agentmods.dev

factory-handoff

factory-handoff is a skill for Claude Code from watt-mind/factory. It costs 47 tokens per session (786 once invoked), scanned A, original, Apache-2.0.

A handoff skill for sending one fully specified development ticket to a central Factory system over SSH.

In plain words
What is it for?
Use it to validate a ticket, add only codebase-derived details when possible, and dispatch it to the configured repository.
Why use it?
It provides a controlled way to delegate ready-to-build work without starting implementation in the current session.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the core plugin — 2 skills, 13 commands, 4 agents shipped together

not rated 19repo 18d ago A scan SkillSpector: pass 47 tokens original Apache-2.0

Good fit Use it to validate a ticket, add only codebase-derived details when possible, and dispatch it to the configured repository.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/watt-mind/factory/factory-handoff
View source ↗ watt-mind/factory watt-mind.github.io
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.

Any agent
npx skills add watt-mind/factory --skill factory-handoff
Clone the repo
git clone --depth 1 https://github.com/watt-mind/factory

Made for: Claude Code.

Or install core, the plugin that ships this one along with the rest of its 2 skills, 13 commands, 4 agents.

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 factory-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/watt-mind/factory/factory-handoff/github.svg)](https://agentmods.dev/skills/watt-mind/factory/factory-handoff)
Your own site
<a href="https://agentmods.dev/skills/watt-mind/factory/factory-handoff"><img src="https://agentmods.dev/badge/skills/watt-mind/factory/factory-handoff/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 factory-handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/watt-mind/factory/factory-handoff"><img src="https://agentmods.dev/badge/skills/watt-mind/factory/factory-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 786 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00047 $0.00786
Opus 5.5 $0.00019 $0.00314
Sonnet 5.5 $0.00009 $0.00157
Haiku 4.5 $0.00005 $0.00079

Measured 1mo ago against content hash 139b10c02c94, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

factory-handoff 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 1mo 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/skills/factory-handoff/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Remote Factory handoff

Handoff means capture/specify here, execute centrally. Never claim the ticket, create a worktree, spawn an implementation subagent, or begin the implementation in this session.

Existing ticket identifier

  1. Resolve the current repository through Factory's configured repo registry.

  2. Read the ticket and confirm it is dispatchable: Todo, ai:agent-ready, unassigned, and complete under the five-section protocol (Problem & Context, Acceptance Criteria, Source File Pointers, Owned Paths, Verification Command). Do not "repair" an ambiguous ticket by guessing.

  3. If it is not ready, apply the ticket-spec skill: explore read-only, complete only derivable sections, verify the command exists/runs, and promote only when the specification is falsifiable. A genuine product decision remains Triage and is not handed off.

  4. Run the mechanical client with the canonical ticket identifier:

    factory handoff --repo <configured-short-name> <ticket>

    The repo flag may be omitted when cwd is inside the configured checkout or one of its worktrees. GitHub tickets use OWNER/REPO#N; Linear tickets use TEAM-N.

  5. Return the machine receipt's admission/duplicate disposition, event/proposal/run state, and dashboard URL. A watched/refused result is a safe outcome, not permission to start locally.

Prose request

Follow the existing capture and specification protocols before handoff:

  1. Search for duplicates and use the existing ticket when one covers the request.
  2. Otherwise file exactly one meaningful ticket with source:human, the correct repo/team/project and taxonomy, and the five complete sections only when supported by code evidence.
  3. Use ticket-spec to fill derivable gaps. If intent or credentials are missing, leave it in Triage and report what is needed; do not hand it off yet.
  4. Once the ticket is Todo + ai:agent-ready + unassigned, invoke factory handoff as above.

Checking run progress and traces

When an operator asks for the status of a handed-off ticket or wants to inspect execution:

Read the full file on GitHub · 73 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. 1mo ago First seen · 73 lines · 47 tokens per session scan A 139b10c02c94

Subscribe to this mod's changes

factory-handoff is a skill published in the GitHub repository watt-mind/factory (19 stars, last pushed 18d ago), licensed Apache-2.0. It adds 47 tokens to every session and 786 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.

Autonomous AgentsGit and workflowProject managementagent-orchestrationagentic-workflowsai-agentsautomationbun
Related

Other skills, from other repositories

triage

Triage a GitHub repository's open issues by finding exact duplicates, rejecting evidenceably off-base requests, requesting concrete clarification, applying only existing labels, and opening a linked root-cause issue when multiple reports share one underlying invariant failure. Use when a maintainer asks to triage…

arcee-ai/nac · 65 tokens

github-issue-agent

Agent skill for safe, dry-run-first, deduplicated, root-cause-consolidated, evidence-validated, and secret-redacted logging of repository execution friction into GitHub Issues. USE ONLY for durable repository bugs, execution friction (T1-T3), map debt, and architectural improvements. DO NOT USE for managing git…

richfrem/agent-plugins-skills · 101 tokens

github-issue-backlog-agent

Bridge skill for escalating ephemeral local task scratchpad items (tasks/.md) into durable, taxonomy-validated, evidence-rich GitHub Issues. USE ONLY when promoting a single-session local task into durable repository backlog. DO NOT USE for directly querying/commenting on issues (use github-issue-agent instead).

richfrem/agent-plugins-skills · 69 tokens

github-issue-prioritizer

Automatically ranks GitHub issues (P0-P3) based on friction tier, frequency, and blockages, synchronizing priority labels and GitHub Projects v2 custom fields. USE ONLY when calculating issue priority ranks or generating Projects v2 payload mutations. DO NOT USE for logging issues (use github-issue-agent).

richfrem/agent-plugins-skills · 73 tokens

github-issue-pr-lifecycle-agent

Skill for orchestrating the end-to-end GitHub issue lifecycle flow: Issue -> Worktree -> Implementation -> PR Creation -> Resolution Closure. USE ONLY when running or dry-running full lifecycle orchestration for resolving an issue with a PR. DO NOT USE for isolated worktree management only (use…

richfrem/agent-plugins-skills · 85 tokens

project-flow-ops

CIEL's coordination layer for triaging issues, PRs, and tasks across GitHub and internal tracking systems (e.g., Linear).

jxoesneon/Ciel · 33 tokens