agents

Ready-to-use agents

Repeatable procedures your AI agent runs with judgment. Every run writes a trace. The agent gets better over time.

Anatomy of an agentmodules/support-ops/
index.mdmanifest
steps/
1-collect.md
2-process.md
commands/
setup.md
runs/
1/
1-collect/
results.md
2-process/
results.json
done/
info.md
(other)
How a run works
1
Read index.md
Learn the purpose
2
Read steps
Load all instructions
2a
1-collect.md
2b
2-process.md
3
Run steps
Execute and report
3a
1-collect.md
3b
2-process.json
4
Done
Report to user

What is a context-based agent

An agent is a folder of markdown files that an AI runtime follows. It has steps, a setup command, and a runs/ folder where every execution writes its trace. The agent reads past runs before it starts a new one, so it makes better decisions each time.

This is not a prompt chain or a static runbook. The steps give the agent room for judgment: they say what to accomplish and when the step is done, not which API call to make. The result is a procedure that works across different systems because the agent adapts it.

Every agent declares two kinds of inputs:

  • connections are the services the agent talks to (an API, a database, a platform). You map them once at setup, and the agent uses them for every run.
  • parameters are the values you give when you start a run: the scope, the target, the input for that execution. They change each time.
terminal
$ gcontext add browser-cookbook
gcontext - installed Browser Cookbook (14 files) at agents/browser-cookbook/
Next step: run /mcp__<instance_name>__browser_cookbook__setup in your client.

How runs build on each other

The first run starts from the procedure alone. It operates, observes, and writes what happened into its runs/ folder. The second run reads that trace before it begins. If the first run discovered a selector or a retry pattern, the second run knows about it and applies it.

Playbooks, decision logs, and checklists accumulate inside the agent's folder. The agent consults them before every step. Nothing is retrained, no model is fine-tuned. The context is just files, and the agent reads them.

run trace
$ /mcp__<instance_name>__browser_cookbook__browse task: export this month's invoices
BROWSING: billing page, export dialog, CSV download
DONE: invoices-aug.csv (42 rows)
Updated sites/billing.example.com/ (navigation, selectors)
Trace in runs/2026-08-22-export-invoices/
To save as recipe: /mcp__<instance_name>__save_recipe

Anatomy of an agent folder

Every agent follows the same structure. A manifest, numbered steps, a place for runs, and optional commands and functions.

agent folder
📄
index.md

Manifest with metadata, description, parameters, and connection requirements.

📋
steps/

Numbered markdown files the agent follows, each with a clear objective and done condition.

🗂
runs/

Traces from completed runs. The agent reads past runs to make better decisions.

⚙️
commands/

Setup interview and user-invokable actions. The setup command personalizes the agent.

anything else/

Functions, playbooks, checklists, templates. Add whatever folders the agent needs. The structure is yours.

How to add an agent

With gcontext

One command. The agent lands in your instance's modules/ folder, ready for the setup interview.

$ gcontext add browser-cookbook

Without gcontext

Every agent is a plain folder of markdown files. Download it from the agent page and drop it into any instance. No lock-in, no runtime dependency.

Published agents

Browse all →
Browser Cookbook23 files

A browser agent that learns your sites. It performs browser tasks through your real Chrome, accumulates per-site knowledge, and crystallizes repetitive tasks into plain Python scripts; on later runs the AI only dispatches the script and heals failures. Broken knowledge heals itself; blockers like captchas escalate to you.

automationbrowser
gcontext add browser-cookbook
Diagram Crafter31 files

A diagram agent that turns an initial text into a polished explanatory visual, hand-crafted as SVG. It scopes the single claim the diagram must make, proposes 2-3 ASCII wireframe compositions built from proven archetypes, and expands the chosen one using a written design system so results stay consistent across runs. The user decides composition; the design system decides style. Finished diagrams accumulate in a library the agent consults on later runs.

diagramsvisualscommunication
gcontext add diagram-crafter
Post Crafter35 files

A marketing post agent that puts the headline first. Each post starts from a chosen angle, then a headline workshop generates candidates from proven persuasion formulas (Cialdini, Kahneman, Caples), scores them, red-teams the best, and lets the user pick or rewrite. The body follows in two layers: a System 1 hook to stop the scroll, then System 2 proof to close the deal. The user controls every content decision. Product knowledge accumulates in a shared products/ folder so repeat runs stop re-asking.

marketingcontentcopywriting
gcontext add post-crafter