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 agentmods add skills/grainulation/grainulator/healthchecknpx skills add grainulation/grainulator --skill healthcheckgit clone --depth 1 https://github.com/grainulation/grainulatorWrote 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/grainulation/grainulator/healthcheck)<a href="https://agentmods.dev/skills/grainulation/grainulator/healthcheck"><img src="https://agentmods.dev/badge/skills/grainulation/grainulator/healthcheck.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.01035 |
| Opus 5 | $0.00027 | $0.00517 |
| Sonnet 5 | $0.00011 | $0.00207 |
| Haiku 4.5 | $0.00005 | $0.00103 |
Grade A, and why
healthcheck 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 5d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/healthcheck -- Pre-flight MCP server verification
Fast health check for all Grainulator MCP servers. One ping per server, no retries, immediate fix commands if anything is down.
Arguments
$ARGUMENTS
Instructions
Step 1: Ping all three servers in parallel
Call these three tools simultaneously (in a single message):
wheat_status— verifies the Wheat claims enginemill_formats— verifies the Mill format convertersilo_list— verifies the Silo knowledge store
Step 2: Report results
Print a status table:
Grainulator Health Check
========================
wheat ✓ healthy — claims engine
mill ✓ healthy — format conversion
silo ✓ healthy — knowledge storage
All servers operational.
If any server fails, show:
Grainulator Health Check
========================
wheat ✗ FAILED — claims engine
mill ✓ healthy — format conversion
silo ✓ healthy — knowledge storage
Fix commands:
wheat: claude mcp add wheat -- npx -y -p @grainulation/wheat wheat-mcp
Step 3: Diagnose failure class (only if a server failed)
Distinguish two failure types by the error message:
- "tool not found" or "not registered" — the MCP server is not connected. Fix: re-add it.
- "tool call failed" or timeout — the server is registered but the process crashed or network is down. Fix: check Node.js/network, then re-add.
Step 4: Provide fix commands
If Wheat failed:
- Re-add:
claude mcp add wheat -- npx -y -p @grainulation/wheat wheat-mcp
If Mill failed:
- Re-add:
claude mcp add mill -- npx -y @grainulation/mill serve-mcp
If Silo failed:
- Re-add:
claude mcp add silo -- npx -y @grainulation/silo serve-mcp
Step 5: Host-capability probe (Claude Code version drift)
After the three MCP pings succeed, verify the Claude Code host exposes the APIs grainulator needs. If Anthropic ships a breaking change in a minor version, this is how we detect it before the user sees silent hook failures.
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.
- 5d ago First seen · 121 lines · 54 tokens per session scan A b487122bc078
healthcheck is a skill published in the GitHub repository grainulation/grainulator (86 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 1,035 once invoked, about $0.0003 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.
Other skills, from other repositories
wf-pm
Sole team lead of the waterfall workflow — creates the team, dispatches OR's spawnrequest, relays HO decisions via AskUserQuestion, and runs the final git commit at CLOSURE.
wf-new
Starts a new SDD need via the waterfall workflow — agent teams preflight, OR spawn, bootstrapneed.
wf-pm-light
PM solo pour le mode subagent-light — élicitation, specs.md, checkpoint specs, spawn TL passe 1+2, checkpoint tasks, validation finale, git commit.
wf-resume
Resumes an interrupted waterfall workflow — preflight, need lookup, agent re-spawn (implicit team), OR handoff with resume brief.
wf-tl-light
TL solo-impl pour le mode subagent-light — rédige design.md + tasks.md (passe 1), puis implémente toutes les tâches T-xxx en solo (passe 2). Pas de sous-agent DV, pas de worktrees.
wf-quit
Cleanly stops the active wf workflow — shutdown teammates, marker cleanup, state preservation for resume.