agentleFS
InsForgeInsForge/insforge-skills/AGENTS.md

insforge-skills

AGENTS.md47 starsChanged 5 months agoApache-2.0View on GitHub

This document helps AI coding agents work effectively with the InsForge Agent Skills repository. This repository follows the Agent Skills Open Standard. Each skill contains a SKILL.md with: Most InsForge skill modules use focused app-facing guides: The AI module is capability-based instead: start at skills/insforge/ai/overview.md, then load only the needed OpenRouter guide (chat-completions.md, image-generation.md, video-generation.md, audio.md, embeddings-and-rag.md, or models-list.md). 1. Create a directory under skills/insforge/ with the module name 2. Add sdk-integration.md for client-side SDK usage, or use a focused…

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository4 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create a directory under skills/insforge/ with the module name

    line 71
  2. Very specific:

    Add sdk-integration.md for client-side SDK usage, or use a focused capability guide when the module spans multiple APIs

    line 72
  3. Distinctive:

    Add specialized guides only when a capability needs separate backend, security, protocol, or workflow documentation

    line 74
  4. Very specific:

    Update the module reference table in skills/insforge/SKILL.md

    line 76
  5. Distinctive:

    Keep code examples concise and runnable

    line 84
  6. Distinctive:

    When working with InsForge skills, remember:

    line 99
  7. Very specific:

    Metadata Endpoint: Always fetch /api/metadata before making changes

    line 102
  8. Very specific:

    Auth References: Use auth.users(id) for user foreign keys, auth.uid() in RLS policies

    line 103

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AI Agent Guidance

This document helps AI coding agents work effectively with the InsForge Agent Skills repository.

Repository Structure

agent-skills/
├── skills/
│   └── insforge/           # InsForge BaaS development skill
│       ├── SKILL.md        # Skill manifest and overview
│       ├── database/       # Database operations
│       ├── auth/           # Authentication flows
│       ├── storage/        # File storage
│       ├── functions/      # Serverless functions
│       ├── ai/             # AI/ML operations
│       ├── realtime/       # Real-time messaging
│       ├── payments/       # Stripe and Razorpay app payment flows
│       └── email/          # Transactional email
│   └── insforge-cli/       # InsForge CLI project management
│       ├── SKILL.md        # Skill manifest and command reference
│       └── references/     # CLI command reference
│           ├── database/   # Database migrations, query, RLS, vector, import/export
│           ├── auth.md
│           ├── create.md
│           ├── login.md
│           ├── functions-deploy.md
│           ├── payments/   # Shared payments routing plus provider references
│           │   ├── overview.md
│           │   ├── stripe.md
│           │   └── razorpay.md
│           ├── deployments/
│           │   ├── deploy.md
│           │   └── domains.md
│           └── ...
├── AGENTS.md               # This file
├── CONTRIBUTING.md         # Contribution guidelines
├── LICENSE                 # Apache License 2.0
└── README.md               # Repository documentation

Skill Format

This repository follows the Agent Skills Open Standard.

SKILL.md Structure

Each skill contains a SKILL.md with:

  1. YAML Frontmatter: Required name and description fields, optional license. No metadata: block — the OpenAI plugin submission portal rejects it; interface settings go in the skill's agents/openai.yaml
  2. Markdown Body: Instructions, examples, and references to module documentation

Documentation Pattern

Most InsForge skill modules use focused app-facing guides:

FilePurposeWhen to Use
sdk-integration.mdApp-facing SDK/API usage, usually through @insforge/sdkImplementing features in user's app code
Specialized guides such as storage/postgres-rls.md, s3-gateway.md, CLI references like references/database/access-control.md, references/database/integrity.md, references/database/vector.md, or payment provider filesBackend, security, payment-provider, protocol, or infrastructure-specific patternsWhen the task needs that capability

The AI module is capability-based instead: start at skills/insforge/ai/overview.md, then load only the needed OpenRouter guide (chat-completions.md, image-generation.md, video-generation.md, audio.md, embeddings-and-rag.md, or models-list.md).

Working with This Repository

Adding a New Module

  1. Create a directory under skills/insforge/ with the module name
  2. Add sdk-integration.md for client-side SDK usage, or use a focused capability guide when the module spans multiple APIs
  3. Add specialized guides only when a capability needs separate backend, security, protocol, or workflow documentation
  4. Update the module reference table in skills/insforge/SKILL.md

For payments, keep app guides provider-specific (payments/stripe.md, payments/razorpay.md) and keep CLI routing/provider docs in skills/insforge-cli/references/payments/.

Updating Existing Documentation

  1. Locate the relevant file in the module directory
  2. Maintain the existing format: Setup, Usage Examples, Best Practices, Common Mistakes
  3. Keep code examples concise and runnable
  4. Include both correct and incorrect examples where helpful

Validation Checklist

Before committing changes:

  • SKILL.md frontmatter is valid YAML
  • Skill name matches directory name (lowercase, hyphens only)
  • Description is clear and includes keywords for agent discovery
  • Code examples are syntactically correct
  • All internal links are valid relative paths

Key InsForge Patterns

When working with InsForge skills, remember:

  1. Backend First: Most features require backend configuration before SDK integration
  2. Metadata Endpoint: Always fetch /api/metadata before making changes
  3. Auth References: Use auth.users(id) for user foreign keys, auth.uid() in RLS policies
  4. Auth Profile Metadata: auth.users.profile is JSONB; read profile->>'name' / profile->>'avatar_url' in triggers.
  5. Array Inserts: Database inserts require array format: insert([{...}])
  6. Storage Keys: Save both url and key for storage operations

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.