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 SienkLogic/plan-build-run --skill healthgit clone --depth 1 https://github.com/SienkLogic/plan-build-runWrote 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/sienklogic/plan-build-run/health)<a href="https://agentmods.dev/skills/sienklogic/plan-build-run/health"><img src="https://agentmods.dev/badge/skills/sienklogic/plan-build-run/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.
<a href="https://agentmods.dev/skills/sienklogic/plan-build-run/health"><img src="https://agentmods.dev/badge/skills/sienklogic/plan-build-run/health.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 | $0.00013 | $0.01849 |
| Opus 5 | $0.00006 | $0.00924 |
| Sonnet 5 | $0.00003 | $0.00370 |
| Haiku 4.5 | $0.00001 | $0.00185 |
Grade A, and why
health 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STOP — DO NOT READ THIS FILE. You are already reading it. This prompt was injected into your context by Claude Code's plugin system. Using the Read tool on this SKILL.md file wastes ~7,600 tokens. Begin executing Step 1 immediately.
Step 0 — Immediate Output
Before ANY tool calls, display this banner:
╔══════════════════════════════════════════════════════════════╗
║ PLAN-BUILD-RUN ► HEALTH CHECK ║
╚══════════════════════════════════════════════════════════════╝
Then proceed to Step 1.
/pbr:health — Planning Directory Diagnostics
You are running the health skill. Your job is to validate the integrity of the .planning/ directory, report problems, and suggest targeted fixes.
This skill runs inline. It is read-only by default, but offers an optional auto-fix flow for common corruption patterns (see the Auto-Fix section below).
References
references/questioning.md— Questioning philosophy for diagnostic probingreferences/ui-brand.md— Status symbols, banners, checkpoint boxes
Argument Parsing
Check if the user passed --repair:
--repair: Skip the AskUserQuestion prompt in the Auto-Fix section and automatically apply ALL fixes (equivalent to selecting "Fix all"). Still create backups before any destructive operations.- No flag: Use the interactive AskUserQuestion flow as described below (default behavior).
How Checks Work
Health checks are now CLI-driven via verify health. The check-pattern template (${CLAUDE_SKILL_DIR}/templates/check-pattern.md.tmpl) describes the classification model (PASS/FAIL/WARN/INFO) used by the CLI internally.
Read ${CLAUDE_SKILL_DIR}/templates/output-format.md.tmpl for the output format: summary table, status indicators, issues list, optional recent decisions, and final result line.
Checks
Run all health checks via the CLI:
pbr-tools verify health
Parse the JSON output. The CLI returns an object with:
checks: array of{ name, status, message, fix_suggestion }for each checksummary:{ passed, failed, warned, total }
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 205 lines · 13 tokens per session scan A 4efb7b2484e8
health is a skill published in the GitHub repository SienkLogic/plan-build-run (17 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 1,849 once invoked, about $0.0001 per session on Opus 5. 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 2026-09-03.
Other skills, from other repositories
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
investigate
Systematic root-cause debugging: find the cause before writing any fix.
sandbox-unblock
Diagnostic protocol to run before reporting a sandbox blocker or asking for a configuration change. Eight checks that eliminate false positives, then a report template the person holding the settings can act on. On one measured day, six of eight reported blockers turned out to be false, all from the same handful of…
qa
Systematic QA testing of a web application: diff-aware, tiered, with fix-and-verify loop.
optimize
Analyze and suggest performance improvements for code, queries, or systems.
code-review
Review code changes for concrete defects.