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/ticket-specnpx skills add watt-mind/factory --skill ticket-specgit 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/ticket-spec)<a href="https://agentmods.dev/skills/watt-mind/factory/ticket-spec"><img src="https://agentmods.dev/badge/skills/watt-mind/factory/ticket-spec.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 | $0.00045 | $0.01274 |
| Opus 5 | $0.00023 | $0.00637 |
| Sonnet 5 | $0.00009 | $0.00255 |
| Haiku 4.5 | $0.00005 | $0.00127 |
Grade A, and why
ticket-spec 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 today.
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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specifying a ticket
A ticket is dispatchable only when it carries all five sections (docs/protocol.md §5). Most of that is derivable from the codebase, not from the human: Source File Pointers, Owned Paths, and Verification Command are search-and-read problems. Acceptance Criteria is usually the problem restated observably. Only genuine product intent needs a person.
So the job is not "spec everything" — it's sorting tickets into three piles and handling the first two yourself.
The three outcomes
Auto-specifiable — the problem is unambiguous and the answer is in the code. Explore read-only, write all five sections, promote to Todo + ai:agent-ready plus a tier:* label.
Sizing the tier:* label
Closed vocabulary, at most one per ticket: tier:light, tier:standard, tier:strong.
tier:light— one or two files inOwned Paths, no path underescalate_paths(config/repos.yaml),type:docs/ copy / config-value changes, or atype:bugwith a repro and a one-line expected fix.tier:strong— any path underescalate_paths(auth, payments, migrations, prod infra),type:security, cross-package or architecture work (area:architecture), anything whose acceptance criteria say "design"/"decide" or list open questions, or a ticket that previously failed verification.tier:standard— everything else (the default).
If the ticket already carries a tier:* label, leave it — don't recompute or overwrite an existing tier decision. State the tier and why in the promotion comment.
Answerable from written decisions — intent is unclear but already recorded: the repo's docs/product-decisions.md, docs/, the Linear project Overview, or a prior ticket in the same area. Resolve it, cite where you found it in the ticket so the next agent doesn't re-litigate, then promote.
Genuinely needs a human — a real product decision, a missing credential, a priority call. Leave in Triage, comment the specific question phrased so one reply unblocks it, and batch every such question into a single notification at the end of the run. Never a ping per ticket.
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.
- today First seen · 53 lines · 45 tokens per session scan A 6cd7e613072a
ticket-spec is a skill published in the GitHub repository watt-mind/factory (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 1,274 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…