ai-fleet-project-execution

ai-fleet-project-execution is a skill for Claude Code, Codex from Szotasz/marveen. It costs 63 tokens per session (18,008 once invoked), scanned A, original, MIT.

A workflow for coordinating a project among several AI agents, such as project management, marketing, backend development, and video work. It manages work through a Kanban board, where tasks move through statuses such as planned, in progress, waiting, and done.

In plain words
What is it for?
Use it when a team of agents must execute a project independently, delegate tasks, record updates on Kanban cards, and run regular progress audits.
Why use it?
It keeps multi-agent projects organized and makes ownership, priorities, progress, and handoffs visible across longer work sessions.

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 when a team of agents must execute a project independently, delegate tasks, record updates on Kanban cards, and run regular progress audits.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/szotasz/marveen/ai-fleet-project-execution
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 Szotasz/marveen --skill ai-fleet-project-execution
Clone the repo
git clone --depth 1 https://github.com/Szotasz/marveen

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 ai-fleet-project-execution

README.md
[![agentmods](https://agentmods.dev/badge/skills/szotasz/marveen/ai-fleet-project-execution/github.svg)](https://agentmods.dev/skills/szotasz/marveen/ai-fleet-project-execution)
Your own site
<a href="https://agentmods.dev/skills/szotasz/marveen/ai-fleet-project-execution"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/ai-fleet-project-execution/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 ai-fleet-project-execution

Your own site · 80×15
<a href="https://agentmods.dev/skills/szotasz/marveen/ai-fleet-project-execution"><img src="https://agentmods.dev/badge/skills/szotasz/marveen/ai-fleet-project-execution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 18,008 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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: 3 findings, up to high

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 →

  • high Agent Snooping · line 206
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • medium MCP Rug Pull · line 106
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium Excessive Agency · line 245
    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.
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 $0.00063 $0.18008
Opus 5 $0.00032 $0.09004
Sonnet 5 $0.00013 $0.03602
Haiku 4.5 $0.00006 $0.01801

Measured 11d ago against content hash 664ca9383c61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ai-fleet-project-execution scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

2. `curl -s -X POST http://localhost:3420/api/agents/<name>/start -H "Authorization: Bearer $(cat store/.dashboard-token)"` → `{"ok":true}` válasz
seed-skills/ai-fleet-project-execution/SKILL.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Fleet Project Execution

Mikor használd

A user átad egy projektet "csapatként vigyétek végig önállóan" instrukcióval. Triggerek:

  • "Rátok bízom, csináljátok"
  • "Folyamatosan adj feladatokat az ágenseknek",
  • "Nem akarok beleszólni, csak a heti riportot kérem"

KANBAN-FIRST workflow (KÖTELEZŐ alapértelmezés)

Minden projekt és részfeladat KÖTELEZŐEN kanban-kártyán keresztül menedzselt. Az ad-hoc inter-agent message-csak delegálás csak EMERGENCY-re (pl. broken-prod fix, time-critical pairing) -- minden más:

  1. Részfeladat → új kártya: project mezővel, assignee mezővel (backend dev / marketing / video agent / stb.), priority + status='planned' vagy 'in_progress'.
  2. Delegálás → inter-agent message + kanban referencia: az üzenetben hivatkozz a kártya ID-ra (Lásd kanban kártya XXXX, status=in_progress). Az agent a kártyán is jelezzen vissza (kanban_comments táblába írjon kommentet).
  3. Sub-agent kötelezettsége: az agent CLAUDE.md-jébe építve, hogy minden feladaton STATUS-OLJON (planned → in_progress → waiting/done). NEM csak inter-agent reply.
  4. Orchestrator 3-4 órás audit: scheduled task ami 3 óránként:
    • Tisztítja a 7+ napos done-okat (archive)
    • Beakadt taskokat (>24h in_progress mozgás nélkül) számon kéri az assignee-nél inter-agent message-szel
    • Új delegálatlan/nélküli kártyákat jelzi az orchestratornak
  5. Heti riport: az orchestrator összegzi a board-állapotot Telegramon a usernek (minden péntek).
  6. Meta-task NEM kerül kanbanra: ami folyamatos monitor / scheduled-task / mindenkori /loop-ciklus (pl. "GitHub PR monitor", "Reggeli napindító"), ne legyen kanban-kártya -- mert a kanban-audit beakadtnak fogja jelölni. Ezeket ~/.claude/scheduled-tasks/<név>/ mappában tartsuk, vagy a ~/.claude/scheduled-tasks.json-ben. (Sub-agent feedback alapján: a pr-figyelés scheduled-task-ja kezeli, nem kanban-kártya.)

Eljárás

1. Indítás (~30 perc)

  1. Kanban parent kártya: hozz létre egy nagy hierarchia-fa parent-kártyát a projektnek. Description: scope, célok, szabályok.

Read the full file on GitHub · 290 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. 11d ago First seen · 290 lines · 63 tokens per session scan A 664ca9383c61

Subscribe to this mod's changes

ai-fleet-project-execution is a skill published in the GitHub repository Szotasz/marveen (98 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 18,008 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

commonly

You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…

Team-Commonly/commonly · 0 tokens

oma-coordination

Guide for coordinating PM, Frontend, Backend, Mobile, and QA agents on complex projects via CLI. Use for manual step-by-step coordination and workflow guidance.

first-fluke/oh-my-agent · 36 tokens

oma-pm

Product manager that decomposes requirements into actionable tasks with priorities and dependencies. Use for planning, requirements, specification, scope, prioritization, task breakdown, and ISO 21500, ISO 31000, or ISO 38500-aligned planning recommendations.

first-fluke/oh-my-agent · 55 tokens

wayfinder

Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

willdady/platypus · 46 tokens

triage

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

willdady/platypus · 33 tokens

to-tickets

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.

willdady/platypus · 54 tokens