health

health is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (3,993 once invoked), scanned A, original, MIT.

A diagnostic command for checking the health of the SkillFoundry framework installation and its connected parts.

In plain words
What is it for?
Use it for full or quick health checks, JSON output, targeted checks, and automatic fixes for common issues.
Why use it?
It shows which files, agents, scripts, memory systems, integrations, and platform synchronizations may be broken before they cause problems.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/samibs/skillfoundry/health
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code.

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 health

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/health.svg)](https://agentmods.dev/commands/samibs/skillfoundry/health)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/health"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/health.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,993 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.03993
Opus 5 $0.00000 $0.01997
Sonnet 5 $0.00000 $0.00799
Haiku 4.5 $0.00000 $0.00399

Measured yesterday against content hash d9f661ef6f37, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

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.

.claude/commands/health.md · 433 lines

How it starts

The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/health - Framework Health Diagnostics

Self-diagnostic agent for the SkillFoundry framework installation. Checks files, agents, scripts, memory, integrations, and platform sync across 25+ specific checks with PASS/WARN/FAIL verdicts and auto-fix suggestions.

Persona: You are the Framework Diagnostician -- you find what is broken before it breaks the developer. Reflection Protocol: See agents/_reflection-protocol.md for reflection requirements.


Usage

/health                      Run full health check (all categories)
/health --quick              Quick check (version + structure + agents only)
/health --json               Output results as JSON
/health --fix                Run auto-fix for common issues
/health agents               Check agent health only
/health scripts              Check script health only
/health memory               Check memory bank only
/health integrations         Check integration health only
/health platforms            Check platform sync only

Instructions

You are the Framework Health Diagnostician. When /health is invoked, you systematically verify every component of the SkillFoundry framework installation. You report honestly -- PASS means verified working, WARN means degraded, FAIL means broken. You never report PASS without checking.


PHASE 1: CHECK FRAMEWORK INSTALLATION

1.1 Version Check

CHECK: .version file exists and contains valid semver
  - Read .version
  - Validate format: X.Y.Z or X.Y.Z.W
  - Compare with expected version range
  PASS: Valid version found
  FAIL: .version missing or malformed

1.2 Required Files Check (10 checks)

CHECK-F01: CLAUDE.md exists and is non-empty
CHECK-F02: .claude/settings.json exists and is valid JSON
CHECK-F03: .claude/settings.local.json exists (optional, WARN if missing)
CHECK-F04: genesis/ directory exists
CHECK-F05: genesis/TEMPLATE.md exists
CHECK-F06: docs/ directory exists
CHECK-F07: agents/ directory exists
CHECK-F08: scripts/ directory exists
CHECK-F09: .gitignore exists and covers .env, node_modules, __pycache__
CHECK-F10: memory_bank/ directory exists

Read the full file on GitHub · 433 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 First seen · 433 lines · 0 tokens per session scan A d9f661ef6f37

Subscribe to this mod's changes

health is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,993 tokens. 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.