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/friz-zy/ai-capability-registry/agents-mdgit clone --depth 1 https://github.com/Friz-zy/ai-capability-registryWrote 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/friz-zy/ai-capability-registry/agents-md)<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>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 5.1 | $0.00758 | $0.00758 |
| Opus 5 | $0.00379 | $0.00379 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
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.
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:
~/.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:
~/.ai-registry/capability-routing.md~/.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.
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.
- 5d ago First seen · 59 lines · 758 tokens per session scan A 1b42aa6f76fd
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.
Other instructions, from other repositories
n8n-skills CLAUDE.md
Claude Code instructions for czlonkowski/n8n-skills, covering claude.md, project overview, repository structure, the 14 skills and 1. n8n expression syntax.
workflows-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/workflows-mcp-server, covering agent protocol, what's next?, core rules, patterns and tool.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.