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.
npx agentmods add skills/watt-mind/factory/factory-handoffnpx skills add watt-mind/factory --skill factory-handoffgit clone --depth 1 https://github.com/watt-mind/factoryWrote 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.
[](https://agentmods.dev/skills/watt-mind/factory/factory-handoff)<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="Measured on agentmods" height="20"></a>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 5.1 | $0.00047 | $0.00786 |
| Opus 5 | $0.00023 | $0.00393 |
| Sonnet 5 | $0.00009 | $0.00157 |
| Haiku 4.5 | $0.00005 | $0.00079 |
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 yesterday.
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.
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
-
Resolve the current repository through Factory's configured repo registry.
-
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. -
If it is not ready, apply the
ticket-specskill: 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. -
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 useTEAM-N. -
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:
- Search for duplicates and use the existing ticket when one covers the request.
- 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. - Use
ticket-specto fill derivable gaps. If intent or credentials are missing, leave it in Triage and report what is needed; do not hand it off yet. - Once the ticket is
Todo+ai:agent-ready+ unassigned, invokefactory handoffas above.
Checking run progress and traces
When an operator asks for the status of a handed-off ticket or wants to inspect execution:
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.
- yesterday First seen · 73 lines · 47 tokens per session scan A 139b10c02c94
factory-handoff is a skill published in the GitHub repository watt-mind/factory (12 stars, last pushed 2d ago), licensed Apache-2.0. It adds 47 tokens to every session and 786 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
seeds-issue-audit
Audit and triage open Seeds (sd) issues — find which can be closed, auto-close high-confidence completed ones, and report borderline cases. Activate for prompts like "audit open issues", "which seeds issues can be closed", "clean up the issue tracker", "triage the seeds backlog".
good-first-issue-batch
File a batch of contributor-ready GitHub issues from the seeds backlog, re-verifying every candidate against HEAD first so no dead issue reaches a contributor. Activate for prompts like "file some good first issues", "open a batch of GFIs", "publish backlog issues to GitHub", "find contributor-ready work", or after an…
os-eco-dep-sync
Bump warren onto the latest published @os-eco/ versions across package.json + bun.lock and the Dockerfile CLI pins, then run the gates and open a PR. Use when checking if warren is on the newest burrow/plot/canopy/seeds/mulch/sapling.
release
Prepare, cut, and verify a warren release — tracker audits, version bump, CHANGELOG curation, ROADMAP update, push, then watch the pipeline through to published artifacts.
warren-dogfood-pipeline
Full prioritize → dispatch → shepherd → track pipeline against the live warren instance. Audits the seeds backlog around a focus theme, dispatches the surviving issues to warren agents one at a time, babysits the resulting PRs to merge (update-branch, conflict-repair runs, auto-merge), and closes the loop in the…
atelier
Operate the Atelier software factory (the ADW engine stamped into this repo's adws/). Use when the user says /atelier, wants to create / run / update an ADW or workflow, manage the agent roster in sssf.config.yaml, keep the engine current, or observe running agent workflows. Keywords - atelier, software factory, ADW…