skills-registry

skills-registry is a skill for Claude Code from dryvist/claude-code-plugins. It costs 19 tokens per session (1,391 once invoked), scanned A, original, Apache-2.0.

A registry for finding available coding-agent tools, skills, commands, and plugins, with notes about what each one does.

In plain words
What is it for?
Use it to discover installed add-ons, find the right command for a task, and check which plugin provides it.
Why use it?
It removes the need to search through separate configuration files or remember command names when looking for an existing capability.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the project-standards plugin — 4 skills shipped together

Good fit Use it to discover installed add-ons, find the right command for a task, and check which plugin provides it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dryvist/claude-code-plugins/skills-registry
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 dryvist/claude-code-plugins --skill skills-registry
Clone the repo
git clone --depth 1 https://github.com/dryvist/claude-code-plugins

Made for: Claude Code.

Or install project-standards, the plugin that ships this one along with the rest of its 4 skills.

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 skills-registry

README.md
[![agentmods](https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/skills-registry.svg)](https://agentmods.dev/skills/dryvist/claude-code-plugins/skills-registry)
Your own site
<a href="https://agentmods.dev/skills/dryvist/claude-code-plugins/skills-registry"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/skills-registry.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,391 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 $0.00019 $0.01391
Opus 5 $0.00010 $0.00696
Sonnet 5 $0.00004 $0.00278
Haiku 4.5 $0.00002 $0.00139

Measured yesterday against content hash 1e888ca3cd3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

skills-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 yesterday.

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.

project-standards/skills/skills-registry/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skills & Tools Registry

Plugin Slash Commands

Intent Command Plugin Notes
Sync branch with main /sync-main git-workflows Merge into current
Sync repo /refresh-repo git-workflows Also merges PRs
Prune dead branches, worktrees /prune-branches github-workflows Local and remote
Rebase + merge PR /rebase-pr git-workflows Local rebase-merge
Merge PR /merge-pr github-workflows Merge commit by default; --squash/-s to squash
Troubleshoot rebase /troubleshoot-rebase git-workflows Recover failures
Troubleshoot worktrees /troubleshoot-worktree git-workflows Fix refname
Troubleshoot pre-commit /troubleshoot-precommit git-workflows Fix hooks
Pre-commit architecture /pre-commit-architecture git-workflows Hook/config homes
Shared workflow org refs /shared-workflow-org-refs github-workflows Literal uses: owners
Nix tool policy /nix-tool-policy project-standards No ad-hoc installs
Manage your PR /finalize-pr github-workflows PR author flow (all/org for multi-repo)
Create GitHub issues /shape-issues github-workflows Shape Up method
Resolve PR threads /resolve-pr-threads github-workflows Thread resolution
Resolve CodeQL alerts /resolve-codeql codeql-resolver Fix alerts
Autonomous maintenance /auto-maintain ai-delegation Finds work
Delegate to AI models /delegate-to-ai ai-delegation External AI
Orchestrate premium agents /premium-agent-orchestration ai-delegation Preserve senior judgment
Offload to a local or cheap model /local-subagents ai-delegation Live model menu with speed/quality hints
Pick a hosted model, watch spend /openrouter-models ai-delegation Budget & egress
Sync permissions /sync-permissions config-management Merge perms
Add tool permissions /quick-add-permission config-management Quick allow
Orchestrate infra /orchestrate-infra infra-orchestration Cross-repo
Sync terraform inventory /sync-inventory infra-orchestration Outputs
E2E pipeline test /test-e2e infra-orchestration Full stack
Git workflow standards /git-workflow-standards git-standards Branches
PR & issue standards /pr-standards git-standards PR guards
Code quality /code-quality-standards code-standards Code rules
Code review /review-standards code-standards Review focus
Infrastructure /infrastructure-standards infra-standards IaC standards
Claude skill authoring /claude-skill-authoring project-standards Token budgets & placement
Workspace management /workspace-standards project-standards Multi-repo
This registry /skills-registry project-standards Tool lookup

Read the full file on GitHub · 90 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. yesterday Changed 1e888ca3cd3d
  2. 3d ago First seen · 90 lines · 19 tokens per session scan A 1c48aaaf92cf

Subscribe to this mod's changes

skills-registry is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 19 tokens to every session and 1,391 once invoked, about $0.0001 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 2026-09-04.