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/magerko/claude-code-skills/pipelinenpx skills add Magerko/claude-code-skills --skill pipelinegit clone --depth 1 https://github.com/Magerko/claude-code-skillsWrote 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/magerko/claude-code-skills/pipeline)<a href="https://agentmods.dev/skills/magerko/claude-code-skills/pipeline"><img src="https://agentmods.dev/badge/skills/magerko/claude-code-skills/pipeline.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 | $0.04466 |
| Opus 5 | $0.00049 | $0.02233 |
| Sonnet 5 | $0.00020 | $0.00893 |
| Haiku 4.5 | $0.00010 | $0.00447 |
Grade A, and why
pipeline 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 5d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline: проект от идеи до выката
Сегодня: !date +%F. Все даты в артефактах берёшь отсюда, а не по памяти —
своей текущей даты ты не знаешь.
Одиннадцать стадий с жёсткими воротами между ними. Ты ведёшь пользователя по стадиям,
материализуя каждую в файл. Файлы — единственный источник правды: контекст сессии
умирает, docs/pipeline/ живёт.
0. context load — project brief подгружается, не пересказывается
1. idea — что и зачем, в 3–5 предложениях
2. plan + criteria — шаги + явное «готово = ...»
3. risk spikes — только реально неизвестное, код на выброс
4. contracts — модели, сигнатуры, схемы ответов, формат ошибок
5. vertical slice — один сквозной путь end-to-end
6. tasks — атомарные, у каждой свой критерий готовности
7. implementation — по одной задаче за сессию
8. audit — в свежем контексте: тесты + ручные проверки
9. feedback — находки аудита → обратно в brief + decision log
10. release — выкат: пред-запусковые проверки, доступы, бэкапы, откат
Стадии 0–9 — цикл разработки, он повторяется. Стадия 10 проходится не каждый круг, а перед реальной публикацией.
Артефакты
Всё в docs/pipeline/ в корне проекта:
| Файл | Стадия | Природа |
|---|---|---|
state.md |
все | текущая стадия + статус ворот. Обновляй каждый раз |
brief.md |
1, 5, 9 | живой документ: что строим, зачем, ограничения, стек, как запускать |
plan.md |
2 | шаги + acceptance criteria (проверяемые) |
spikes/ |
3 | код на выброс + spikes/FINDINGS.md с ответами |
contracts.md |
4 | модели данных, сигнатуры, схемы, конфиг, ошибки |
tasks.md |
6 | атомарные задачи с DoD-чекбоксами |
audit.md |
8 | отчёт аудита свежим контекстом |
decisions.md |
9 (append) | лог решений: дата, решение, альтернативы, почему |
release.md |
10 | что выкачено, куда, чем проверено, как откатить |
Шаблоны — в references/templates.md. Детали по стадиям — в references/stages.md.
Читай нужный раздел stages.md перед началом стадии, а не по памяти.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 269 lines · 98 tokens per session scan A 6bdaca06e6d5
pipeline is a skill published in the GitHub repository Magerko/claude-code-skills (21 stars, last pushed 22d ago), licensed MIT. It adds 98 tokens to every session and 4,466 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 2026-08-30.
Other skills, from other repositories
daily-coding
Use for everyday coding tasks that involve writing or modifying source code.
Release Checklist
Check release readiness and record a release note. Use for release and rollback requests.
frontend-checklist-global
Use when auditing or improving any frontend codebase against the full Front-End Checklist rule corpus through one entry point.
improve-rule
Use when reviewing or improving a Front-End Checklist rule MDX file to raise its quality score, fix stub prompts, add missing fields, or enrich content with real code examples.
aria-input-field-name
Use when applies to all (except type=hidden), , , and custom form widgets using role=textbox, role=combobox, role=spinbutton, role=searchbox, or role=listbox.
aria-required-children
Use when applies to custom ARIA widgets using composite roles: tablist, list, listbox, menu, menubar, tree, treegrid, grid, rowgroup, row, radiogroup. Use when reviewing components built with div/span elements that replace native HTML list, select, or nav elements.