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.
npx agentmods add instructions/aak204/tool-catalog-compiler/agents-mdgit clone --depth 1 https://github.com/aak204/Tool-Catalog-CompilerWrote 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/instructions/aak204/tool-catalog-compiler/agents-md)<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>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 | $0.00342 | $0.00342 |
| Opus 5 | $0.00171 | $0.00171 |
| Sonnet 5 | $0.00068 | $0.00068 |
| Haiku 4.5 | $0.00034 | $0.00034 |
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.
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/iras 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
functionimporter works for raw YAML/JSON tool lists and catalog-like inputsopenapiimporter covers a practical OAS3 subset, not the full specmcpimporter 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.mdwhen changing architectural boundaries.
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.
- 4d ago First seen · 46 lines · 342 tokens per session scan A 86e9e14ec0d4
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.
Other instructions, from other repositories
ollama CLAUDE.md
Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.
gorest AGENTS.md
AGENTS.md instructions for pilinux/gorest, covering agents.md, project overview, build and run commands, build and tidy dependencies.
chatgpt-cli CLAUDE.md
Claude Code instructions for kardolus/chatgpt-cli, covering chatgpt-cli — release runbook, prerequisites, 1. cut the release, 2. publish the github release + binaries and 3. update the homebrew tap.
kessoku AGENTS.md
AGENTS.md instructions for mazrean/kessoku, covering repository guidelines — kessoku, project structure, common commands, build and test.
Sighthound AGENTS.md
Instructions for Corgea/Sighthound, covering claude, commands, python / django test naming and agent skill.