An interactive workflow for reviewing Linear issues, which are tracked work items, against the actual codebase. It lists issues and checks whether their implementation matches their current status.

Use it to review assigned issues, group them by project, inspect priorities, and verify selected items in a codebase.

It helps reveal issues marked as in progress even though the code is complete, incomplete, or missing the expected work.

triage — Command by alleneubank

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.

agentmods

npx agentmods add commands/alleneubank/claude-code/triage

Clone the repo

git clone --depth 1 https://github.com/alleneubank/claude-code

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,039 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00025	$0.01039
Opus 5	$0.00013	$0.00519
Sonnet 5	$0.00005	$0.00208
Haiku 4.5	$0.00003	$0.00104

Measured 2d ago against content hash 27b7e9f18fc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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.

commands/triage.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Linear Issue Triage

Interactive triage workflow for Linear issues. Syncs issue states with actual implementation status in the codebase.

Arguments

Parse $ARGUMENTS for:

--team TEAM - Team key (default: from Linear CLI config)
--codebase PATH - Default codebase path for verification
--state STATE - Issue state filter: in_progress (default), backlog, todo, or all

Arguments: $ARGUMENTS

Phase 1: Gather Issues

Fetch issues assigned to the current user:

linear issues list --team TEAM --assignee me --state-type started --include-projects --human-time --all

If --state all was specified, also fetch backlog and todo:

linear issues list --team TEAM --assignee me --state-type unstarted --include-projects --human-time --all

Phase 2: Present Summary

Group issues by project and display:

Issue count per project
High priority items (P0, P1, P2) highlighted
Issues without projects (orphans)

Format as a scannable table:

| ID | Title | State | Priority | Project | Updated |

Phase 3: Interactive Triage

For each issue (or batch selected by user), offer these actions via AskUserQuestion:

Verification Options

Verify in codebase - Spawn Explore agent to check implementation
Mark done - Issue is complete
Mark canceled - Issue is no longer needed
Move to backlog - Deprioritize
Skip - No action needed
Set blocker - This issue blocks another

Codebase Verification

When user selects "Verify in codebase":

Ask which codebase to check (use --codebase default if provided)

Fetch issue details:

linear issue view ISSUE_ID --fields identifier,title,description,comments --json

Spawn Explore agent with Task tool:

subagent_type: Explore
prompt: |
  Check if Linear issue ISSUE_ID is implemented in CODEBASE_PATH.

  Issue: TITLE
  Description: DESCRIPTION

  Look for:
  - Code implementing this feature/fix
  - Tests covering the functionality
  - Any TODOs or incomplete work

  Report:
  - Implementation status: complete / partial / not started
  - Key files found
  - Evidence summary

Based on findings, propose state change and ask for confirmation

Read the full file on GitHub · 155 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.

2d ago First seen · 155 lines · 0 tokens per session scan A 27b7e9f18fc0

Subscribe to this mod's changes

triage is a command published in the GitHub repository alleneubank/claude-code (52 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 1,039 once invoked, about $0.0001 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.

Code review Productivity

triage

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Linear Issue Triage

Arguments

Phase 1: Gather Issues

Phase 2: Present Summary

Phase 3: Interactive Triage

Verification Options

Codebase Verification

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement