factory-report

A read-only status report for a software delivery queue managed in Linear, a tool for tracking issues and work.

In plain words
What is it for?
It reports ticket counts, work ready to start, blocked items, open pull requests waiting for merging, and the age and reply status of blocked holds.
Why use it?
It shows where tickets stand across repositories without requiring someone to combine queue and blocked-work information manually.

Command

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/watt-mind/factory/factory-report
Clone the repo
git clone --depth 1 https://github.com/watt-mind/factory
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 574 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.

ModelPer sessionOnce invoked
Fable 5 $0.00022 $0.00574
Opus 5 $0.00011 $0.00287
Sonnet 5 $0.00004 $0.00115
Haiku 4.5 $0.00002 $0.00057

Measured 2d ago against content hash bb849a376fde, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

factory-report 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.

plugins/core/commands/factory-report.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Give a snapshot of where the factory pipeline stands, across Linear, right now. Read-only — this never claims, triages, or dispatches anything.

1. Resolve scope

Default: every repo in config/repos.yaml. $ARGUMENTS, if present, names one repo (matches factory queue --repo <name>'s matching).

2. Gather

From the factory checkout (or any cwd with factory on PATH):

factory queue --repo <repo>      # omit --repo for every configured repo
factory digest --repo <repo>     # omit --repo for every configured repo

queue gives per-repo counts (Triage, Todo-not-ready, READY to dispatch, In Progress, In Review, Blocked, Done/total) plus which tickets are startable right now and how many open PRs are waiting on merge. digest lists every ai:blocked hold with its age and whether a reply has landed (which means the next triage tick will re-examine it). Both are cheap, read-only, and already read the same queue snapshot the pipeline itself uses — don't re-derive counts by querying Linear directly.

3. Report

Synthesize, don't just relay raw terminal output (the ANSI coloring won't survive into chat). Structure:

  • Headline — total tickets across scope, and the one-line pipeline constraint: is it starved for specification (deep Triage, empty ready queue), starved for dispatch slots (ready tickets but no free workers), or clear?
  • Per-repo table — repo, Triage, Todo-not-ready, Ready, In Progress, In Review, Blocked, Done/total. Flag any repo where Triage is unusually deep (>20) or Ready sat nonzero with zero free slots.
  • Ready to work now — the startable tickets queue printed, grouped by repo, so this doubles as "what can we work next."
  • Needs a human — every held ticket from digest, oldest first, with its question excerpt; call out any marked ANSWERED since those are one triage tick away from unblocking, not stuck.
  • Awaiting review/merge — repos with nonzero In Review or open PRs.

Close with one line: if there's a clear next action (/factory-triage, /factory-work, /factory-merge, or a specific held ticket that needs an answer), name it — but don't run it. That's /factory-next's job, not this command's.

Read the full file on GitHub · 35 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 · 35 lines · 22 tokens per session scan A bb849a376fde

Subscribe to this mod's changes

factory-report is a command published in the GitHub repository watt-mind/factory (10 stars, last pushed 2d ago), licensed Apache-2.0. It adds 22 tokens to every session and 574 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 2026-08-31.