ai-capability-registry AGENTS.md

ai-capability-registry AGENTS.md is an instructions file for Codex, OpenCode from Friz-zy/ai-capability-registry. It costs 758 tokens per session, scanned A, original, MIT.

Repository instructions for an AI capability registry, which is a catalogue of available AI tools and workflows. They tell the coding agent how to load the registry and choose a workflow.

In plain words
What is it for?
Following registry startup, routing work to a matching workflow, and applying code-writing rules for the ai-capability-registry project.
Why use it?
They prevent the agent from acting before checking the registry's shared rules and source of truth. This reduces missed instructions and incorrect workflow choices.

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/friz-zy/ai-capability-registry/agents-md
Clone the repo
git clone --depth 1 https://github.com/Friz-zy/ai-capability-registry

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 ai-capability-registry AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/friz-zy/ai-capability-registry/agents-md.svg)](https://agentmods.dev/instructions/friz-zy/ai-capability-registry/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/friz-zy/ai-capability-registry/agents-md"><img src="https://agentmods.dev/badge/instructions/friz-zy/ai-capability-registry/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 758 This file is loaded in full into every session.
When invoked 758 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 5.1 $0.00758 $0.00758
Opus 5 $0.00379 $0.00379
Sonnet 5 $0.00152 $0.00152
Haiku 4.5 $0.00076 $0.00076

Measured 5d ago against content hash 1b42aa6f76fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ai-capability-registry 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 5d 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Before resolving ~/ or $HOME and read files, discover the actual home directory from the environment instead of assuming /root/ as home dir.

Follow these instructions if you are the user-facing Primary Agent

You MUST read and apply the shared workflow runtime instructions listed below before acting:

  1. ~/.ai-registry/workflows/workflow.md

Then perform workflow capability routing before acting:

  • Decide whether a workflow applies.
  • If a workflow applies, follow the selected workflow.
  • If no workflow applies, explicitly use the no-workflow fallback from ~/.ai-registry/workflows/workflow.md.

For trivial conversational requests, still obey the registry files, but no workflow delegation is required unless the routing instructions require it.

Mandatory Registry Bootstrap

Before any substantive response, tool use, planning, analysis, implementation, review, or command execution, read and apply the shared registry runtime files listed below in order:

  1. ~/.ai-registry/capability-routing.md
  2. ~/.ai-registry/skills/skills.md

This bootstrap is mandatory when these files are listed. Do not rely on memory, prior summaries, or assumptions about their contents.

After reading them, perform skill capability routing before acting:

  • Select skills only according to ~/.ai-registry/skills/skills.md.
  • Do not dynamically route to MCP servers unless local instructions separately enable MCP routing.

Local repository instructions override shared registry guidance when more specific. These shared registry files are the source of truth. Do not replace them with summaries or assumptions. If ~/.ai-registry is unavailable, state that and continue with local instructions only.

Common Rules

  • After any planning or brainstorming phase, before you actually start making changes to the files, show me your work plan and ask for my opinion.
  • All code, comments, docstrings, and documentation must be in English. When talking to me, use the same language I do.
  • Use descriptive, meaningful full names for variables, parameters, classes, etc. Avoid abbreviations and short names.
  • Provide explanatory comments in code.
  • All functions, classes, high-level objects: docstrings in Google format.
  • Do not change the formatting in the files or make cosmetic edits unless I have specifically asked you to do so.

Read the full file on GitHub · 59 lines

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. 5d ago First seen · 59 lines · 758 tokens per session scan A 1b42aa6f76fd

Subscribe to this mod's changes

ai-capability-registry AGENTS.md is an instructions file published in the GitHub repository Friz-zy/ai-capability-registry (9 stars, last pushed 5d ago), licensed MIT. It adds 758 tokens to every session, about $0.0038 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.