Tool-Catalog-Compiler AGENTS.md

Tool-Catalog-Compiler AGENTS.md is an instructions file for Codex, OpenCode from aak204/Tool-Catalog-Compiler. It costs 342 tokens per session, scanned A, original, MIT.

Contributor instructions for Tool Catalog Compiler, a project that turns different tool descriptions into one shared format and makes them discoverable through a gateway.

In plain words
What is it for?
Use them when changing importers, the shared internal format, compiler passes, gateway code, benchmarks, or validation scripts.
Why use it?
They keep imports, compiler results, tests, and builds consistent across Windows and other development environments.

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/aak204/tool-catalog-compiler/agents-md
Clone the repo
git clone --depth 1 https://github.com/aak204/Tool-Catalog-Compiler

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for Tool-Catalog-Compiler AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aak204/tool-catalog-compiler/agents-md.svg)](https://agentmods.dev/instructions/aak204/tool-catalog-compiler/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/aak204/tool-catalog-compiler/agents-md"><img src="https://agentmods.dev/badge/instructions/aak204/tool-catalog-compiler/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 342 This file is loaded in full into every session.
When invoked 342 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 $0.00342 $0.00342
Opus 5 $0.00171 $0.00171
Sonnet 5 $0.00068 $0.00068
Haiku 4.5 $0.00034 $0.00034

Measured 4d ago against content hash 86e9e14ec0d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Tool-Catalog-Compiler 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 4d 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.

AGENTS.md · 46 lines

What it actually says

AGENTS.md

Purpose

This repository builds toolc: a Tool Catalog Compiler + Gateway centered on a single IR and a pass-based compiler.

Working Rules

  • Keep Windows 11 + PowerShell as the primary contributor workflow.
  • Do not make Bash-only tooling mandatory.
  • Prefer standard library solutions unless a real requirement justifies another dependency.
  • Keep the IR in internal/ir as the system of record.
  • Importers must translate provider-native inputs into IR before compiler logic runs.
  • Compiler behavior should remain deterministic and testable.
  • Gateway changes should keep startup/build/test loops fast and local.
  • Benchmark code belongs in internal/bench, not mixed into runtime paths.

Validation Loop

Before considering work complete, run:

./scripts/check.ps1

If only a subset changed, at minimum run the affected package tests plus:

./scripts/build.ps1

Current MVP Boundaries

  • function importer works for raw YAML/JSON tool lists and catalog-like inputs
  • openapi importer covers a practical OAS3 subset, not the full spec
  • mcp importer currently consumes MCP-like manifests/tool metadata, not live wire sessions
  • gateway supports discovery/schema/invoke HTTP flows, but invocation is still backed by a mock adapter
  • model config is loaded now for later OpenAI-compatible execution work

Change Guidance

  • Preserve honest documentation. Do not imply provider/runtime support that does not exist.
  • Prefer adding tests with new compiler/importer behavior.
  • Keep scripts reproducible and CI-friendly.
  • Update docs/architecture.md when changing architectural boundaries.
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. 4d ago First seen · 46 lines · 342 tokens per session scan A 86e9e14ec0d4

Subscribe to this mod's changes

Tool-Catalog-Compiler AGENTS.md is an instructions file published in the GitHub repository aak204/Tool-Catalog-Compiler (20 stars, last pushed 4mo ago), licensed MIT. It adds 342 tokens to every session, about $0.0017 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.