Borrowing it
Nothing to install: this file belongs to jamesbrink/mcp-coroot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jamesbrink/mcp-coroot/main/.claude/commands/coroot-triage.mdgit clone --depth 1 https://github.com/jamesbrink/mcp-corootWrote 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/commands/jamesbrink/mcp-coroot/coroot-triage)<a href="https://agentmods.dev/commands/jamesbrink/mcp-coroot/coroot-triage"><img src="https://agentmods.dev/badge/commands/jamesbrink/mcp-coroot/coroot-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/commands/jamesbrink/mcp-coroot/coroot-triage"><img src="https://agentmods.dev/badge/commands/jamesbrink/mcp-coroot/coroot-triage.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00278 |
| Opus 5.5 | $0.00000 | $0.00111 |
| Sonnet 5.5 | $0.00000 | $0.00056 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
coroot-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 a Coroot project
Work out what is wrong with the system right now, using the Coroot MCP tools.
Start with list_alerts for what is firing, list_incidents with
state_filter open for SLO breaches, and list_applications for anything at
warning or critical. Check list_nodes for a host that is down or saturated.
If all of those come back empty, call get_project_status before concluding
that everything is fine: an empty result can mean telemetry is not arriving.
Then, for the most serious problem, follow it down:
- Latency:
get_tracesfor the service, thenget_trace_latency, thenget_traceon a sample. - Errors:
get_trace_errors, thenget_logswith severity error over the same window. - Resource pressure:
get_applicationwith the CPU or Memory report, andget_nodefor its host. - Something changed:
list_deploymentsover a window starting before the problem did. - Blame upstream:
get_service_map, then repeat for any unhealthy dependency.
Report the ranked problems with the application id and the evidence for each, then name the single thing worth doing first. Say what you could not establish rather than guessing.
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 · 27 lines · 0 tokens per session scan A 9bce16f1168c
coroot-triage is a command published in the GitHub repository jamesbrink/mcp-coroot (16 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 278 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 2026-09-28.
coroot-triage compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| coroot-triagejamesbrink/mcp-coroot | Command | 16 | 1mo ago | MIT | A | 0 | Claude Code |
| vs-doctormtarcure/claude-vibe-squad | Command | 228 | 9d ago | MIT | A | 0 | Claude Code |
| preflightcdeust/Cortex | Command | 76 | yesterday | MIT | A | 20 | Claude Code |
| umt-doctorMarkgatcha/universal-mcp-toolkit | Command | 16 | 3d ago | MIT | A | 16 | Claude Code |
| fixHimanshu507/cgcone | Command | 9 | yesterday | MIT | A | 15 | Claude Code |
| wiki-linttboome33/obsidian-mcp-router | Command | 1 | 5d ago | Apache-2.0 | A | 42 | Claude Code |
| foldicloudza/algokiller-plugin | Command | 80 | 5mo ago | MIT | A | 37 | Claude Code |