registry

A command-line role registry for finding, installing, inspecting, updating, and removing reusable agent roles from InitHub or OCI registries. Installed roles are checked and saved for use by InitRunner.

In plain words
What is it for?
Use it to discover roles, install shared role packages, inspect their details, update them, or uninstall them.
Why use it?
It removes the need to download and manage agent roles manually. You can use a specific role version or search for roles by topic.

Agent

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 agents/vladkesler/initrunner/registry
Clone the repo
git clone --depth 1 https://github.com/vladkesler/initrunner
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,982 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.02982
Opus 5 $0.00000 $0.01491
Sonnet 5 $0.00000 $0.00596
Haiku 4.5 $0.00000 $0.00298

Measured 2d ago against content hash 9c83737a3c53, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

registry 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 2d 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.

docs/agents/registry.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role Registry

InitRunner's role registry lets you install, share, and discover roles from InitHub and OCI registries. Roles are downloaded, validated, and saved to ~/.initrunner/roles/ where they integrate automatically with the CLI.

Quick Start

# Install from InitHub
initrunner install owner/agent-pack
initrunner install owner/[email protected]

# Install from an OCI registry
initrunner install oci://ghcr.io/user/my-role:latest

# Inspect a role (works with all source types)
initrunner info owner/agent-pack
initrunner info oci://ghcr.io/user/my-role:latest

# Search InitHub
initrunner search "code review"

# List / update / remove
initrunner list
initrunner update code-reviewer
initrunner update --all
initrunner uninstall code-reviewer

Source Identifiers

The install and info commands accept flexible source identifiers:

Format Example Description
owner/name alice/code-reviewer Installs from InitHub (latest version)
owner/name@ver alice/[email protected] Installs a specific version from InitHub
hub:owner/name hub:alice/code-reviewer InitHub (backward compatibility alias)
hub:owner/name@ver hub:alice/[email protected] InitHub pinned version (backward compatibility alias)
oci://reg/repo:tag oci://ghcr.io/user/role:latest Pulls an OCI bundle
bare-name code-reviewer Error with a search hint: "Did you mean to search? Try: initrunner search code-reviewer"

Detection order: oci:// prefix selects OCI, hub: prefix or owner/name format selects InitHub, and bare names without a / produce an error with a search suggestion.

Install Flow

When you run initrunner install, the following happens:

  1. Parse the source identifier into owner, name, and optional version.
  2. Resolve the package on InitHub, selecting the requested version or latest.
  3. Download the bundle archive from InitHub.
  4. Extract the role YAML and any bundled assets from the archive.
  5. Validate the file as a valid InitRunner role definition (reuses the same validation as initrunner validate).
  6. Check dependencies declared in the role's top-level dependencies list and warn about any that are missing.
  7. Display a security summary showing the role name, description, tools, model provider, and other features. Prompt for confirmation.
  8. Save the role to ~/.initrunner/roles/{owner}__{name}.yaml.
  9. Record the installation in ~/.initrunner/roles/registry.json with source, version, and content hash.

Read the full file on GitHub · 349 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. 2d ago First seen · 349 lines · 0 tokens per session scan A 9c83737a3c53

Subscribe to this mod's changes

registry is an agent published in the GitHub repository vladkesler/initrunner (41 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,982 tokens. 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.

Related

Other agents, from other repositories

unittest-generator

Use this agent when you need to create unit tests for your code in unittest.TestCase format, organized in a tests folder with concept-based subfolders. Examples: Context: User has just written a new authentication module and needs comprehensive unit tests. user: 'I just finished writing my user authentication…

Upsonic/Upsonic · 0 tokens

harness-radar

Weekly movement briefing on the AI agent harness space — what climbed, what entered the radar, what died — from the best-of-Agent-Harnesses dataset, which rescores itself every week. Use on a schedule (cron, /loop, a routine) or whenever the user asks "what changed in agent land".

RyanAlberts/best-of-Agent-Harnesses · 68 tokens

ecosystem-doc-bridge-corpus-scanner

Status: human guide. Owner: Emerson Braun. Reviewed: 2026-08-14.

AgentsKit-io/agentskit-registry · 0 tokens

ecosystem-registry-eval-author

Status: human guide. Owner: Emerson Braun. Reviewed: 2026-08-14.

AgentsKit-io/agentskit-registry · 0 tokens

content-newsletter-author

Status: human guide. Owner: Emerson Braun. Reviewed: 2026-08-14.

AgentsKit-io/agentskit-registry · 0 tokens

application-patterns-wave-06

Wave 06 adds practical workflows for agency operations, clinical drafting, privacy, content, data, infrastructure, education, commerce, finance, people, insurance, legal review, operations, product, research, and security. Every pattern below uses synthetic input and is a starting point for inspection, not evidence of…

AgentsKit-io/agentskit-registry · 0 tokens