mega-swarm

mega-swarm is a command for Claude Code from ANcpLua/ancplua-claude-plugins. It costs 42 tokens per session (1,642 once invoked), scanned A, original, MIT.

A parallel codebase audit that uses several specialist agents to inspect architecture, APIs, security, dependencies, performance, tests, configuration, documentation, and other areas. It combines their findings into one report and can pass them to a fixing workflow.

In plain words
What is it for?
Use it for release-readiness checks, general audits, or focused reviews of source code, tests, configuration, or security.
Why use it?
It gives a broad review of a repository without relying on one person or one type of inspection.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; names the TodoWrite tool; positional $N argument.

Part of the exodia plugin — 2 skills, 7 commands shipped together

Good fit Use it for release-readiness checks, general audits, or focused reviews of source code, tests, configuration, or security.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ancplua/ancplua-claude-plugins/mega-swarm
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ANcpLua/ancplua-claude-plugins

Made for: Claude Code.

Or install exodia, the plugin that ships this one along with the rest of its 2 skills, 7 commands.

Wrote 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.

agentmods badge for mega-swarm

README.md
[![agentmods](https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/mega-swarm/github.svg)](https://agentmods.dev/commands/ancplua/ancplua-claude-plugins/mega-swarm)
Your own site
<a href="https://agentmods.dev/commands/ancplua/ancplua-claude-plugins/mega-swarm"><img src="https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/mega-swarm/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.

agentmods 80×15 button for mega-swarm

Your own site · 80×15
<a href="https://agentmods.dev/commands/ancplua/ancplua-claude-plugins/mega-swarm"><img src="https://agentmods.dev/badge/commands/ancplua/ancplua-claude-plugins/mega-swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,642 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.01642
Opus 5.5 $0.00017 $0.00657
Sonnet 5.5 $0.00008 $0.00328
Haiku 4.5 $0.00004 $0.00164

Measured 14d ago against content hash b9c8352529c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mega-swarm 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 14d 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.

plugins/exodia/commands/mega-swarm.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MEGA SWARM — Parallel Codebase Audit

Maximum coverage. Every angle. One report.

Scope: $0 (default: full | full|src|tests|config|security) Focus: $1 (optional focus area) Mode: $2 (default: full | full|quick|focused) Quick: $3 (default: false — same as mode=quick)


TEAM ARCHITECTURE

SWARM LEAD (You — Orchestrator)
│
├─ Full mode (12 agents) ─────────────────────
│  ├── arch-auditor        ├── api-auditor
│  ├── security-auditor    ├── dependency-auditor
│  ├── perf-auditor        ├── config-auditor
│  ├── test-auditor        ├── docs-auditor
│  ├── quality-auditor     ├── consistency-auditor
│  ├── error-auditor       └── bug-hunter
│
├─ Quick mode (6 agents) ─────────────────────
│  ├── arch-auditor    ├── security-auditor
│  ├── perf-auditor    ├── test-auditor
│  ├── quality-auditor └── bug-hunter
│
├─ Focused mode (8 agents) ───────────────────
│  └── $1-related auditors + adjacent concerns
│
└── GATE → >=80% complete → SYNTHESIZE

<CRITICAL_EXECUTION_REQUIREMENT>

STEP -1 — Inherit Prior Findings: If <EXODIA_FINDINGS_CONTEXT> tag exists in session context, .eight-gates/artifacts/findings.json already has prior scan data. Report existing findings instead of re-scanning. Only launch agents for UNCOVERED areas.

STEP FINAL — Persist Findings: After synthesis, write ALL findings to .eight-gates/artifacts/findings.json:

{"session":"[ID]","source":"mega-swarm","total_findings":N,"by_category":{...},"findings":[{"id":"...","category":"...","severity":"P0-P3","title":"...","files":[...],"fix":"...","effort":"S|M|L|XL"}]}

This enables auto-inherit for ALL downstream Exodia skills in parallel sessions.

Launch ALL agents for selected mode in ONE message. NOTHING ELSE.

  • Full ($2=full or unspecified): 12 agents
  • Quick ($2=quick or $3=true): 6 agents
  • Focused ($2=focused): 8 agents relevant to $1

Wait for completion. Synthesize. Report.

YOUR NEXT MESSAGE: Task tool calls for selected mode. NOTHING ELSE.

Read the full file on GitHub · 193 lines

Changes

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.

  1. 14d ago First seen · 193 lines · 42 tokens per session scan A b9c8352529c8

Subscribe to this mod's changes

mega-swarm is a command published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 1,642 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 2026-10-01.