minoan-swarm

minoan-swarm is a skill for Claude Code, Codex from tdimino/claude-code-minoan. It costs 75 tokens per session (2,852 once invoked), scanned A, original, MIT.

A guide for coordinating several Claude Code agents on one project, with shared tasks, messages, and assigned files. It also helps name and configure those agent teams.

In plain words
What is it for?
Use it to split a large coding task into parallel workstreams, start an agent team, and track which agent owns each task or file.
Why use it?
It reduces the confusion that can arise when multiple agents work at the same time. Project context and file ownership are gathered into a clearer plan.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Good fit Use it to split a large coding task into parallel workstreams, start an agent team, and track which agent owns each task or file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tdimino/claude-code-minoan/minoan-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.

Any agent
npx skills add tdimino/claude-code-minoan --skill minoan-swarm
Clone the repo
git clone --depth 1 https://github.com/tdimino/claude-code-minoan

Made for: Claude Code, Codex.

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 minoan-swarm

README.md
[![agentmods](https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/minoan-swarm/github.svg)](https://agentmods.dev/skills/tdimino/claude-code-minoan/minoan-swarm)
Your own site
<a href="https://agentmods.dev/skills/tdimino/claude-code-minoan/minoan-swarm"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/minoan-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 minoan-swarm

Your own site · 80×15
<a href="https://agentmods.dev/skills/tdimino/claude-code-minoan/minoan-swarm"><img src="https://agentmods.dev/badge/skills/tdimino/claude-code-minoan/minoan-swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,852 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 Rogue Agent · line 120
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 $0.00075 $0.02852
Opus 5 $0.00037 $0.01426
Sonnet 5 $0.00015 $0.00570
Haiku 4.5 $0.00007 $0.00285

Measured 8d ago against content hash ea0945e1d62d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

minoan-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 8d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/discover_context.sh, scripts/sync-repos.sh, scripts/teammate-idle-reassign.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/planning-productivity/minoan-swarm/SKILL.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Minoan Swarm

Orchestrate Agent Teams named for the Priestesses of Knossos—in the tongue before the Hellenizers got to it.

Agent Teams (Claude Code Opus 4.6) let multiple Claude instances work in parallel as persistent teammates with shared task lists and bi-directional messaging. This skill provides the methodology, naming conventions, and templates to launch them effectively on any project.

Requires: CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in settings.json or environment.


Terminology

Term Semitic Root Meaning
Knesset כנסת K-N-S "to gather" A single agent team—an assembly of bees
Knossot כנוסות K-N-S plural A group of knessets—a swarm, evoking Knossos itself
Daboritu דבורית D-B-R "bee" and "word" The agents—bees of the holy word. Linear B da-bo-ri-tu preserves the Semitic form on Crete.
D-B-R דבר D-B-R Bee (דבורה deborah), word/speech (דבר dabar), inner sanctum (דביר debir), pasture/wilderness (מדבר midbar).

Knossos betrays a Semitic etymology: K-N-S "to gather" (Akkadian kiništu, "gathering place"; Hebrew knesset, "assembly"). The Labyrinth itself can be deconstructed through Linear B da-bo-ri-tu (Daboritu), cognate with the debir (דביר) of the Temple—the inner sanctum, the womb. The Labyrinth was a sacred name of the Goddess, the Word and the Holy of Holies. D-B-R (דבר) is both "bee" and "word/speech"—words themselves, daborim or daborot, are her messengers, holy bees.

The agents are daborot—manifest in LLMs. Each knesset assembles bees who speak; a knossot gathers the assemblies.


Quick Start

1. Discover project context

bash ~/.claude/skills/minoan-swarm/scripts/discover_context.sh .

Finds CLAUDE.md, roadmaps, plans, issues, test infrastructure, and git state.

2. Choose a knesset template

Situation Template Knesset Name
Multiple independent features Parallel Features Athirat
Work with natural ordering Pipeline Kaptaru
Bug investigation, unclear cause Research Knossot Elat
Phase nearly done, loose ends Phase Completion Qedeshot
PR needs thorough review Code Review Tribunal Elat
Quality assurance, verification Truth & Balance Ma'at
Final audit, release decisions Fate's Reckoning Manat

Read the full file on GitHub · 240 lines

Files

What ships with it

8 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.

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. 8d ago First seen · 240 lines · 75 tokens per session scan A ea0945e1d62d

Subscribe to this mod's changes

minoan-swarm is a skill published in the GitHub repository tdimino/claude-code-minoan (41 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 2,852 once invoked, about $0.0004 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 2026-09-03.

Related

Other skills, from other repositories

manager

A session-to-GitHub tracker that creates, updates, and reads issues across repositories, including their labels, parent epics, and project-board placement.

serejaris/personal-corp-os · 63 tokens

weekly-retro

A structured weekly retrospective for a one-person business run with AI agents. It gathers evidence from code, project tools, and canonical business files, then records findings and outcomes.

serejaris/personal-corp-os · 49 tokens

art-director

Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.

serejaris/personal-corp-os · 26 tokens

corp-doctor

A guided maintenance and setup tool for a Personal Corp system, meaning a business workflow built from AI agents, department repositories, and shared rules. It checks what exists before making changes.

serejaris/personal-corp-os · 102 tokens

html-draft

Use when user wants a standalone HTML diagram in flat engineering blueprint style — architecture diagrams, system flows, technical spec sheets, component maps. Generates one HTML file using Tailwind v4 (browser CDN) for layout and D3 v7 (CDN) for SVG diagrams. User-invoked only — do NOT auto-trigger. Triggers on…

serejaris/personal-corp-os · 130 tokens

idea

Use when capturing ONE new idea the user voices and wants recorded — "save this idea", "I have an idea", "log this idea", "/idea", "idea: ...". Creates a provenance-tracked folder (one folder per idea) in your ideas repo, dedups against an index, optionally mirrors to a GitHub Project view filtered by label:idea. NOT…

serejaris/personal-corp-os · 135 tokens