health SKILL.md skillA

health from tw93/waza is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add tw93/waza/health@git:20261015.c8985bb

Pins git:20261015.c8985bb in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
tw93/waza
Path
plugins/waza/skills/health/SKILL.md
Versions recorded
5
Latest version
git:20261015.c8985bb, committed Oct 15, 2026
First version recorded
Oct 7, 2026
Size
21,233 bytes
Repository stars
7,489
License
MIT

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.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Health: Agent-Assisted Engineering Health

Prefix your first line with 🥷 inline, not as its own paragraph.

Audit the current project's agent setup and AI coding maintainability against this framework:
`agent config → instruction surfaces → tools/runtime → verifiers → maintainability`

Find violations. Identify the misaligned layer. Calibrate to evidence and risk, not repository size.

## Outcome Contract

- Outcome: a budget-aware health report that separates agent configuration risk from AI maintainability risk.
- Done when: each finding names the misaligned layer, the concrete evidence, and a copy-pasteable action or diagnostic command.
- Evidence: collected health script output, tracked project instructions, runtime config summaries, verifier logs, hooks/MCP surfaces, and read-only live probes when needed.
- Output: prioritized findings with status, impact, and next action, or a clear clean bill with residual risk.

Two lanes share one report:

- **Agent config health**: Codex/Claude/Pi instruction drift, permissions, hooks, MCP, skills, and memory supply chain.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add tw93/waza/health@sha256:690e3b44f71deaa9

The line at the top of this page pins the label git:20261015.c8985bb, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_3csmkhtvjh64pxra.svg)](https://markdownregistry.com/a/art_3csmkhtvjh64pxra)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Oct 7, 2026 and Oct 15, 2026, about one every 2 days.

versioncommittedcommitsizeaudit
git:20261015.c8985bb latest2026-10-15 c8985bb 21,233 BA view · diff
git:20261010.1afbd222026-10-10 1afbd22 21,060 BA view · diff
git:20261010.57976f02026-10-10 57976f0 21,042 BA view · diff
git:20261007.6b6c7362026-10-07 6b6c736 21,054 BA view · diff
git:20261007.7dfb9e52026-10-07 7dfb9e5 20,954 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (21233 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

tw93/waza · 7,489 stars · license MIT · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_3csmkhtvjh64pxra
GET https://markdownregistry.com/api/v1/resolve?ref=tw93/waza/health
GET https://markdownregistry.com/api/v1/blob/690e3b44f71deaa9b45baf67adaac40efc3e4e2278b89ed6bf2db4624d5bec4e

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from tw93/waza

AGENTS.md AGENTS.md file
tw93/waza · AGENTS.md
git:20261029.6f2bd24 · audit A · 7,489 stars
llms.txt llms.txt file
tw93/waza · llms.txt
git:20260907.2ae9e48 · audit A · 7,489 stars
check SKILL.md skill
tw93/waza · plugins/waza/skills/check/SKILL.md · Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs…
git:20261028.7703a48 · audit A · 7,489 stars
hunt SKILL.md skill
tw93/waza · plugins/waza/skills/hunt/SKILL.md · Finds root cause before any fix. Use when something errors, crashes, regresses, or used to work. Not for code review or…
git:20260925.c3b74dd · audit A · 7,489 stars
learn SKILL.md skill
tw93/waza · plugins/waza/skills/learn/SKILL.md · Runs a six-phase research workflow from source bundle to publish-ready output. Use when researching an unfamiliar…
git:20261006.6d988e2 · audit A · 7,489 stars
read SKILL.md skill
tw93/waza · plugins/waza/skills/read/SKILL.md · Fetches URLs and PDFs, then summarizes or returns clean Markdown; can also search the web through DeepSeek when…
git:20261018.840f926 · audit A · 7,489 stars
think SKILL.md skill
tw93/waza · plugins/waza/skills/think/SKILL.md · Turns rough ideas into approved, decision-complete plans before coding. Use when planning architecture, judging whether…
git:20261007.6b6c736 · audit A · 7,489 stars
ui SKILL.md skill
tw93/waza · plugins/waza/skills/ui/SKILL.md · Produces distinctive production UI and screenshot-grounded visual polish. Use when building or restyling pages…
git:20261030.66cad88 · audit A · 7,489 stars
write SKILL.md skill
tw93/waza · plugins/waza/skills/write/SKILL.md · Rewrites and polishes Chinese or English prose, technical instructions, and product copy. Use when drafting, editing…
git:20261027.9ac7a67 · audit A · 7,489 stars
check SKILL.md skill
tw93/waza · skills/check/SKILL.md · Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs…
git:20261028.7703a48 · audit A · 7,489 stars
health SKILL.md skill
tw93/waza · skills/health/SKILL.md · Audits agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks…
git:20261015.c8985bb · audit A · 7,489 stars
hunt SKILL.md skill
tw93/waza · skills/hunt/SKILL.md · Finds root cause before any fix. Use when something errors, crashes, regresses, or used to work. Not for code review or…
git:20260925.c3b74dd · audit A · 7,489 stars

Every file in tw93/waza

Other files named health

health SKILL.md skill
garrytan/gstack · health/SKILL.md · Code quality dashboard. (gstack)
v1.0.0 · audit A · 138,879 stars
health SKILL.md skill
tw93/waza · skills/health/SKILL.md · Audits agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks…
git:20261015.c8985bb · audit A · 7,489 stars
health SKILL.md skill
solpbc/solstone-journal · core/payload/solstone/apps/health/talent/health/SKILL.md · Monitor solstone uptime, troubleshoot capture/processing failures, review agent runs and errors, pipeline health. CLIs…
git:20261003.3be907f · audit A · 28 stars
health SKILL.md skill
varun-singhh/lfg · plugin/skills/health/SKILL.md · Scans the codebase for deepening opportunities (shallow modules, leaky seams, hard-to-test areas) using the graphs, and…
git:20261015.6b3a06b · audit A · 10 stars
health SKILL.md skill
tekkiiiii/the-agency · skills/health/SKILL.md · Code quality dashboard. Wraps existing project tools (type checker, linter, test runner, dead code detector, shell…
v1.0.0 · audit A · 7 stars
health SKILL.md skill
timurgaleev/vibestack · skills/health/SKILL.md · Code quality dashboard: runs the project's type checker, linter and tests, scores health 0-10, tracks trends.
git:20261013.11d1a4f · audit A · 7 stars
health SKILL.md skill
broomva/skills · skills/healthcare/health/SKILL.md · Personal health knowledge graph — local-first ingest of Garmin (Apple Health, Whoop, Oura, CGM in v2+) traces into…
v0.12.0 · audit A · 5 stars
health SKILL.md skill
linggen/skills · health/SKILL.md · Linggen Health — the health app for people whose job is a computer. Your iPhone reads Apple Health and keeps your body…
git:20261014.0c42039 · audit A · 3 stars

Browse by kind, by grade A, or by owner.