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 skills add Avalon-27reg/smyslokod-starter --skill project-bootstrapgit clone --depth 1 https://github.com/Avalon-27reg/smyslokod-starterWrote 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/avalon-27reg/smyslokod-starter/project-bootstrap)<a href="https://agentmods.dev/skills/avalon-27reg/smyslokod-starter/project-bootstrap"><img src="https://agentmods.dev/badge/skills/avalon-27reg/smyslokod-starter/project-bootstrap/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/avalon-27reg/smyslokod-starter/project-bootstrap"><img src="https://agentmods.dev/badge/skills/avalon-27reg/smyslokod-starter/project-bootstrap.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00081 | $0.03201 |
| Opus 5.5 | $0.00032 | $0.01280 |
| Sonnet 5.5 | $0.00016 | $0.00640 |
| Haiku 4.5 | $0.00008 | $0.00320 |
Grade A, and why
project-bootstrap 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 6d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: project-bootstrap
Старт проекта на шаблоне smyslokod-starter от того, что у пользователя уже есть: идея, код или документ архитектуры. Результат - ядро business/INDEX.md, стек в CLAUDE.md и первый план результата, одобренный пользователем. Обязательной анкеты нет: вопросы задаются только о пробелах, которые меняют ближайшее решение.
Общий процесс - docs/workflow.md. Этот скилл - подробный порядок для входов «есть идея», «есть код» и «есть архитектура» из раздела 1 процесса.
Когда применять
- Пользователь пришёл с идеей, кодом или документом архитектуры, а ядро
business/INDEX.mdв основном «неизвестно». - Пользователь просит адаптировать шаблон или начать проект на нём.
Когда НЕ применять
- В
plans/есть план со статусом не «завершён» и не «отменён» - это вход «Продолжаем» (docs/workflow.md, раздел 1). - Пользователь пришёл с конкретной задачей, не связанной со стартом, - сначала она (
docs/workflow.md, раздел 1). - Идеи ещё нет - это вход «Нет идеи» (
docs/workflow.md, раздел 1): сначала направление, затемdocs/prompts/grill-idea.md.
Продолжение после перерыва
Отдельного журнала нет, состояние восстанавливается по фактам: что записано в ядре business/INDEX.md и в созданных разделах, есть ли черновик плана в plans/. Перечитай их, скажи одной фразой, что уже есть, и продолжи с первого незакрытого шага.
Шаг 1. Собери факты
Прочитай просьбу пользователя, business/INDEX.md, разделы 1-2 CLAUDE.md, docs/architecture/overview.md и plans/. Проверь, есть ли код в корне: package.json, pyproject.toml, requirements.txt, go.mod, Cargo.toml, папки src/ или app/. Документ архитектуры пользователь мог приложить или назвать путь к нему.
Путь: ИДЕЯ, если кода и архитектуры нет; IMPORT, если есть код или документ архитектуры (раздел «Режим IMPORT» ниже).
Готово, когда ты одной фразой сказал пользователю, что понял, и назвал путь. Пользователь может поправить.
Шаг 2. Приватность
До записи первого бизнес-факта пройди проверку из .claude/rules/security.md, раздел «Публичный репозиторий и business/». Для публичного репозитория там же - отдельный коммит .gitignore и снятия business/ с учёта: это единственный коммит до одобрения плана, и только с согласия пользователя.
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.
- 6d ago Changed · -88 lines · -18 tokens per session 57055543e274
- 1mo ago First seen · 227 lines · 99 tokens per session scan A fb6017c7985a
project-bootstrap is a skill published in the GitHub repository Avalon-27reg/smyslokod-starter (1 stars, last pushed 7d ago), licensed MIT. It adds 81 tokens to every session and 3,201 once invoked, about $0.0003 per session on Opus 5.5. 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
architect
Produces Alon's design-doc system before code: SOURCEOFTRUTH.md, ARCHITECTUREROADMAP.md, TODOWORKFLOW.md, CLAUDE.md, plus a modular docs/architecture set for larger projects. Model first: data and invariants before framework, every invariant enforced at two boundaries, failure paths designed as deliberately as happy…
context
CONTEXT: Cognitive Order Normalized in Transformer EXtract Truncated. Cross-model context handoff via Progressive Density Layering, MLDoE expert compression, Japanese semantic density, and Negentropic Coherence Lattice validation. Creates portable carry-packets that transfer cognitive state between AI sessions. Use…
ponytail
Forces the laziest solution that actually works: YAGNI, reuse before new code, stdlib before custom, native platform before dependencies, one line before fifty. Three levels — lite (name the lazier alternative, build what's asked), full (ladder enforced, default), ultra (YAGNI extremist, challenge the requirement…
ask-the-council
Convenes a panel of opinionated Claude advisors, each with a distinct mandate and a forbidden move so they genuinely diverge, then a Chairman synthesis that commits to one recommendation with the decisive tradeoff and the strongest dissent named.
review-swarm
Local, free, multi-specialist review of a diff: parallel Claude subagents for correctness, security/trust boundaries, data/perf, architecture-altitude, ponytail-simplicity, and tests/failure-paths, each non-trivial finding adversarially verified before being kept, deduped, and ranked into a Blockers / Should-fix /…
up-to-date
Preflight sync and situational brief before repo work: fetches origin, reports ahead/behind divergence (with a no-upstream/detached-HEAD fallback), recent commits, open PRs and issues touching the work, and dirty-tree warnings, then names one recommended first action. Read-only by default — never pulls, rebases…