project-harness-bootstrap

project-harness-bootstrap is a skill for Claude Code from KirillSachkov/sachkov-stack. It costs 93 tokens per session (1,880 once invoked), scanned A, original, MIT.

A setup guide for adding an agent harness to a software project. An agent harness is the project-specific rules, checks, and workflow that help coding agents work consistently.

In plain words
What is it for?
Use it when starting agent-driven work in a repository with no AGENTS.md, .harness directory, checks, or harness lock file. It also checks whether an existing harness is missing or outdated.
Why use it?
It gives projects without a complete harness a defined foundation before development work begins, including tests, review, verification, and owner approval.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Good fit Use it when starting agent-driven work in a repository with no AGENTS.md, .harness directory, checks, or harness lock file. It also checks whether an existing harness is missing or outdated.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kirillsachkov/sachkov-stack/project-harness-bootstrap
Install

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.

Any agent
npx skills add KirillSachkov/sachkov-stack --skill project-harness-bootstrap
Clone the repo
git clone --depth 1 https://github.com/KirillSachkov/sachkov-stack

Made for: Claude Code.

Wrote 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.

agentmods badge for project-harness-bootstrap

README.md
[![agentmods](https://agentmods.dev/badge/skills/kirillsachkov/sachkov-stack/project-harness-bootstrap/github.svg)](https://agentmods.dev/skills/kirillsachkov/sachkov-stack/project-harness-bootstrap)
Your own site
<a href="https://agentmods.dev/skills/kirillsachkov/sachkov-stack/project-harness-bootstrap"><img src="https://agentmods.dev/badge/skills/kirillsachkov/sachkov-stack/project-harness-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.

agentmods 80×15 button for project-harness-bootstrap

Your own site · 80×15
<a href="https://agentmods.dev/skills/kirillsachkov/sachkov-stack/project-harness-bootstrap"><img src="https://agentmods.dev/badge/skills/kirillsachkov/sachkov-stack/project-harness-bootstrap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,880 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00093 $0.01880
Opus 5.5 $0.00037 $0.00752
Sonnet 5.5 $0.00019 $0.00376
Haiku 4.5 $0.00009 $0.00188

Measured 1mo ago against content hash 31b9d3bdb52b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project-harness-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 1mo 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.

skills/project-harness-bootstrap/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Harness Bootstrap

Правило владельца (2026-07-19): у каждого проекта свой полноценный харнес поверх общего глобального. Агент, начавший работу в репозитории без харнеса, сначала строит харнес вместе с владельцем и только потом ведёт задачу через него. Молча работать без харнеса нельзя.

Харнес больше не копипастится с эталонного проекта. Он разворачивается из версионируемого пакета harness/ в мозге, и расхождение проекта с пакетом считается механически. Это и есть разница с прошлой версией скилла.

Глобальный контракт остаётся каноном: проектный адаптер переопределяет маршруты (трекер, базовая ветка, команды, CI), но не ослабляет ядро coding-task-pipeline (изоляция, TDD, независимое ревью, свежая верификация, отчёт владельцу, мерж по его команде).

Шаг 0. Посмотреть, что уже есть

Проверяй, не предполагай. Расположение пакета получай через harness/bin/brain-root, не хардкодом пути.

BRAIN=$("$HOME/.claude/hooks/harness-detect.sh" >/dev/null 2>&1; \
        for c in "$AGENT_BRAIN" "$HOME/dev/brain" "$HOME/brain"; do \
          [ -n "$c" ] && [ -f "$c/AGENTS.md" ] && echo "$c" && break; done)
python3 "$BRAIN/harness/bin/harness" diff <repo>

Три исхода:

  • харнеса нет — идём дальше по этому скиллу;
  • дрейф — харнес есть, но отстал: покажи владельцу вывод diff и предложи harness update, полный bootstrap не нужен;
  • совпадает с пакетом — ничего не строим, идём работать.

Никогда не пересобирай молча то, что уже стоит.

Шаг 1. Интервью с владельцем

Спроси один раз, одним компактным списком, и только то, чего нельзя вычитать из репозитория. Выведенные факты подтверждай, а не переспрашивай открытым вопросом.

  • что за проект и стадия (активная разработка, поддержка, эксперимент);
  • стек и версии (предзаполни из манифестов и лок-файлов);
  • точные команды: setup, run, test, lint, build;
  • базовая ветка и политика мержа (по умолчанию: агент доводит до merge-ready, мерж командует владелец);
  • трекер: свой трекер проекта, задачи мозга, или пока никакого;
  • границы: что можно всегда, что спросить сначала, что не трогать;
  • маршрут деплоя или релиза и доступ к проду, если он есть;
  • Definition of Done для типичной задачи.

Read the full file on GitHub · 135 lines

Changes

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.

  1. 1mo ago First seen · 135 lines · 93 tokens per session scan A 31b9d3bdb52b

Subscribe to this mod's changes

project-harness-bootstrap is a skill published in the GitHub repository KirillSachkov/sachkov-stack (4 stars, last pushed 2mo ago), licensed MIT. It adds 93 tokens to every session and 1,880 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens