agent-factory

agent-factory is a skill for Claude Code, Codex from Sistema2D/FrameCode-VibeWork. It costs 16 tokens per session (1,073 once invoked), scanned A, original, Apache-2.0.

A decision guide for creating reusable skills or agent profiles. It checks whether a repeated task needs a new asset, a small addition to an existing one, or nothing new.

In plain words
What is it for?
Use it when proposing a new skill, specialist agent, persona, command pack, or operating procedure. It helps assess repeated work, existing coverage, ownership, validation, and maintenance cost.
Why use it?
It prevents a project from accumulating unnecessary instructions and agents. It also requires evidence that a proposed asset will be useful and maintainable.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/sistema2d/framecode-vibework/agent-factory
Any agent
npx skills add Sistema2D/FrameCode-VibeWork --skill agent-factory
Clone the repo
git clone --depth 1 https://github.com/Sistema2D/FrameCode-VibeWork

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 agent-factory

README.md
[![agentmods](https://agentmods.dev/badge/skills/sistema2d/framecode-vibework/agent-factory.svg)](https://agentmods.dev/skills/sistema2d/framecode-vibework/agent-factory)
Your own site
<a href="https://agentmods.dev/skills/sistema2d/framecode-vibework/agent-factory"><img src="https://agentmods.dev/badge/skills/sistema2d/framecode-vibework/agent-factory.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,073 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00016 $0.01073
Opus 5 $0.00008 $0.00536
Sonnet 5 $0.00003 $0.00215
Haiku 4.5 $0.00002 $0.00107

Measured 5d ago against content hash 8177d47d933c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agent-factory 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 5d 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.

FCVW/skills/agent-factory/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SKILL: Agent and Skill Factory

Purpose

Govern the creation of new skills and specialized agent profiles without allowing uncontrolled proliferation. This skill is a Markdown-only gate: it decides whether a recurring problem deserves a reusable procedural asset, a small checklist inside an existing document, or no new asset.

Activation Triggers

Load this skill before creating any new file under skills/ or any new agent profile when:

  • a user asks to create a new agent, skill, specialist, persona, command pack, or operational procedure;
  • the same task pattern appears repeatedly in plans, sessions, troubleshooting records, or changelogs;
  • an existing skill is too broad, too vague, or missing a repeatable procedure for a high-risk task;
  • a proposed solution would otherwise add long instructions to AGENTS.md, AI.md, or another base-loaded document;
  • an agent proposes a new role to solve a specific recurring problem.

Inputs

Recurring task evidence, existing skill/catalog coverage, trigger and responsibility boundary, expected consumers, validation task, maintenance owner, and token/risk ROI estimate.

Decision Ladder

Use the smallest reusable asset that solves the problem:

Level Use when Output
Inline checklist One-off or low-risk clarification. Add 3-7 bullets to the existing canonical document.
Template Repeated output format is needed, but execution logic is simple. Add a governance/TEMPLATE_*.md file.
Skill A repeatable procedure has clear triggers, gates, validation, and exit criteria. Add skills/<name>/SKILL.md.
Agent profile A bounded role must execute a specialized loop with tools, journals, or handoff. Add or update a focused agent-* skill/profile.

Creation Gate

Creation is allowed only when all required metrics pass:

Metric Pass threshold
Recurrence At least 2 independent occurrences, or 1 P1/P2 high-risk blocker.
Coverage gap Existing docs/skills cover less than 70% of the needed procedure.
Token ROI Expected initial-context reduction of at least 20%, or avoids adding 500+ words to base-loaded docs.
Risk ROI Reduces a recurrent failure class, compliance risk, data risk, monolith risk, or validation gap.
Scope narrowness One trigger family, one responsibility, one primary output, and one validation path.
Validation path The new asset can be tested against at least one real plan/session/task.

Read the full file on GitHub · 110 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. 5d ago First seen · 110 lines · 16 tokens per session scan A 8177d47d933c

Subscribe to this mod's changes

agent-factory is a skill published in the GitHub repository Sistema2D/FrameCode-VibeWork (23 stars, last pushed 5d ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,073 once invoked, about $0.0001 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.