What is use-agent-factory?

Instructions for operating an agent factory: a set of automated workflows that moves a software change from an issue through planning, implementation, review, and merging.

Use it to start or monitor the factory, handle issues and pull requests, choose an implementation workflow, and resolve stalled stages.

It explains when to use the factory, where a person must approve or intervene, and how to recover when the process gets stuck.

How pskoett/measuring-ai-proficiency configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to pskoett/measuring-ai-proficiency. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/pskoett/measuring-ai-proficiency/main/.claude/skills/use-agent-factory/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/pskoett/measuring-ai-proficiency

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pskoett/measuring-ai-proficiency/use-agent-factory/github.svg)](https://agentmods.dev/skills/pskoett/measuring-ai-proficiency/use-agent-factory)

Your own site

<a href="https://agentmods.dev/skills/pskoett/measuring-ai-proficiency/use-agent-factory"><img src="https://agentmods.dev/badge/skills/pskoett/measuring-ai-proficiency/use-agent-factory/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/pskoett/measuring-ai-proficiency/use-agent-factory"><img src="https://agentmods.dev/badge/skills/pskoett/measuring-ai-proficiency/use-agent-factory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,153 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.

Model	Per session	Once invoked
Fable 5.1	$0.00170	$0.03153
Opus 5.5	$0.00068	$0.01261
Sonnet 5.5	$0.00034	$0.00631
Haiku 4.5	$0.00017	$0.00315

Measured 2mo ago against content hash 01b2d105c77c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

use-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 2mo 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.

.claude/skills/use-agent-factory/SKILL.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use the Agent Factory

Purpose

This repo runs a gh-aw agent factory plus one plain Actions workflow. Every non-trivial change should flow through it end to end: issue > spec > plan PR merged > source issue activated > implementer > review > fix > merge > learn. The source issue is the unit of work; there is no sub-issue layer. This skill tells you how to drive that flow correctly, where to stop and wait for a human, and what to do when something stalls.

When to invoke

Activate this skill when any of these hold:

User asks you to add, fix, refactor, or ship something that will end up on main
User references an issue number, PR number, or plan file that belongs to the factory chain
User asks about factory status, stuck PRs, or the needs-spec / needs-changes / fast-track labels
A PR in this repo has been labeled by the factory and you need to decide the next action
User asks to file a new needs-spec issue or to spec-refine an existing issue

Skip this skill for: local scratch work that never reaches main, questions about the codebase that don't require any edits, read-only audits, or small doc tweaks the user explicitly says should bypass the factory.

Prerequisites the user must have already done

Before the factory works end to end, these one-time setup items must be in place. If any PR stalls with symptoms like "waiting for approval" or "labels don't stick", suspect these first. Full table in docs/AGENT_FACTORY.md#prerequisites.

Category	What must be true
Repo settings	`Settings > Actions > General`: Read and write permissions, Allow GitHub Actions to create and approve pull requests checked, Approval for outside collaborators = Require approval for first-time contributors who are new to GitHub
Copilot	`Settings > Copilot > Coding agent` enabled; `Settings > Copilot > Code review` enabled
Secrets	`COPILOT_GITHUB_TOKEN`, `GH_AW_GITHUB_TOKEN`, `GH_AW_GITHUB_MCP_SERVER_TOKEN`, `GH_AW_AGENT_TOKEN`, `GH_AW_CI_TRIGGER_TOKEN` all present in Actions secrets
Labels	All factory labels from the Label Reference table must exist

Read the full file on GitHub · 215 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.

2mo ago First seen · 215 lines · 170 tokens per session scan A 01b2d105c77c

Subscribe to this mod's changes

use-agent-factory is a skill published in the GitHub repository pskoett/measuring-ai-proficiency (13 stars, last pushed 3mo ago), licensed MIT. It adds 170 tokens to every session and 3,153 once invoked, about $0.0007 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 2026-08-31.

Building agents Planning

use-agent-factory next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
use-agent-factorypskoett/measuring-ai-proficiency	Skill	13	3mo ago	MIT	A	170	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

measuring-ai-proficiency: Skill for Claude Code