triage

triage is a command for Claude Code from dork-labs/dorkos. It costs 28 tokens per session (5,838 once invoked), scanned A, original, MIT.

A command for processing a user-feedback queue stored in Linear, a project and issue-tracking service. It separates routine triage from the release-only step that emails reporters about shipped fixes.

In plain words
What is it for?
Use it to triage bug reports and ideas, find queue anomalies, maintain the status mirror, and send shipped emails only during a release.
Why use it?
It keeps feedback statuses accurate and prevents users from being told that a fix shipped before it is actually released.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool; mentions AGENTS.md.

Part of the flow plugin — 41 skills, 44 commands, 5 agents, 4 hooks shipped together

Good fit Use it to triage bug reports and ideas, find queue anomalies, maintain the status mirror, and send shipped emails only during a release.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/dork-labs/dorkos/triage
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.

Clone the repo
git clone --depth 1 https://github.com/dork-labs/dorkos

Made for: Claude Code.

Or install flow, the plugin that ships this one along with the rest of its 41 skills, 44 commands, 5 agents, 4 hooks.

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/dork-labs/dorkos/triage/github.svg)](https://agentmods.dev/commands/dork-labs/dorkos/triage)
Your own site
<a href="https://agentmods.dev/commands/dork-labs/dorkos/triage"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/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.

agentmods 80×15 button for triage

Your own site · 80×15
<a href="https://agentmods.dev/commands/dork-labs/dorkos/triage"><img src="https://agentmods.dev/badge/commands/dork-labs/dorkos/triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,838 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00028 $0.05838
Opus 5.5 $0.00011 $0.02335
Sonnet 5.5 $0.00006 $0.01168
Haiku 4.5 $0.00003 $0.00584

Measured 24d ago against content hash 8e065be6d33f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

triage scanned grade A with 1 finding 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 24d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Read, Bash(composio:*), Bash(gh:*), Bash(curl:*), Bash(python3:*), Bash(node:*), AskUserQuestion
.claude/commands/feedback/triage.md · 444 lines

How it starts

The opening of the file, as written. The whole thing — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Process the User-Feedback Queue

Argument: $ARGUMENTS


Purpose

User bug reports and ideas land as Linear issues in the DorkOS User Feedback (FB) team's Triage. Nothing works that queue automatically — this command is the whole processing loop. It has two modes with deliberately different safety profiles:

  • Default (no argument): triage + anomaly report. Safe to run any time. Every write it makes is silent to reporters and reversible.
  • --sweep: the shipped-email pass. Its ONLY sanctioned trigger is the release flow (/system:release invokes it). A DOR issue goes Done at merge; the reporter's fix is only real at release. Running the sweep at any other moment tells a named human "this shipped" about work they cannot get yet. Do not run --sweep ad hoc.

Both modes serve one promise, meta/user-care.md: a person who reports something hears back within one business day (heard), hears what we decided within five (decided), and hears when it ships (shipped). Nobody gets silence. Reports arrive through two doors. The in-app "Send feedback" dialog files into FB directly. GitHub issues on dork-labs/dorkos are mirrored in by step 0 below. The door decides where each reply goes, never whether it happens. How to word a reply is the writing-to-users skill.

A business day here is Monday to Friday in the operator's local time. Weekends do not count toward the one-day and five-day deadlines. Every other duration in this file is plain calendar time and says so.

If meta/user-care.md or the writing-to-users skill is missing from this checkout, stop and say which one. They are the standard and the wording rules for every reply below. Never draft a reply to a named person freehand because a file did not resolve; a form letter to somebody who took the time to write to us is worse than being an hour late.

Ground rules that protect reporters (from the process design debate, 2026-09-11; ops context in contributing/feedback-pipeline-ops.md):

Read the full file on GitHub · 444 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. 24d ago Changed · +316 lines 8e065be6d33f
  2. 27d ago First seen · 128 lines · 28 tokens per session scan A 9fd3cfed5634

Subscribe to this mod's changes

triage is a command published in the GitHub repository dork-labs/dorkos (10 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 5,838 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.

Related

Other commands, from other repositories

scout-meta-review

Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Checks whether sessions are running, mistake audit is trending well, proposals are flowing, KB files are healthy, and data-source coverage is consistent across session types. Runs in the current conversation.

Raven-Scout/Scout · 61 tokens

scout-work

Interactive work session — walks through today's actionable items one at a time, presents a recommended action with draft content, and executes each one only with explicit approval. Runs in the current conversation (not as a background session).

Raven-Scout/Scout · 47 tokens

scout-work

Interactive work session — walks through today's actionable items one at a time, presents a recommended action with draft content, and executes each one only with explicit approval. Runs in the current conversation (not as a background session).

Raven-Scout/scout-plugin · 47 tokens

modernize-preflight

Run this first — checks the environment, records where the code lives, and says what to fix before anything else runs.

thevibeworks/claude-code-docs · 23 tokens

sp.taskstoissues

Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.

Wania-Kazmi/claude-code-autonomous-agent-workflow · 21 tokens

repo-architect

Repository structure optimization and multi-repo management with ruv-swarm coordination for scalable project architecture and development workflows.

ruvnet/ruflo · 0 tokens