claude-dev-stack CLAUDE.md

claude-dev-stack CLAUDE.md is an instructions file for coding agents from Enakoneschniy/claude-dev-stack. It costs 405 tokens per session, scanned A, original, MIT.

Project instructions for claude-dev-stack, including language rules, automatic task routing, a knowledge base, session records, planning, and commit conventions. They require communication in Russian while code and commits use English.

In plain words
What is it for?
Use them when starting or ending work on this project, switching projects, following its planning system, updating its knowledge base, or creating commits.
Why use it?
They keep work consistent across sessions and projects by loading the right context, recording decisions and issues, and selecting the appropriate workflow automatically.

Instructions file

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.

agentmods
npx agentmods add instructions/enakoneschniy/claude-dev-stack/claude-md
Clone the repo
git clone --depth 1 https://github.com/Enakoneschniy/claude-dev-stack

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 claude-dev-stack CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/enakoneschniy/claude-dev-stack/claude-md.svg)](https://agentmods.dev/instructions/enakoneschniy/claude-dev-stack/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/enakoneschniy/claude-dev-stack/claude-md"><img src="https://agentmods.dev/badge/instructions/enakoneschniy/claude-dev-stack/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 405 This file is loaded in full into every session.
When invoked 405 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00405 $0.00405
Opus 5 $0.00202 $0.00202
Sonnet 5 $0.00081 $0.00081
Haiku 4.5 $0.00040 $0.00040

Measured 4d ago against content hash b39d584e8fc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-dev-stack 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 4d 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.

CLAUDE.md · 41 lines

What it actually says

CLAUDE.md — Project Intelligence Layer

Language

Общение на русском. Код и коммиты на английском.

Auto-Routing (IMPORTANT)

Do NOT ask which tool to use. Determine automatically:

  • First message in session → load context (session-manager)
  • Development task → GSD (/gsd:quick for small, /gsd:plan-phase for large)
  • Research/comparison → deep-research
  • Different project mentioned → project-switcher
  • End of work ("done", "всё", "хватит") → session-manager /end If .planning/ exists → project uses GSD, respect its state.

Knowledge Base

Before starting, ALWAYS read:

  1. cat /Users/eugenenakoneschniy/vault/projects/claude-dev-stack/context.md
  2. Last 3 session logs from /Users/eugenenakoneschniy/vault/projects/claude-dev-stack/sessions/

Session Protocol

  • Start: read context + propose continuation from last TODO
  • During: ADR for decisions, Known Issues for bugs, shared/patterns.md for reusables
  • End ("done"/"всё"/"хватит"): create session log, update context.md

Code Style

  • Commits: conventional commits (feat:, fix:, chore:)
  • Code and comments in en
  • Communication in ru

Rules

  • Do NOT delete code without explicit request
  • On .env change → update .env.example
  • On new dependency → explain in session log

References

  • Vault: /Users/eugenenakoneschniy/vault/
  • Registry: /Users/eugenenakoneschniy/vault/meta/project-registry.md
  • Patterns: /Users/eugenenakoneschniy/vault/shared/patterns.md
  • Skills: /Users/eugenenakoneschniy/.claude/skills/
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. 4d ago First seen · 41 lines · 405 tokens per session scan A b39d584e8fc2

Subscribe to this mod's changes

claude-dev-stack CLAUDE.md is an instructions file published in the GitHub repository Enakoneschniy/claude-dev-stack (5 stars, last pushed 4mo ago), licensed MIT. It adds 405 tokens to every session, about $0.0020 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.