system-health-check

A readiness checker for a computer and its connected services, such as browsers, voice providers, channels, models, and required software.

In plain words
What is it for?
It helps diagnose setup problems, check dependencies, verify browser or voice readiness, inspect integrations, and run local smoke tests.
Why use it?
It shows which parts of a planned workflow are available, missing, or unhealthy before a longer task fails midway.

Skill for Claude CodeCodex

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 skills/codeinfinity1/stram/system-health-check
Any agent
npx skills add CodeInfinity1/Stram --skill system-health-check
Clone the repo
git clone --depth 1 https://github.com/CodeInfinity1/Stram

Made for: Claude Code, Codex.

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 559 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 $0.00029 $0.00559
Opus 5 $0.00015 $0.00280
Sonnet 5 $0.00006 $0.00112
Haiku 4.5 $0.00003 $0.00056

Measured 3d ago against content hash 852a04896578, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

system-health-check 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check_readiness.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/agent-core/system-health-check/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Health Check

Purpose

Give the assistant a reliable view of local readiness before running complex tasks. This skill checks environment and integration health without pretending missing providers are working.

When To Use

Use before end-to-end smoke tests, local model/voice/channel/browser setup, app troubleshooting, dependency diagnosis, or when the user asks whether the system is ready.

Inputs And Evidence

  • User's target workflow and required capabilities.
  • System status, provider status, channel doctor output, external integration status, and browser readiness.
  • Missing environment variables, binaries, models, or local services.

Tool Map

  • system_status
  • external_integrations_status
  • voice_provider_status
  • browser_live_status
  • channel_doctor
  • activity_policy
  • tool_search
  • capability_surface
  • agent_skill_script_catalog
  • agent_skill_script_run

Native Scripts

  • scripts/check_readiness.py: collects workspace, data directory, Python runtime, skill count, and redacted environment-presence facts. Use through agent_skill_script_run when a compact local readiness snapshot is useful.

Workflow

  1. Identify the workflow being checked: voice, browser, OS control, channels, local models, or full agent.
  2. Query the relevant native status tools.
  3. Separate working, missing, disabled, unconfigured, and unsupported capabilities.
  4. Recommend the smallest native setup step for each blocker.
  5. Do not install or run external code unless the user approves the exact action.
  6. Re-run targeted checks after fixes.

Native Implementation Boundaries

  • Use Stram status and capability tools.
  • Do not call upstream health-check scripts from external reference/external reference/Windows-use.
  • Do not infer readiness from installed reference repos alone.

Safety And Approval

  • Status checks should not expose secrets; report presence/missing rather than raw values.
  • Environment changes, installs, and service starts require approval where applicable.
  • Avoid broad scans of private locations unless required.

Read the full file on GitHub · 76 lines

Files

What ships with it

1 file 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.

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. 3d ago First seen · 76 lines · 29 tokens per session scan A 852a04896578

Subscribe to this mod's changes

system-health-check is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 23d ago), licensed MIT. It adds 29 tokens to every session and 559 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 2026-08-31.