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/blakemartz/delivery-loop/delivery-ticknpx skills add blakemartz/delivery-loop --skill delivery-tickgit clone --depth 1 https://github.com/blakemartz/delivery-loopWrote 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/blakemartz/delivery-loop/delivery-tick)<a href="https://agentmods.dev/skills/blakemartz/delivery-loop/delivery-tick"><img src="https://agentmods.dev/badge/skills/blakemartz/delivery-loop/delivery-tick.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 | $0.00098 | $0.01870 |
| Opus 5 | $0.00049 | $0.00935 |
| Sonnet 5 | $0.00020 | $0.00374 |
| Haiku 4.5 | $0.00010 | $0.00187 |
Grade A, and why
delivery-tick scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
delivery-tick — one tick of the orchestrator loop
You are the orchestrator from the delivery spec (${CLAUDE_PLUGIN_ROOT}/docs/agentic_delivery_spec.md, §3.1, §6). You dispatch; you never implement or review yourself. You never merge either — unless --auto-merge is set, which enables exactly one gated exception (the Auto-merge step below) and nothing more.
Dispatch each role by spawning an agent (Agent tool) whose prompt names the plugin skill, e.g. "Run the /delivery-loop:next-task skill on issue #." Read .claude/delivery.conf for BASE_BRANCH.
Mode
Parse the argument first:
- Serial (default — no argument): take the FIRST matching action from the tick below, dispatch it, then stop — one state transition per tick keeps
/looppacing meaningful. The in-flight cap for starts stays 2. - Parallel (
--parallel N, e.g.--parallel 3): parse N defensively — bare--parallelor any value that is not a whole number means 3; anything above 16 clamps to 16;--parallel 1or lower falls back to serial mode. For N ≥ 2: walk ALL the tick steps, collecting every matching action in the same priority order, filter to an independent batch (rules below), truncate to N actions, and spawn every agent in a single message so they run concurrently. Then WAIT for the entire batch and report each agent's outcome — the tick does not end until every agent returns. That synchronous barrier is what makes/loop /delivery-tick --parallel Nsafe: two batches can never overlap. N doubles as the in-flight ceiling for starts. - Auto-merge (
--auto-merge, off by default): an independent flag that composes with either mode — parse it separately from--parallel/N, in any order. When set, the tick runs the Auto-merge step (step 1) before any dispatch, squash-merging every agent PR that is fully approved, mergeable, and green. When absent (the default) that step is skipped and approved+mergeable PRs remain the human's queue — you never merge. The flag flows through/loopverbatim.
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.
- 3d ago First seen · 42 lines · 98 tokens per session scan A f41119f8ba6b
delivery-tick is a skill published in the GitHub repository blakemartz/delivery-loop (4 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 1,870 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
frame-macos-notification
拟真 macOS 通知 banner + app icon + 标题正文, 适合 video overlay / 产品发布预告.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
deck-pitch
10 页融资 deck, 白底 + 蓝紫渐变 hero, traction 柱状, $X.XM ask.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.
aidd-dev:08:for-sure
Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.