What is SKILLS_INDEX?

A central catalogue of available skills, grouped by the stage of work they support.

Browse skills for tasks such as understanding a project, planning, creating teams, managing worktrees, and continuing sessions.

It gives agents one place to find and organize skills instead of searching through separate lists.

SKILLS_INDEX — Agent for Claude Code by ngocsangyem/MeowKit

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.

Clone the repo

git clone --depth 1 https://github.com/ngocsangyem/MeowKit

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/ngocsangyem/meowkit/skills_index/github.svg)](https://agentmods.dev/agents/ngocsangyem/meowkit/skills_index)

Your own site

<a href="https://agentmods.dev/agents/ngocsangyem/meowkit/skills_index"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/skills_index/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/ngocsangyem/meowkit/skills_index"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/skills_index.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

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 4,528 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	$0.00000	$0.04528
Opus 5.5	$0.00000	$0.01811
Sonnet 5.5	$0.00000	$0.00906
Haiku 4.5	$0.00000	$0.00453

Measured 2mo ago against content hash 54180e4ae073, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

SKILLS_INDEX 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.

.claude/agents/SKILLS_INDEX.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

the toolkit Skills Index

Centralized registry of all skills. Updated: 2026-07-03 (v2.13.2).

By Phase

Phase 0 — Orient

[13]{skill,owner,type,architecture}
`mk:agent-detector`|orchestrator|utility|monolithic
`mk:help`|orchestrator|utility|monolithic
`mk:lazy-agent-loader`|orchestrator|utility|monolithic
`mk:project-context`|orchestrator|utility|monolithic
`mk:scale-routing`|orchestrator|utility|monolithic
`mk:scout`|orchestrator|cross-cutting|monolithic
`mk:session-continuation`|orchestrator|cross-cutting|monolithic
`mk:task-queue`|orchestrator|utility|monolithic
`mk:team-config`|orchestrator|utility|monolithic
`mk:workflow-orchestrator`|orchestrator|cross-cutting|monolithic
`mk:memory`|analyst|memory|monolithic
`mk:skill-creator`|orchestrator|utility|monolithic
`mk:worktree`|orchestrator|utility|script-backed (v2.9.5: Node.js CLI `scripts/worktree.cjs`; 6 commands: create/merge/cleanup/list/status/prune; `--orchestrated` flag for parallel agent isolation; `--json` + `--dry-run` on all commands)

Phase 1 — Plan

[9]{skill,owner,type,architecture}
`mk:plan-creator`|planner|planning|step-file (v1.5.0: scope challenge, multi-file output, plan red team, sync-back, **--product-level mode** for green-field app builds via step-03a; **--deep mode** for per-phase scouting; **--tdd flag** injects TDD sections into phase files; **standalone subcommands**: archive/red-team/validate; outputs `red-team-findings.md`; solution design checklist in each phase; memory capture at Gate 1)
`mk:plan-ceo-review`|planner|planning|monolithic (v2.0: layered verification pipeline — pre-screen + two-lens eval + severity tiers + adversarial necessity + append-only verdict)
`mk:validate-plan`|planner|planning|monolithic
`mk:brainstorming`|brainstormer|planning|monolithic
`mk:office-hours`|brainstormer/planner|planning|monolithic
`mk:grill`|brainstormer|planning|monolithic (one-question-at-a-time interview of the user's plan/design; checkpoints to `docs/knowledge/<slug>.md`; read-only on source; hands off to skill-creator/plan-creator/project-context)
`mk:party`|orchestrator/brainstormer|planning|monolithic
`mk:advise`|advisor|planning|monolithic (interview one question at a time → user confirms a reframing of their problem → ONE verdict packet; never a plan/ADR/verdict; isolated advisor by default, disclosed inline fallback)
`mk:planning-engine`|planner|planning|monolithic

Read the full file on GitHub · 267 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 · 267 lines · 0 tokens per session scan A 54180e4ae073

Subscribe to this mod's changes

SKILLS_INDEX is an agent published in the GitHub repository ngocsangyem/MeowKit (15 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,528 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.

Building agents Claude Code ai ai-agents automation claude claude-skills

SKILLS_INDEX next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
SKILLS_INDEXngocsangyem/MeowKit	Agent	15	6d ago	MIT	A	0	Claude Code
ecto-schema-designeroliver-kriska/claude-elixir-phoenix	Agent	573	yesterday	MIT	A	30	Claude Code
frontend-devvibeeval/vibecosystem	Agent	539	2d ago	MIT	A	22	Claude Code
trend-forecasterhoangsonww/Claude-Code-Agent-Monitor	Agent	1.2k	yesterday	MIT	A	82	Claude Code
corporate-strategycbrock84/headcount	Agent	2.6k	20d ago	MIT	A	33	Claude Code
demand-generationcbrock84/headcount	Agent	2.6k	20d ago	MIT	A	30	Claude Code
plinth-architectjabrena/plinth	Agent	461	yesterday	Apache-2.0	A	38	Claude Code, Cursor