What is RegistryManager?

An agent that maintains a JSONL file, where each line is a separate JSON record, containing information about installed skills.

Use it to manage .github/skills/registry.jsonl, including skill names, descriptions, paths, installation dates, versions, sources, and tags.

It gives a consistent place to add, change, remove, search, and list skill records without manually editing the registry.

How shyamsridhar123/Skills-Registry-CLI configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to shyamsridhar123/Skills-Registry-CLI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/shyamsridhar123/Skills-Registry-CLI/main/.github/agents/registry-manager.agent.md

Clone the repo

git clone --depth 1 https://github.com/shyamsridhar123/Skills-Registry-CLI

Made for: Claude Code.

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/agents/shyamsridhar123/skills-registry-cli/registry-manager/github.svg)](https://agentmods.dev/agents/shyamsridhar123/skills-registry-cli/registry-manager)

Your own site

<a href="https://agentmods.dev/agents/shyamsridhar123/skills-registry-cli/registry-manager"><img src="https://agentmods.dev/badge/agents/shyamsridhar123/skills-registry-cli/registry-manager/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/shyamsridhar123/skills-registry-cli/registry-manager"><img src="https://agentmods.dev/badge/agents/shyamsridhar123/skills-registry-cli/registry-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 936 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00027	$0.00936
Opus 5.5	$0.00011	$0.00374
Sonnet 5.5	$0.00005	$0.00187
Haiku 4.5	$0.00003	$0.00094

Measured 2mo ago against content hash e998ffa15a69, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

RegistryManager 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 2mo 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.

.github/agents/registry-manager.agent.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Registry Manager Agent

You are a specialized agent for managing the skill registry in JSONL format.

Primary Responsibilities

Registry Creation and Maintenance
- Create and maintain .github/skills/registry.jsonl
- Each line is a valid JSON object representing one skill
- Support atomic updates and queries
Registry Operations
- ADD: Add new skills to the registry
- REMOVE: Remove skills from the registry
- UPDATE: Update skill metadata
- QUERY: Search and filter skills
- LIST: Display all registered skills

Registry File Format

Location: .github/skills/registry.jsonl

JSONL Entry Schema

Each line in the registry is a JSON object:

{"name": "skill-name", "description": "Skill description", "source": "anthropics/skills", "path": ".github/skills/skill-name", "installed_at": "2026-01-20T00:00:00Z", "version": "1.0.0", "tags": ["category1", "category2"]}

Required Fields

name: Skill identifier (string, lowercase with hyphens)
description: What the skill does (string, max 1024 chars)
path: Local path to skill directory (string)
installed_at: ISO 8601 timestamp (string)

Optional Fields

source: Source repository (string)
version: Skill version (string)
tags: Categories/tags for filtering (array of strings)
author: Skill author (string)
license: License type (string)

Registry Operations

Add Skill to Registry

# Read skill metadata
# Append JSONL entry to registry.jsonl

Example entry:

{"name": "skill-creator", "description": "Guide for creating effective skills", "source": "anthropics/skills", "path": ".github/skills/skill-creator", "installed_at": "2026-01-20T10:30:00Z", "tags": ["meta", "development"]}

Remove Skill from Registry

Read registry.jsonl
Filter out the skill entry
Write back remaining entries

Query Skills

Support queries by:

Name (exact or partial match)
Tags (contains any/all)
Source repository
Date range

Read the full file on GitHub · 143 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.

2mo ago First seen · 143 lines · 27 tokens per session scan A e998ffa15a69

Subscribe to this mod's changes

RegistryManager is an agent published in the GitHub repository shyamsridhar123/Skills-Registry-CLI (3 stars, last pushed 9mo ago), licensed MIT. It adds 27 tokens to every session and 936 once invoked, about $0.0001 per session on Opus 5.5. 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.

Building agents ai-agents cli developer-tools javascript skills-management

RegistryManager next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
RegistryManagershyamsridhar123/Skills-Registry-CLI	Agent	3	9mo ago	MIT	A	27	Claude Code
docs-specialistZaxbyHub/opencode-swarm	Agent	518	yesterday	MIT	A	34	Claude Code
atomic-auditordamusix/atomic-claude	Agent	115	5d ago	MIT	A	169	Claude Code
seo-meta-optimizerechoVic/blade-code	Agent	181	24d ago	MIT	A	39	Claude Code
python-proechoVic/blade-code	Agent	181	24d ago	MIT	A	51	Claude Code
scramjet:instruction-semantics-analyzerLeanAndMean/scramjet	Agent	8	4d ago	Apache-2.0	A	35	Claude Code
fe-reviewerEffulgent-Point/paw	Agent	2	2mo ago	MIT	A	27	Claude Code

Skills-Registry-CLI: Agent for Claude Code