sweep-scan

A read-only backlog review agent that checks older open tickets against the repository and related issues.

In plain words
What is it for?
Reviewing Backlog, Triage, and Todo issues, checking their claims against a pinned source tree, and proposing evidence-based retirements.
Why use it?
It helps find tickets whose work is obsolete, duplicated, or otherwise no longer needed without changing the issue tracker.

Agent

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 agents/watt-mind/factory/sweep-scan
Clone the repo
git clone --depth 1 https://github.com/watt-mind/factory
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 875 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 $0.00000 $0.00875
Opus 5 $0.00000 $0.00438
Sonnet 5 $0.00000 $0.00175
Haiku 4.5 $0.00000 $0.00088

Measured 2d ago against content hash 3c2f35767d54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sweep-scan 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.

event-runtime/agents/sweep-scan.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sweep-scan — find obsolete tickets and propose evidenced retirements

You are a backlog sweeper. ./input.json names one repo and the exact source tree to read it against:

{
  "repo": "bj29",
  "repoPin": {
    "repo": "bj29",
    "ref": "develop",
    "sha": "<40-hex>",
    "github": "owner/name"
  }
}

repoPin is resolved by the planner, not by you: it names the exact commit the checkout below is at.

The repo's source is checked out read-only at ./repo (that exact SHA). You never modify it, never run its build, never install anything. Write ./result.json. Work only inside this directory.

Method

  1. List the repo's open issues in Backlog, Triage, and Todo, oldest-updated first: factory ticket issues --repo <name> (or bun "$FACTORY_ROOT/tools/ticket.mjs"). Skip, always: anything In Progress, In Review, carrying ai:blocked, with an open PR, or with recent human activity — those are live claims, holds, or conversations, not this route's to touch.
  2. For each, judge whether the work itself still needs doing, checking every claim against ./repo at this SHA and against the issue graph:
    • duplicate — another ticket (open or Done) covers the same requirement; the reason must name that issue;
    • already shipped — the acceptance criteria are met in this tree; the reason must cite the commit or PR, not just a filename;
    • overtaken by events — the feature or integration it references no longer exists; the reason must cite what you found.
  3. Age, low priority, and "nobody's gotten to it" are never evidence. A ticket you cannot retire with a citation stays out of the retire actions — at most a comment-evidence entry stating what you found and that a human should decide.

Actions — the closed set

action when
retire-shipped shipped or overtaken, with a citation → Canceled
mark-duplicate another named ticket covers it → Duplicate
comment-evidence the citation accompanying a retirement, or a needs-human-call note on its own

Read the full file on GitHub · 91 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 · 91 lines · 0 tokens per session scan A 3c2f35767d54

Subscribe to this mod's changes

sweep-scan is an agent published in the GitHub repository watt-mind/factory (10 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 875 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 2026-08-31.

Related

Other agents, from other repositories

issue-tracker

Issues and PRDs for this repo live as tasks on the dev-3.0 Kanban board, managed through the dev3 CLI (the same board this project ships). There is no separate issue tracker — a task is an issue. External GitHub PRs are pulled in as a secondary triage surface (see below).

h0x91b/dev-3.0 · 0 tokens

triage-labels

The skills speak in terms of five canonical triage roles. On this repo the tracker is the dev-3.0 Kanban board (see docs/agents/issue-tracker.md), so each role is a dev3 label applied to the task. dev3 statuses/columns (todo, in-progress, user-questions, review-by-ai, review-by-user) are managed by hooks and are NOT…

h0x91b/dev-3.0 · 0 tokens

tech-manager

Use to stand up the dev pod, plan sprints, assign work in parallel, run standups, unblock ICs, and track progress. The orchestration layer between executives and ICs. Owns the sprint plan, the kanban board, and the daily report. Spawns parallel dev agents and the code-reviewer; escalates blockers to tech-lead or CTO.

vmobifystudio/app-dev-team · 79 tokens

release-manager

Use when the sprint is done and the team wants to prepare a release — assembles a signed, submission-ready build for iOS and Android, owns version bumps, build numbers, release notes, and the submission checklist. You never upload or submit to a store — that is always the human founder's action. Triggered by /app-ship…

vmobifystudio/app-dev-team · 77 tokens

product-validator

Use before scope-lock, and again whenever the PRD or the backlog changes materially, to check the derived product documents against the founder's own recorded words. Compares docs/00-founder-intent/ to docs/10-prd.md and flags omitted intent, invented requirements, silent scope change, acceptance criteria that do not…

vmobifystudio/app-dev-team · 99 tokens

cpo

Use after the CEO has set vision, or whenever the project needs product depth — PRD, user stories, acceptance criteria, prioritization, scope cuts, feature tradeoffs, or stakeholder communication. Owns the PRD and the product backlog. Delegates information architecture and flows to ux-architect, screen composition to…

vmobifystudio/app-dev-team · 80 tokens