coach: Command for Gemini CLI

.gemini/commands/support/triage.toml

triage is a command for Gemini CLI from watt-mind/coach. It costs 0 tokens per session (515 once invoked), scanned A, original, Apache-2.0.

A command for investigating the root cause of a production support ticket. It retrieves the ticket, examines its context and logs, and uses project command-line tools or database queries to investigate the affected data.

In plain words
What is it for?
It helps diagnose support issues, inspect production entities and database data, and extend the project's reusable command-line tools when needed.
Why use it?
It provides a repeatable way to trace a user problem through production records instead of relying only on the ticket description.

Command for Gemini CLI

Written for Gemini CLI: installed under .gemini/.

This is watt-mind/coach's own configuration. It tells Gemini CLI how to work on coach itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything coach configures →

Reuse

Borrowing it

Nothing to install: this file belongs to watt-mind/coach. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/watt-mind/coach/master/.gemini/commands/support/triage.toml
Clone the repo
git clone --depth 1 https://github.com/watt-mind/coach

Made for: Gemini CLI.

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 triage

README.md
[![agentmods](https://agentmods.dev/badge/commands/watt-mind/coach/triage.svg)](https://agentmods.dev/commands/watt-mind/coach/triage)
Your own site
<a href="https://agentmods.dev/commands/watt-mind/coach/triage"><img src="https://agentmods.dev/badge/commands/watt-mind/coach/triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 515 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 $0.00000 $0.00515
Opus 5 $0.00000 $0.00258
Sonnet 5 $0.00000 $0.00103
Haiku 4.5 $0.00000 $0.00052

Measured 2d ago against content hash 07ca2b73d4be, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 2d 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.

.gemini/commands/support/triage.toml · 28 lines

How it starts

The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.

description = "Investigate the root cause for a specific ticket ID." prompt = """ You are a support agent and backend investigator for the provided ticket ID from the production environment.

User Input Arguments: {{args}}

Steps

  1. Fetch Details: Execute npx tsx cli/index.ts support tickets get {{args}} --prod to fetch the ticket details.
  2. Analyze: Read the ticket's title, description, context, and logs. Note the affected user ID.
  3. Validate: Use existing cw:cli tools to troubleshoot the issue.
    • Capabilities: The cw:cli provides various tools for production investigations when appending the --prod flag. You can query data using npx tsx cli/index.ts db sql "<query>" --prod to execute raw SQL against the production DB. You can also fetch specific entities, such as npx tsx cli/index.ts db workout get <id> --prod.
    • Preference for CLI: Always prefer using or extending cw:cli scripts for troubleshooting rather than writing one-off ad-hoc scripts.
    • Reuse & Extension: If an existing cw:cli tool is missing a feature needed for your investigation, add that functionality to the tool so it can be reused by others in the future.
  4. Identify Cause: Determine the likely root cause. Look for patterns in similar tickets or system logs.
  5. Propose Fix: Propose a concrete fix plan. Group actions into:
    • Data Fixes: (e.g., updating DB records via CLI)
    • System Actions: (e.g., re-triggering jobs)
    • Code Changes: (e.g., logic fixes)
  6. Document: Log your findings on the ticket.
    • Use --type NOTE for internal technical notes. Replace placeholders with actual technical evidence (IDs, error codes, log snippets). npx tsx cli/index.ts support tickets comment {{args}} "Agent Findings: [ACTUAL FINDINGS HERE]" --type NOTE --prod
    • Use --type MESSAGE if a friendly update to the user is requested. Be nice, empathetic, and thankful for their report.
      • If you are proposing a code fix, mention that it will be available in a future deployment once approved and merged.

Read the full file on GitHub · 28 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. 2d ago First seen · 28 lines · 0 tokens per session scan A 07ca2b73d4be

Subscribe to this mod's changes

triage is a command published in the GitHub repository watt-mind/coach (83 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 515 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 2026-09-04.