agentify AGENTS.md

Development instructions for Agentify, a TypeScript command-line tool that converts OpenAPI specifications into formats for coding agents. Its architecture separates parsing, output generation, security scanning, shared data types, and the command-line interface.

In plain words
What is it for?
Use it to install, build, run, test, lint, and extend Agentify, including adding generators for new agent-facing formats.
Why use it?
It gives contributors consistent build, run, coding, security, and testing rules. The sanitizer and security scanner help control what enters and leaves generated code.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/monadworks/agentify/agents-md
Clone the repo
git clone --depth 1 https://github.com/MonadWorks/agentify

Made for: Codex, OpenCode.

Per session 371 This file is loaded in full into every session.
When invoked 371 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00371 $0.00371
Opus 5 $0.00186 $0.00186
Sonnet 5 $0.00074 $0.00074
Haiku 4.5 $0.00037 $0.00037

Measured 2d ago against content hash 6bb2965e72bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentify AGENTS.md 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 45 lines

What it actually says

AGENTS.md

Agentify is an Agent Interface Compiler that transforms OpenAPI specifications into multiple agent-consumable formats (MCP Server, Skills, CLAUDE.md, .cursorrules, AGENTS.md, llms.txt, A2A Card).

Build & Run

npm install
npm run build        # Build with tsup
npm run dev          # Dev mode with tsx
npm test             # Run tests with Vitest
npm run lint         # TypeScript type check

Architecture

  • Parser (src/parser/): OpenAPI spec parsing + input sanitization
  • Generator (src/generator/): Pluggable emitters for each output format
  • Security (src/security/): Generated code scanning for dangerous patterns
  • IR (src/types.ts): Canonical intermediate representation (AgentifyIR)
  • CLI (src/cli.ts): Commander.js CLI entry point

Code Conventions

  • TypeScript strict mode (all strict flags enabled)
  • Immutable data patterns — never mutate objects, always spread
  • Small files: 200-400 lines typical, 800 max
  • Emitter interface: implement emit(ir, options) => EmitterResult
  • All OpenAPI spec fields must pass through sanitizer before use
  • Generated code must pass security scanner before output

Testing

  • Framework: Vitest
  • Coverage target: 80%+
  • Test files: test/*.test.ts
  • Integration tests use live Petstore API

Security

  • Input sanitization blocks: eval, exec, Function constructor, require/import in descriptions
  • Handlebars template injection prevention
  • Prompt injection pattern detection
  • Generated code scanner checks for critical patterns before writing files
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.

  1. 2d ago First seen · 45 lines · 371 tokens per session scan A 6bb2965e72bb

Subscribe to this mod's changes

agentify AGENTS.md is an instructions file published in the GitHub repository MonadWorks/agentify (37 stars, last pushed 5mo ago), licensed MIT. It adds 371 tokens to every session, about $0.0019 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 2026-08-30.