Skip to content
mcp/skillhub

Agent Skill

Health skill

healthtw93/Wazaplugins/waza/skills/health/SKILL.md

Audits agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks wrong. Not for application bugs or PR review.

7.3kMIT

always on

40 tokname + description

once used

4,337 tokSKILL.md body

bundled files

2014 scripts

repo stars

7.3kGitHub

Install the Health skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/tw93/Waza --skill health

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/tw93/Waza.git /tmp/Waza
mkdir -p ~/.claude/skills
cp -R /tmp/Waza/plugins/waza/skills/health ~/.claude/skills/health

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description40 tok
When the agent uses itThe SKILL.md instructions4,337 tok
Only if opened20 bundled files (286 KB)varies

Until it is used, health costs about 34× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 16 skills from tw93/Waza would load 658 tokens of descriptions. Skills vs MCP study

Checks

  • Ships scripts the agent can run. Read them before installing.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Health: Agent-Assisted Engineering Health
  • Outcome Contract
  • Durable Context Preflight
  • Hard Rules
  • Step 0: Establish the evidence basis
  • Step 1: Collect data
  • Step 1b: Runtime Inventory and MCP Check
  • Step 1c: Safety and security checks
  • Security Baseline Checks
  • Memory and Skill Supply Chain
  • Long-Running Agent Stop Conditions
  • Step 2: Analyze
  • Gotchas
  • Output
  • [PASS] Passing checks (table, max 5 rows)
  • Finding format
  • [!] Critical -- fix now
  • [~] Structural -- fix soon
  • [-] Incremental -- nice to have

More skills from tw93/Waza

All skills in this repo
  1. checktw93/Waza

    Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.

    7.3k341 tok idle · 5,322 in use
  2. hunttw93/Waza

    Finds root cause before any fix. Use when something errors, crashes, regresses, or used to work. Not for code review or new features.

    7.3k32 tok idle · 3,552 in use
  3. learntw93/Waza

    Runs a six-phase research workflow from source bundle to publish-ready output. Use when researching an unfamiliar domain or compiling materials into one reference. Not for quick lookups or single-file reads.

    7.3k39 tok idle · 1,747 in use
  4. readtw93/Waza

    Fetches URLs and PDFs, then summarizes or returns clean Markdown; can also search the web through DeepSeek when built-in search is thin. Use when asked to read, fetch, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.

    7.3k561 tok idle · 1,644 in use
  5. thinktw93/Waza

    Turns rough ideas into approved, decision-complete plans before coding. Use when planning architecture, judging whether to build, or writing a handoff. Not for bug fixes or small edits.

    7.3k39 tok idle · 2,356 in use
  6. uitw93/Waza

    Produces distinctive production UI and screenshot-grounded visual polish. Use when building or restyling pages, components, or typography. Not for backend logic or data pipelines.

    7.3k36 tok idle · 2,959 in use
  7. writetw93/Waza

    Rewrites and polishes Chinese or English prose, technical instructions, and product copy. Use when drafting, editing, localizing, or cutting AI tone. Not for code comments or commit messages.

    7.3k241 tok idle · 3,073 in use