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/aaddrick/ticketmill/millnpx skills add aaddrick/ticketmill --skill millgit clone --depth 1 https://github.com/aaddrick/ticketmillWhat 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 | $0.00062 | $0.03682 |
| Opus 5 | $0.00031 | $0.01841 |
| Sonnet 5 | $0.00012 | $0.00736 |
| Haiku 4.5 | $0.00006 | $0.00368 |
Grade A, and why
mill 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.
How it starts
The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mill: launch a ticketmill batch run
Runs the ticketmill engine. For each selected GitHub issue: research, contrarian-gated approach and plan, per-task implementation with quality loops, a test loop, PR creation, spec + code review loops, and a squash-merge into a batch integration branch. The run ends with ONE batch PR for a human to review and merge; the engine never merges to the base branch itself.
Hard preconditions: check these IN ORDER before doing anything else
-
The Workflow tool must be available in this session. Check your available tools for a tool named
Workflowthat accepts ascriptPathinput. If it is not available: STOP IMMEDIATELY. Tell the user:The ticketmill engine requires the Claude Code Workflow tool, which is not available in this session/plan. The engine cannot run without it.
NEVER attempt to simulate, approximate, or hand-execute the batch pipeline yourself (no ad-hoc issue implementing, no manual worktree orchestration in place of the engine). The engine's value is its journaling, claims, circuit breakers, and resumability. An inline imitation has none of those and is strictly worse than not running at all.
-
The target repo must have a profile at
<repo-root>/.claude/ticketmill.json. If missing, stop and direct the user to run/ticketmill:mill-initfirst. Do not write a profile ad hoc: mill-init exists to verify the environment (doctor pass) before a profile is trusted. -
Locate the engine script, in this order:
${CLAUDE_PLUGIN_ROOT}/workflows/ticketmill.js(plugin install)<repo-root>/.claude/workflows/ticketmill.js(copied by mill-init)
If neither exists, stop and direct the user to
/ticketmill:mill-init.
Engine-owned paths need a clean root tree
If an issue's fix touches the ticketmill profile (.claude/ticketmill.json), the
agent roster (.claude/agents/**), or the engine copy (.claude/workflows/ticketmill.js,
.claude/scripts/ticketmill/**), check the root working tree before you launch. The
engine works from each issue's own worktree, and that worktree only sees committed
state. Uncommitted edits sitting in the root tree, like a freshly forged agent or a
profile field you just added, are invisible to it.
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.
- 2d ago First seen · 254 lines · 62 tokens per session scan A 95c6b333ff13
mill is a skill published in the GitHub repository aaddrick/ticketmill (15 stars, last pushed 23d ago), licensed MIT. It adds 62 tokens to every session and 3,682 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…