shared-skills-registry-access

shared-skills-registry-access is a skill for Claude Code, Codex from cobibean/shared-skills-registry-mcp. It costs 44 tokens per session (1,614 once invoked), scanned A, original, MIT.

A workflow for finding, reviewing, retrieving, and installing reusable instructions for coding agents from a shared registry. It keeps registry access separate from installing files in the agent’s own environment.

In plain words
What is it for?
Use it to search a shared skills registry, inspect skill bundles and their checksums, guide installation, and verify that the installed skill is available to the consuming agent.
Why use it?
It helps agents reuse existing skills instead of creating duplicates, and helps explain why a skill found in the registry may not appear locally.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to search a shared skills registry, inspect skill bundles and their checksums, guide installation, and verify that the installed skill is available to the consuming agent.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cobibean/shared-skills-registry-mcp/shared-skills-registry-access
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.

Any agent
npx skills add cobibean/shared-skills-registry-mcp --skill shared-skills-registry-access
Clone the repo
git clone --depth 1 https://github.com/cobibean/shared-skills-registry-mcp

Made for: Claude Code, Codex.

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 shared-skills-registry-access

README.md
[![agentmods](https://agentmods.dev/badge/skills/cobibean/shared-skills-registry-mcp/shared-skills-registry-access/github.svg)](https://agentmods.dev/skills/cobibean/shared-skills-registry-mcp/shared-skills-registry-access)
Your own site
<a href="https://agentmods.dev/skills/cobibean/shared-skills-registry-mcp/shared-skills-registry-access"><img src="https://agentmods.dev/badge/skills/cobibean/shared-skills-registry-mcp/shared-skills-registry-access/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.

agentmods 80×15 button for shared-skills-registry-access

Your own site · 80×15
<a href="https://agentmods.dev/skills/cobibean/shared-skills-registry-mcp/shared-skills-registry-access"><img src="https://agentmods.dev/badge/skills/cobibean/shared-skills-registry-mcp/shared-skills-registry-access.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,614 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.01614
Opus 5 $0.00022 $0.00807
Sonnet 5 $0.00009 $0.00323
Haiku 4.5 $0.00004 $0.00161

Measured 12d ago against content hash c67e9bcedd19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

shared-skills-registry-access 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 12d 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.

skills/shared-skills-registry-access/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shared Skills Registry Access

Overview

Use the configured Shared Skills Registry (SSR) as the first place to look for reusable procedural capability. Search before improvising a duplicate skill, inspect the selected bundle before installation, and verify installation in the consuming agent's own runtime.

This workflow is runtime-neutral. It applies to any MCP-compatible orchestrator or agent that exposes the standard SSR tools. The registry supplies metadata and checksum-bearing bundles; the caller-local adapter decides whether and where files are written.

When to Use

  • An agent needs a reusable capability that may already exist in its SSR.
  • An orchestrator is selecting capabilities for one or more workers.
  • A user asks to inspect, retrieve, or install a shared skill.
  • An install request succeeds at the registry layer but the skill is not visible locally.
  • A team wants to avoid maintaining divergent copies of the same skill.

Do not use SSR as an arbitrary code-execution channel. A skill may contain instructions or scripts, but retrieval and installation do not grant permission to execute them.

Standard SSR Tools

A compatible registry exposes these MCP operations:

  • list_shared_skills — browse visible entries, optionally by category.
  • search_shared_skills — find candidates from capability-oriented terms.
  • describe_shared_skill — inspect one entry's metadata and applicability.
  • retrieve_shared_skill — return SKILL.md and approved support files with checksums.
  • install_shared_skill — request a caller-local installation through the configured adapter.

Tool names may be namespaced by the MCP client. Use the locally registered equivalents when a client prefixes server names.

Consumer Agent Branch

Use this branch when installing a capability for the agent running the current task.

  1. Confirm SSR access. Verify the five standard tools are available through the configured MCP server.
  2. Search by capability. Use terms describing the missing work, not only a guessed skill name. Search multiple related terms when the first query is narrow.
  3. Describe before installing. Check applicability, lifecycle status, owner, source, category, install guidance, and whether the capability actually matches the task.
  4. Retrieve and inspect. Review the file list, SKILL.md, checksums, references, templates, scripts, and assets. Treat scripts as untrusted until reviewed.
  5. Install locally. Call install_shared_skill only after selecting the exact skill. Use the runtime's configured local skills root; never invent or override a destination outside that boundary.
  6. Verify runtime visibility. Confirm the installed SKILL.md exists in the expected local skill directory and start a fresh agent session or reload skills if the runtime caches discovery.
  7. Report exact state. Distinguish “found,” “retrieved,” “installation authorized,” “written locally,” and “visible to a fresh runtime.”

Read the full file on GitHub · 136 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. 12d ago First seen · 136 lines · 44 tokens per session scan A c67e9bcedd19

Subscribe to this mod's changes

shared-skills-registry-access is a skill published in the GitHub repository cobibean/shared-skills-registry-mcp (7 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 1,614 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens