Agent Factory Agent Skill

Manage Agent Factory (af) sessions, tabs, scheduled tasks, and the daemon via the af CLI.

Context cost
2.3k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 9.3 kBtext throughout, nothing executable
Licence
GPL-3.0the author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Manage Agent Factory (af) sessions, tabs, scheduled tasks, and the daemon via the af CLI

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

agentproductivity

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md9.3 kB · preview
--- name: agent-factory ---
5<!-- Generated by af gen-docs --plugin-root — DO NOT EDIT. Regenerate with scripts/gen-docs.sh. -->
6
7Agent Factory (af) is a terminal multiplexer that runs each AI coding agent in its own isolated git worktree and tmux session. Use the "af" CLI to hand a task to a background agent instead of doing it in this conversation, and to schedule recurring agent runs. You are NOT running inside af: af is a separate program that this plugin does not install, so run "af version" first, and if that fails tell the user to install it with "curl -fsSL https://raw.githubusercontent.com/sachiniyer/agent-factory/master/install.sh | sh" and stop — never download or run an installer yourself. Session and task commands need af's background daemon, which starts on demand; "af daemon status" reports it. Commands print JSON on stdout; run "af <command> --help" for full flag lists. Every session and task command is PROJECT-SCOPED: it acts on the current directory's project unless --repo <path> names another one, so "af tasks list" shows this project's tasks and "af tasks add" binds the new task here. Acting on another project always takes an explicit --repo; "af tasks list --all" is the one opt-in that spans every project. Session titles are unique WITHIN a project, not across projects, so the same name may exist in several repos: a <title> resolves inside --repo when given, else the current directory's repo. Task ids are globally unique but still project-scoped — "af tasks get/show/update/trigger/remove/restart <id-or-name>" accepts a task's id OR its exact name: an exact id match always wins (a name that collides with another task's id still resolves to the id), and otherwise the name must belong to exactly one task in scope — a name several in-scope tasks share is refused with their ids, and a task owned by another project is refused naming the --repo that would reach it. A task whose project changed underneath a command is refused rather than acted on; nothing is changed, so re-run it. With no repo context (outside a git repository) a title or task id-or-name held by just one project still resolves, while one held by several reports an error naming the matches — sessions list the projects to pick with --repo, tasks the ids to pass instead. Remote hook sessions are the one exception: their names are shared across projects because the hook scripts receive them verbatim.
8
9Sessions (one agent per isolated worktree):
10 af sessions whoami Identify your own session
11 af sessions list [--live] [--status <state>] [--max-age <duration>] [--limit N]
12 af sessions get <title> Fetch one session
13 af sessions create --name <title> [--prompt <p>] [--program claude|codex|aider|gemini|amp|opencode|devin]
14 af sessions send-prompt <title> <prompt> [--create] Send a prompt (--create makes the session first if missing)
15 af sessions preview <title> Snapshot another session's terminal output
16 af sessions watch <title> Wait for agent idle (awaiting input, not work completion); exits 0 on idle, non-zero on lost/dead/archived or --timeout (default 30m)
17 af sessions attach <title> Attach interactively (foreground)
18 af sessions kill <title> Delete a session; work in af-owned workspaces can be lost
19 af sessions archive <title> Archive (tmux down, worktree moved out; restartable)
20 af sessions archive --self Archive your OWN session (resolved via whoami); no title needed
21 af sessions handoff <title> [--to <agent>] [--account <name>] Continue under another agent, account, or both
22 af sessions retry-limit <title> Retry a usage-limit resume or an inspected, unconfirmed handoff
23 af sessions retry-limit <title> --delivered Mark an inspected handoff mission delivered (no resend); only after confirming it landed
24 af sessions restore <title> Restore an archived, lost, or dead session
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md1,361 words
Files1
LicenceGPL-3.0
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈30
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
2,295
on trigger
The instruction body, read only when the skill fires.
1.2%
of a 200k window
Ten skills this size would take about 12% of the window before you open a file.
050k100k150k200k context window

2.3k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Middling. Fine to keep on in a project where you use it weekly, worth unloading in one where you never do.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 9.3 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md9.3 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing. The GPL-3.0 licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Agent Factory · 2.3k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/sachiniyer-agent-factory/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/agent-factory" ] && { [ ! -e .claude/skills/agent-factory ] || { mv .claude/skills/agent-factory "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/agent-factory" .claude/skills/ && echo "Installed .claude/skills/agent-factory"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add sachiniyer/agent-factory

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/agent-factory/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/sachiniyer-agent-factory/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/agent-factory" ] && { [ ! -e ~/.claude/skills/agent-factory ] || { mv ~/.claude/skills/agent-factory "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/agent-factory" ~/.claude/skills/ && echo "Installed ~/.claude/skills/agent-factory" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/agent-factory/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencesachiniyer/agent-factory

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

SA
sachiniyer

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill