scope or permission to change external state.
Before spawning, confirm:
- At least two work streams are genuinely independent.
- Each worker has a bounded objective and sufficient starting evidence.
- Writable files have exactly one owner.
- The expected speed or quality gain exceeds coordination overhead.
- Available thread capacity can accommodate the team; prefer 2-3 workers and never exceed the configured limit.
Stay sequential when tasks share state, one result determines the next, or workers would edit the same files.
Compose the team
Select the narrowest installed custom agents. Typical choices include planner, architect, code-reviewer, security-reviewer, quality-engineer, hypothesis-debugger, performance-reviewer, database-reviewer, accessibility-reviewer, and language reviewers.
Use team-coordinator only to advise on decomposition. The parent agent remains responsible for spawning, monitoring, resolving conflicts, and final verification. Keep nesting depth at one unless the user explicitly asks for recursive delegation and the runtime configuration safely allows it.
Write dispatch contracts
Every worker task must include:
Objective: one concrete result.
Scope: exact subsystem, files, or hypothesis.
Ownership: writable files; all other files are read-only.
Starting evidence: errors, requirements, paths, and relevant constraints.
Acceptance criteria: observable completion conditions.
Safety: no commit, push, deploy, external messages, secret access, or destructive commands.
Output: findings or changes, evidence, commands run, gaps, and a concise handoff.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 74 lines · 70 tokens per session scan A c2d290287978
native-agent-swarms is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (92 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 835 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
guidance
Add, edit, or audit guidance docs. Default writes guidance for Claude (.claude/guidance/, Markdown, moflo universal rules). -h writes for human readers (docs/, lighter ruleset). --html emits HTML with a minimal default stylesheet instead of Markdown. -a audits the .claude/guidance/ directory.
deslop
The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
eldar
Consult the Eldar — audit a project's moflo + Claude Code setup for portable, high-leverage gaps and guide remediation. Default mode is read-only audit with severity-ranked findings; --fix presents an interactive triage menu and walks the user through each chosen fix (healer, missing CLAUDE.md, sparse guidance…
root-cause
Find the mechanism behind a failure instead of patching its symptom - reproduce first, one variable per experiment with the prediction written before the run, exit by naming the mechanism and pinning it with a failing test. Use for a bug, an unexplained red test, or a failure that will not reproduce.
memory-worktree
Verify, customize, or opt out of moflo's AUTOMATIC durable-learning sharing across git worktrees / Conductor workspaces on one machine. As of the worktree-auto-sharing change this is on by default — learnings converge across a repo's worktrees with no setup. Use when the user asks "is memory shared across my…
code-tour
Maintain docs/code-tour.md — the annotated guided reading of Aigon's core logic. Use when you have changed code the tour quotes, added a subsystem a new reader would need, or the user says "update the code tour", "the tour is stale", "add X to the code tour", or asks to review/refresh the code examples doc.