mtk-agent-toolkit: Skill for Claude Code

.claude/skills/toolkit-health/SKILL.md

toolkit-health is a skill for Claude Code from moberghr/mtk-agent-toolkit. It costs 40 tokens per session (1,961 once invoked), scanned B, original, MIT.

A read-only report of how the MTK toolkit is being used, based on saved analytics and project files. MTK is a set of coding workflows and supporting tools.

In plain words
What is it for?
Use it to review toolkit adoption, inspect usage statistics, count specifications and lessons, and decide whether a lesson reflects enough real usage to become a project rule.
Why use it?
It helps identify unusual usage patterns or missing workflow records without changing the project.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions CLAUDE.md.

This is moberghr/mtk-agent-toolkit's own configuration. It tells Claude Code how to work on mtk-agent-toolkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mtk-agent-toolkit configures →

Part of the mtk plugin — 45 skills, 6 agents, 7 hooks, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to moberghr/mtk-agent-toolkit. 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/moberghr/mtk-agent-toolkit/main/.claude/skills/toolkit-health/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/moberghr/mtk-agent-toolkit

Made for: Claude Code.

Or install mtk, the plugin that ships this one along with the rest of its 45 skills, 6 agents, 7 hooks, 1 MCP server.

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 toolkit-health

README.md
[![agentmods](https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/toolkit-health/github.svg)](https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/toolkit-health)
Your own site
<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/toolkit-health"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/toolkit-health/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 toolkit-health

Your own site · 80×15
<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/toolkit-health"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/toolkit-health.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,961 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00040 $0.01961
Opus 5 $0.00020 $0.00981
Sonnet 5 $0.00008 $0.00392
Haiku 4.5 $0.00004 $0.00196

Measured yesterday against content hash 69a6b40102fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

toolkit-health scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

if [ -f .claude/analytics.json ]; then cat .claude/analytics.json; else echo "(not yet created — needs at least one non-trivial session)"; fi
.claude/skills/toolkit-health/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Toolkit Health

Current Analytics Snapshot

echo "--- Analytics file ---"
if [ -f .claude/analytics.json ]; then cat .claude/analytics.json; else echo "(not yet created — needs at least one non-trivial session)"; fi
echo "--- Specs on disk ---"
if [ -d docs/specs ]; then find docs/specs -name '*.md' 2>/dev/null | wc -l | tr -d ' '; else echo "0"; fi
echo "--- Lessons captured ---"
if [ -f tasks/lessons.md ]; then grep -c '^## ' tasks/lessons.md 2>/dev/null || echo "0"; else echo "0 (file missing)"; fi

Overview

hooks/session-analytics.sh persists session stats to .claude/analytics.json. This skill reads that file plus on-disk artifacts (specs, lessons, MTK-related commits) and produces a human-readable health report with anomaly flags and suggested actions. Treat the analytics as an operational pulse, not a formal KPI dashboard: some counters are activity metrics, others are lightweight workflow signals. Read-only — never mutates state.

When To Use

  • Engineer asks "how are we using MTK?" / "toolkit health" / "usage stats"
  • Periodic team review of adoption (weekly/monthly retro)
  • Before promoting a lesson to a CLAUDE.md rule — sanity-check that it reflects real usage
  • After a big change to skill routing, to see whether the new routes are firing

When NOT To Use

  • As part of a regular build/test loop (this is a diagnostic, not a gate)
  • When .claude/analytics.json has fewer than 3 sessions — not enough data
  • As a substitute for /mtk status / context-report (that skill reports current config, this skill reports historical usage)

Workflow

  1. Load the data sources in parallel (independent reads — see docs/parallelism-patterns.md):
    • .claude/analytics.json (session counts, ops, mods, specs_created, lessons_captured, scope_guard_warnings, benchmarks_run, benchmark_last_score)
    • tasks/lessons.md if present (count ^## entries)
    • docs/specs/ and docs/plans/ directory listings
    • git log --since="30 days ago" --oneline --grep='mtk\|MTK\|toolkit' for MTK-related commits

Read the full file on GitHub · 129 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 69a6b40102fe
  2. 10d ago First seen · 129 lines · 40 tokens per session scan B a54b19677788

Subscribe to this mod's changes

toolkit-health is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (7 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,961 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens