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 activeing123/mcptoon --skill triagegit clone --depth 1 https://github.com/activeing123/mcptoonWrote 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/activeing123/mcptoon/triage)<a href="https://agentmods.dev/skills/activeing123/mcptoon/triage"><img src="https://agentmods.dev/badge/skills/activeing123/mcptoon/triage/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/activeing123/mcptoon/triage"><img src="https://agentmods.dev/badge/skills/activeing123/mcptoon/triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.00489 |
| Opus 5.5 | $0.00012 | $0.00196 |
| Sonnet 5.5 | $0.00006 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
triage 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 1mo 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.
What it actually says
Triage MCP server failures with mcptoon
Work top-down; stop as soon as the layer with the fault is found.
1. Read the config layer first
mcptoon doctor
Catches: invalid JSON, unknown fields, missing binaries for stdio commands, malformed URLs. Fix anything reported before deeper probing.
2. Check connectivity
mcptoon health # every server, human-readable
mcptoon health --json # CI/CD friendly, exit 1 if any dead
3. Probe the tool layer
mcptoon list # is the server even registered?
mcptoon manifest --compact # do its tools appear at all?
mcptoon inspect <server> <tool> # full schema of one tool
mcptoon call <server> <tool> '{}' --toon # minimal live call
list shows it but manifest does not → the server answers initialize but
fails tools/list: read the server's own logs (run its command manually).
Common failures → fixes
| Symptom | Likely cause | Fix |
|---|---|---|
| doctor: binary not found | command not on PATH | fix PATH, or install the package, or use npx/uvx |
| health: timeout | server hangs on startup | raise timeout, or fix slow startup; try running the command directly |
| call: unknown tool | tool toggled off | check the toggle on that tool in config, then mcptoon sync |
| call: schema error | wrong args shape | mcptoon inspect the tool and match the inputSchema exactly |
| stdio: spawn ENOENT | bad command token | command must be one token on PATH or ./relative; never a shell string |
| everything dead after edit | config overwritten by hand in agent dir | re-edit ~/.mcptoon/config.json, run mcptoon sync |
After fixing
mcptoon sync # push the repaired config to all agents
mcptoon health # prove it is green
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.
- 1mo ago First seen · 55 lines · 30 tokens per session scan A 1a09a1a8e3ed
triage is a skill published in the GitHub repository activeing123/mcptoon (359 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 489 once invoked, about $0.0001 per session on Opus 5.5. 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
cortex-snippets
Use when installing, running, or adapting reusable Labby Code Mode snippets for Cortex incidents, session search, topology, reports, troubleshooting, service diagnostics, or assessment evidence. Use using-cortex for an ordinary single Cortex tool call.
using-cortex
Use when searching Cortex syslog, Docker, OTLP, or AI session evidence; checking hosts, errors, fleet state, topology, or correlations; or investigating homelab events through the Cortex MCP tool. For first-run setup or repair, use install-cortex.
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
ix
Answer structural questions about a codebase — what a symbol is, what calls it, what a change breaks, where the hotspots are — from a persistent code graph via the ix CLI, instead of grepping.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
opik-explain
Root-cause a specific Opik trace, or a pattern across traces, and return a grounded explanation. Uses the hosted Opik MCP when it is connected, and falls back to SDK scripting otherwise. Returns the root cause, the evidence spans as clickable Opik UI links, and one suggested next step. Use for "why did this trace…