What is elemctl CLAUDE.md?

Repository-specific instructions for elemctl, a command-line tool, MCP server, and Python library for controlling the 1C:Enterprise Element Console API. They describe how code, comments, user messages, and documentation should be written.

Use them when editing elemctl source code, tests, tools, editors, documentation, help text, or user-facing messages. They guide English technical text and the places where Russian is required.

They prevent contributors from using inconsistent languages, typography, names, or translations. They also clarify which Russian terms are official platform identifiers and must stay unchanged.

elemctl CLAUDE.md — Instructions file by keyfire

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/keyfire/elemctl/claude-md

Clone the repo

git clone --depth 1 https://github.com/keyfire/elemctl

Per session 703 This file is loaded in full into every session.

When invoked 703 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.

Model	Per session	Once invoked
Fable 5	$0.00703	$0.00703
Opus 5	$0.00351	$0.00351
Sonnet 5	$0.00141	$0.00141
Haiku 4.5	$0.00070	$0.00070

Measured yesterday against content hash dba20c006588, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

elemctl 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 yesterday.

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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository conventions

elemctl is a public, international project: a CLI, an MCP server and a Python library for the 1C:Enterprise.Element Console API v2. The contract the tool implements lives in docs/SPEC.md (with a Russian twin, docs/SPEC.ru.md); this file records how the repository itself is written.

Language of the code

Code is English. Comments, docstrings, identifiers, test names – all of them, in src/, tests/, tools/ and editors/. The code is read by people who do not speak Russian.
Russian stays where it faces the user: the i18n message catalog (src/elemctl/i18n.py), argparse help strings, user-facing strings, the MCP tool descriptions and the server INSTRUCTIONS literal – an agent reads those in Russian.
Platform identifiers are quoted as they are: Проект.yaml, Ресурсы, Имя, Поставщик, ВидПроекта, ОбластьВидимости and the like are real keys and file names, not text to translate. The same goes for the Russian data of test fixtures.

Typography

Applies to English text as well:

dashes – en dash – (U+2013) only, never an em dash;
quotes – straight " and ', never guillemets or curly quotes;
ellipsis – three dots ..., never the … character.

Nothing internal

The repository is public. It must not carry internal project identifiers, stand names, real application or assembly ids, internal hosts, issue keys or machine paths – not in the code, not in comments, not in test fixtures. Neutral examples: vendors acme, globex, applications crm-dev, demo-app.

Documentation pairs

English and Russian pages go together: README.md / README.ru.md, docs/SPEC.md / docs/SPEC.ru.md, CHANGELOG.md / CHANGELOG.ru.md and the rest of docs/*.md. A change to one side without the other is an unfinished change. Two pages are generated – never edit them by hand:

docs/cli.md / docs/cli.ru.md – python scripts/gen-cli-docs.py;
docs/changelog.md / docs/changelog.ru.md – node scripts/sync-docs.mjs.

Read the full file on GitHub · 57 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.

yesterday First seen · 57 lines · 703 tokens per session scan A dba20c006588

Subscribe to this mod's changes

elemctl CLAUDE.md is an instructions file published in the GitHub repository keyfire/elemctl (4 stars, last pushed 2d ago), licensed MIT. It adds 703 tokens to every session, about $0.0035 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.

Backend and APIs Testing Writing and docs

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

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 · 6,785 tokens

elemctl CLAUDE.md