watercooler-health

watercooler-health is a skill for Claude Code from mostlyharmless-ai/watercooler. It costs 49 tokens per session (815 once invoked), scanned A, original, Apache-2.0.

A diagnostic procedure for checking the health of the Watercooler system and its related services, such as its MCP server, baseline graph, Git authentication, rate limits, and background services.

In plain words
What is it for?
Use it to check service status, agent identity, repository and branch settings, write access, graph services, and other Watercooler dependencies.
Why use it?
It helps locate which part of the system is failing when synchronisation or other Watercooler functions stop working.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the watercooler plugin — 7 skills, 1 MCP server shipped together

Good fit Use it to check service status, agent identity, repository and branch settings, write access, graph services, and other Watercooler dependencies.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mostlyharmless-ai/watercooler/watercooler-health
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.

Any agent
npx skills add mostlyharmless-ai/watercooler --skill watercooler-health
Clone the repo
git clone --depth 1 https://github.com/mostlyharmless-ai/watercooler

Made for: Claude Code.

Or install watercooler, the plugin that ships this one along with the rest of its 7 skills, 1 MCP server.

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 watercooler-health

README.md
[![agentmods](https://agentmods.dev/badge/skills/mostlyharmless-ai/watercooler/watercooler-health/github.svg)](https://agentmods.dev/skills/mostlyharmless-ai/watercooler/watercooler-health)
Your own site
<a href="https://agentmods.dev/skills/mostlyharmless-ai/watercooler/watercooler-health"><img src="https://agentmods.dev/badge/skills/mostlyharmless-ai/watercooler/watercooler-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.

agentmods 80×15 button for watercooler-health

Your own site · 80×15
<a href="https://agentmods.dev/skills/mostlyharmless-ai/watercooler/watercooler-health"><img src="https://agentmods.dev/badge/skills/mostlyharmless-ai/watercooler/watercooler-health.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 815 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00049 $0.00815
Opus 5 $0.00024 $0.00407
Sonnet 5 $0.00010 $0.00163
Haiku 4.5 $0.00005 $0.00081

Measured 11d ago against content hash 0b55f9cd4340, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

watercooler-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 11d 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.

plugins/claude/watercooler/skills/watercooler-health/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Watercooler Health Check

Run a full health check across all watercooler subsystems.

Steps

  1. Load diagnostic tools in parallel:

    ToolSearch: select:mcp__watercooler__watercooler_health
    ToolSearch: select:mcp__watercooler__watercooler_baseline_graph
    
  2. Run checks in parallel:

    mcp__watercooler__watercooler_health(code_path="<repo root>")
    mcp__watercooler__watercooler_health(code_path="<repo root>", detail="identity")
    mcp__watercooler__watercooler_baseline_graph(scope="sync", code_path="<repo root>")
    

    The detail="identity" call returns the resolved agent identity and a write-readiness assessment (threads-dir writability + agent_func guidance) — this is the folded-in former whoami check.

  3. Report status — organize output into these sections:


    Server Health (from watercooler_health):

    • Server version and status
    • Agent identity and threads directory
    • Code branch and auto-branch mode
    • Python / fastmcp versions
    • Write-readiness (from watercooler_health(detail="identity")): resolved identity and whether the threads dir is writable

    Graph Services (from watercooler_health):

    • Summaries enabled, LLM service URL and availability
    • Embeddings enabled, embedding service URL and availability

    Backend Services (from watercooler_health):

    • Auto-start services (llm, embedding, falkordb) with state icons
    • Include startup time (ms) for running services
    • Surface setup instructions for any failed services

    Daemons (from watercooler_health):

    • Each daemon: state, interval, ticks, findings, errors

    Thread Storage (from watercooler_health):

    • Mode (orphan worktree), path, code branch

    Git Authentication (from watercooler_health):

    • Protocol (ssh/https), connectivity status
    • Credential helper or SSH agent/key status
    • Any auth warnings and recommended fixes

    GitHub (from watercooler_health):

    • gh CLI version (warn if outdated)
    • API rate limit: remaining/total (%) and reset time
    • Any warnings and recommendations

Read the full file on GitHub · 91 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. 11d ago First seen · 91 lines · 49 tokens per session scan A 0b55f9cd4340

Subscribe to this mod's changes

watercooler-health is a skill published in the GitHub repository mostlyharmless-ai/watercooler (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 815 once invoked, about $0.0002 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 2026-08-30.