LastHumanCommit: Instructions file for Claude Code

CLAUDE.md

LastHumanCommit CLAUDE.md is an instructions file for Claude Code from megamen32/LastHumanCommit. It costs 2,417 tokens per session, scanned A, a copy of LastHumanCommit AGENTS.md, MIT.

A set of project instructions for how an agent should inspect and work in a repository. It covers worktrees, which are separate working copies of a code repository, and temporary files.

In plain words
What is it for?
Checking repository state, choosing the right workspace, handling worktrees, and storing temporary files under the project.
Why use it?
It reduces accidental work in the wrong branch or folder and keeps temporary project material organized.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is megamen32/LastHumanCommit's own configuration. It tells Claude Code how to work on LastHumanCommit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything LastHumanCommit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to megamen32/LastHumanCommit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/megamen32/LastHumanCommit/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/megamen32/LastHumanCommit

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 LastHumanCommit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/megamen32/lasthumancommit/claude-md/github.svg)](https://agentmods.dev/instructions/megamen32/lasthumancommit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/megamen32/lasthumancommit/claude-md"><img src="https://agentmods.dev/badge/instructions/megamen32/lasthumancommit/claude-md/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 LastHumanCommit CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/megamen32/lasthumancommit/claude-md"><img src="https://agentmods.dev/badge/instructions/megamen32/lasthumancommit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,417 This file is loaded in full into every session.
When invoked 2,417 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.02417 $0.02417
Opus 5.5 $0.00967 $0.00967
Sonnet 5.5 $0.00483 $0.00483
Haiku 4.5 $0.00242 $0.00242

Measured today against content hash 5dede43eaa41, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

LastHumanCommit CLAUDE.md 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 today.

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.

Origin

This is a copy

100% identical to LastHumanCommit AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Last Human Commit 1.4

Работай от обычного запроса пользователя до проверенного результата. Для инженерной задачи LHC включается сам: пользователь не выбирает режим, роль или slash-команду. Простой вопрос, перевод и запрос статуса не запускают разработку.

Понять и сделать

Из голосового или неточного запроса восстанови смысл по текущему разговору и коду. Сохрани исходную цель и последние поправки. Уточняй только неоднозначность, которая меняет результат или последствия действия; уже известное не спрашивай заново. Выбери кратчайший рабочий путь и сразу проверь его на реальном сценарии.

Маленькую задачу делай напрямую. Для сложной используй ровно те исследования, план, архитектурный разбор и независимые проверки, которые помогают принять решение. Сильную модель используй для сложного выбора, дешёвую для понятной работы; считай стоимость всего результата, включая передачу контекста и переделки. В большом неоднозначном изменении сохрани независимые тестирование и review. Роли — доступные инструменты, а не очередь обязательных церемоний.

Для долгой работы достаточно одной короткой записи в .agents/tasks/: исходный запрос, результат, последние решения, что готово и следующий шаг. После сжатия контекста или возобновления сначала сверяй эту запись с текущим кодом и поправками пользователя. Планы и зависимости добавляй по мере необходимости. Навыки GSD можно использовать как методы, не запуская второй полный workflow.

Осязаемый результат до кода

До изменения сформулируй: кто и какую реальную задачу решает, что раньше не получалось, что будет получаться после и где это можно попробовать руками. Ошибка исчезла, новая функция работает, интерфейс позволяет сделать нужное; для API/CLI — реальный вызов и результат. SHA, новые файлы и ожидание соседей — средства, не бизнес-результат. Для бага сразу TDD: воспроизведи сбой проверкой RED, затем исправь до GREEN и проверь исходный сценарий. Код каждого шага должен вести к этой наблюдаемой разнице.

Read the full file on GitHub · 151 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. today Changed · +2 lines · +56 tokens per session 5dede43eaa41
  2. 2d ago Changed · -226 lines · -2,061 tokens per session c9773840b79a
  3. 1mo ago Changed · +6 lines · +73 tokens per session 66080a164df0
  4. 1mo ago Changed · +60 lines · +772 tokens per session e19bfd472a7c
  5. 1mo ago Changed · +35 lines · +470 tokens per session 68507c025289
  6. 1mo ago Changed · +51 lines · +585 tokens per session 4fda7c8f6d3f
  7. 1mo ago First seen · 223 lines · 2,522 tokens per session scan A 317d75b8e73c

Subscribe to this mod's changes

LastHumanCommit CLAUDE.md is an instructions file published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed yesterday), licensed MIT. It adds 2,417 tokens to every session, about $0.0097 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to LastHumanCommit AGENTS.md, differing in 0 lines, and is treated as a copy.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,649 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,257 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,159 tokens