What is agentskit-registry AGENTS.md?

Repository instructions for a registry that publishes ready-to-use AI agents and their metadata, validation evidence, and installation bundles. It also defines a documentation bridge for searching and retrieving agent documentation.

Use it when editing registry agents, documentation, validation evidence, generated artifacts, deterministic discovery data, or the documentation bridge.

It protects the boundary between the registry and the underlying AgentsKit runtime, while ensuring published claims and generated files come from approved sources.

agentskit-registry AGENTS.md — Instructions file for Codex and OpenCode by AgentsKit-io: Repository instructions for a registry that publish

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/agentskit-io/agentskit-registry/agents-md

Clone the repo

git clone --depth 1 https://github.com/AgentsKit-io/agentskit-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/agentskit-io/agentskit-registry/agents-md.svg)](https://agentmods.dev/instructions/agentskit-io/agentskit-registry/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/agentskit-io/agentskit-registry/agents-md"><img src="https://agentmods.dev/badge/instructions/agentskit-io/agentskit-registry/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 328 This file is loaded in full into every session.

When invoked 328 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.

Model	Per session	Once invoked
Fable 5	$0.00328	$0.00328
Opus 5	$0.00164	$0.00164
Sonnet 5	$0.00066	$0.00066
Haiku 4.5	$0.00033	$0.00033

Measured 4d ago against content hash 9facc0a12acb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentskit-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 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 · 33 lines

What it actually says

AGENTS.md

AgentsKit Registry owns source, metadata, validation evidence, install bundles, and deterministic discovery for ready-to-use AgentsKit agents. Read docs/for-agents/index.md before editing.

Non-negotiable boundaries

Never recreate AgentsKit runtime, adapter, tool, skill, memory, RAG, eval, or CLI behavior. Registry agents compose supported @agentskit/* releases.
Never recreate AgentsKit Chat protocols or fuzzy-match locally. Generate its published deterministic artifact and escalate semantic questions.
Files under public/r, public/deterministic, ecosystem-claims.json, and .doc-bridge are generated. Change their canonical source and rebuild.
Draft agents are not installable. Validated claims require public evidence.
Keep boundaries typed; no credentials, prompts, private reviewer output, or user queries may enter generated claims, artifacts, logs, or analytics.

doc-bridge

Route coding agents with @agentskit/doc-bridge (ak-docs).

npm run docs:bridge:index   # or pnpm
npx ak-docs query package <registry agent id> --agent
npx ak-docs gate run

MCP: ak-docs mcp → tools handoff.resolve, doc.search, doc.get.

Before shipping, run validate, lint, tests, eval replay, build, Doc Bridge, and confirm every committed generated artifact has no diff.

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.

4d ago First seen · 33 lines · 328 tokens per session scan A 9facc0a12acb

Subscribe to this mod's changes

agentskit-registry AGENTS.md is an instructions file published in the GitHub repository AgentsKit-io/agentskit-registry (5 stars, last pushed yesterday), licensed MIT. It adds 328 tokens to every session, about $0.0016 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.

Code Generation agent-framework agent-registry agentskit ai-agents ai-tools

agentskit-registry AGENTS.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

AGENTS.md

Non-negotiable boundaries

doc-bridge

What this file has done since we first saw it

Other instructions, from other repositories

vizra-adk CLAUDE.md

agentprodready AGENTS.md

initrunner CLAUDE.md

mcpforge AGENTS.md

synthorg CLAUDE.md

mcp-zero copilot-instructions.md