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.
npx skills add jasonkneen/lazar --skill health-checkgit clone --depth 1 https://github.com/jasonkneen/lazarWrote 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.
[](https://agentmods.dev/skills/jasonkneen/lazar/health-check)<a href="https://agentmods.dev/skills/jasonkneen/lazar/health-check"><img src="https://agentmods.dev/badge/skills/jasonkneen/lazar/health-check/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.
<a href="https://agentmods.dev/skills/jasonkneen/lazar/health-check"><img src="https://agentmods.dev/badge/skills/jasonkneen/lazar/health-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00107 | $0.02935 |
| Opus 5 | $0.00053 | $0.01468 |
| Sonnet 5 | $0.00021 | $0.00587 |
| Haiku 4.5 | $0.00011 | $0.00294 |
Grade C, and why
health-check scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$HC" How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
health-check
Verify lazar is installed correctly and all the load-bearing behaviors work end-to-end. Runs in a temp directory so it doesn't pollute real state.
When to use
- Right after install or
setup.sh, to confirm everything works. - After a kernel rebuild, to verify the patch didn't break anything.
- After
--reset-all, to validate fresh state. - When something feels off and you want a baseline.
- Periodically as a smoke test before a long session.
How to use
Run the recipes in order. Each check prints [PASS], [FAIL: <reason>], or [SKIP: <reason>] for things that aren't applicable on this system. Print a summary at the end with the PASS/FAIL count.
If any FAIL appears, the user should investigate before doing real work — most failures point at a misconfiguration that will silently bite later.
Setup
HC="$LAZAR_HOME/workspace/.health-check-$(date +%s)"
mkdir -p "$HC"
echo "[health-check] starting in $HC"
PASS=0; FAIL=0; SKIP=0
pass() { echo " [PASS] $1"; PASS=$((PASS+1)); }
fail() { echo " [FAIL] $1"; FAIL=$((FAIL+1)); }
skip() { echo " [SKIP] $1"; SKIP=$((SKIP+1)); }
1. Static checks (kernel + filesystem)
echo "── 1. static checks ────────────────────────────────"
# kernel binary
[ -f "$LAZAR_HOME/bin/lazar" ] && pass "kernel binary at bin/lazar" || fail "no kernel binary"
# kernel locked (macOS chflags uchg)
ls -lO "$LAZAR_HOME/bin/lazar" 2>/dev/null | rg -q uchg \
&& pass "kernel binary is uchg-locked (immutable)" \
|| fail "kernel binary is NOT immutable — chflags uchg should be set"
# source not user-writable
TESTSRC="$LAZAR_HOME/src/.health-write-probe"
touch "$TESTSRC" 2>/dev/null && { rm -f "$TESTSRC"; fail "src/ is writable — should be chmod a-w"; } \
|| pass "src/ is read-only"
# env vars from kernel
[ -n "$LAZAR_HOME" ] && pass "LAZAR_HOME=$LAZAR_HOME" || fail "LAZAR_HOME unset"
[ -n "$LAZAR_SKILLS" ] && pass "LAZAR_SKILLS=$LAZAR_SKILLS" || fail "LAZAR_SKILLS unset"
[ -n "$LAZAR_MEMORY" ] && pass "LAZAR_MEMORY=$LAZAR_MEMORY" || fail "LAZAR_MEMORY unset"
[ -n "$LAZAR_WORKSPACE" ] && pass "LAZAR_WORKSPACE=$LAZAR_WORKSPACE" || fail "LAZAR_WORKSPACE unset"
[ -n "$LAZAR_LOGS" ] && pass "LAZAR_LOGS=$LAZAR_LOGS" || fail "LAZAR_LOGS unset"
# api key
[ -n "$ANTHROPIC_API_KEY" ] && pass "ANTHROPIC_API_KEY is set" || fail "ANTHROPIC_API_KEY not set"
# seed skills present in live skills/
for s in create-skill find-capability shell-handoff load-context log-rotation archive-search distill propose-kernel-patch project-context create-tui health-check; do
[ -f "$LAZAR_SKILLS/_meta/$s/SKILL.md" ] && pass "skill _meta/$s" || fail "skill _meta/$s missing"
done
[ -f "$LAZAR_SKILLS/memory/SKILL.md" ] && pass "skill memory" || fail "skill memory missing"
[ -f "$LAZAR_SKILLS/INDEX.md" ] && pass "skills/INDEX.md present" || fail "INDEX.md missing"
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.
- 12d ago First seen · 257 lines · 107 tokens per session scan C 413f63b39acf
health-check is a skill published in the GitHub repository jasonkneen/lazar (31 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 2,935 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
verify-bug
Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.
reality-verification
This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy…
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
qa
Read-only automated QA sweep of a deployed stardust site on AEM Edge Delivery Services — validates routing, content fidelity vs the source capture, template conformance, rendered integrity (geometry, JS errors, broken images), visual regression vs baselines, metadata/SEO/JSON-LD, link integrity, accessibility (axe)…