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.
git clone --depth 1 https://github.com/shuchitajain/awesome-ai-setupWrote 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.
[](https://agentmods.dev/agents/shuchitajain/awesome-ai-setup/generate-agent-workflows)<a href="https://agentmods.dev/agents/shuchitajain/awesome-ai-setup/generate-agent-workflows"><img src="https://agentmods.dev/badge/agents/shuchitajain/awesome-ai-setup/generate-agent-workflows.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00024 | $0.02611 |
| Opus 5 | $0.00012 | $0.01306 |
| Sonnet 5 | $0.00005 | $0.00522 |
| Haiku 4.5 | $0.00002 | $0.00261 |
Grade A, and why
generate-agent-workflows 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Agent Workflows
You are generating AGENTS.md and workflow files for this repository.
These files define structured AI agent roles and repeatable development workflows. They are used to give AI tools a scoped, consistent approach to common tasks like adding a new feature, fixing a bug, or refactoring code.
Agent definitions should reflect this project's actual architecture. Generic agents that could apply to any project are not useful. The value is in agents that know this codebase's specific layer structure, conventions, and patterns.
Step 1 - Read the Repository Context
This agent should be run after architecture and context files exist. Read them first.
Required reading:
ARCHITECTURE.md- understand the layers, data flow, and conventionsMEMORY.md- understand decisions made and patterns to avoidCONTEXT.mdif present - understand the domain- The primary source directory structure
- An existing feature (pick one that seems complete) - read its files across all layers to understand the actual development pattern
Understand:
- How many distinct layers exist? (e.g., domain / data / presentation)
- What is the typical development sequence for a new feature in this project?
- What are the natural "hand-off points" between layers?
- What repeatable tasks happen most often? (new feature, bug fix, refactor, migration?)
- What does a complete feature look like in terms of files? (count them, name the patterns)
Reference Example (Optional)
Check for a reference example in this order:
.ai/reference/*/AGENTS.mdand.ai/reference/*/workflows/- if the user copied one during setupnode_modules/awesome-ai-setup/examples/*/AGENTS.mdand.../workflows/- if the package is installed locally
If neither path exists, skip this section entirely and proceed to Step 2.
Use them as a structural guide only - what sections to include, how agents are defined, and how workflow steps are formatted. Do not copy their content; they describe a different project. All content must come from reading this codebase in Step 1.
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.
- 6d ago First seen · 305 lines · 24 tokens per session scan A df401ef21a2f
generate-agent-workflows is an agent published in the GitHub repository shuchitajain/awesome-ai-setup (5 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 2,611 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 2026-08-31.
Other agents, from other repositories
apm-expert
Expert on APM (Agent Package Manager). Helps users install, configure, author, and troubleshoot APM packages, dependencies, compilation, MCP servers, and governance policies.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
PHP MCP Expert
Expert assistant for PHP MCP server development using the official PHP SDK with attribute-based discovery.
react18-class-surgeon
Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE prefix). Migrates legacy context to createContext, string refs to React.createRef(), findDOMNode to direct refs, and ReactDOM.render to createRoot. Uses memory…
Custom Agent Foundry
Expert at designing and creating VS Code custom agents with optimal configurations.