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 agentmods add instructions/dmitriyoproii-pixel/claude-code-secrets-guard/claude-mdgit clone --depth 1 https://github.com/dmitriyoproii-pixel/claude-code-secrets-guardWrote 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/instructions/dmitriyoproii-pixel/claude-code-secrets-guard/claude-md)<a href="https://agentmods.dev/instructions/dmitriyoproii-pixel/claude-code-secrets-guard/claude-md"><img src="https://agentmods.dev/badge/instructions/dmitriyoproii-pixel/claude-code-secrets-guard/claude-md.svg" alt="Measured on agentmods" 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 | $0.00552 | $0.00552 |
| Opus 5 | $0.00276 | $0.00276 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
claude-code-secrets-guard 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 5d 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.
What it actually says
secrets-guard (страж секретов)
Наш «проект №0» — разминочная утилита. Контекст для будущих сессий в этой папке.
Что это
PreToolUse-хук для Claude Code, который блокирует публикацию/вывод секретов
(пароли, токены, API-ключи, .env, ключи) в Bash-командах.
Цель
Технический барьер к правилу «Безопасность секретов» (см. корневой CLAUDE.md).
Критерий «готово»: установлен, test.sh проходит без провалов, срабатывает вживую.
Стек / инструменты
Чистый bash + jq (разбор JSON хука). Никаких внешних зависимостей и сети — важно для доступности из РФ и простоты.
Важные решения
- Логика вынесена в отдельный скрипт (а не строкой в settings.json) — чище и тестируемо.
- Активная копия живёт в
~/.claude/hooks/(глобально, внеsz), чтобы барьер работал в любой папке и любой сессии. Исходник-источник — здесь, в проекте; разворачивается черезinstall.sh. - Настройки в отдельном
secrets-guard.config;install.shне перезатирает уже существующий конфиг. - Три уровня решения: deny (явная утечка) / ask (риск) / allow (молча пропустить).
Статус
Готово и развёрнуто. Барьер активен. Тест: 27 проверок.
Дальше (TODO, по желанию)
- Дорастить шаблоны под реальные сервисы СТВ (когда появятся токены/ключи).
- Подумать про аналогичную проверку для инструментов Write/Edit (не только Bash).
- Если понадобится серьёзная защита репозитория — подключить gitleaks/pre-commit.
Заметки для Claude
- Не выводить и не пересылать секреты при работе над проектом (рекурсивно — то же правило).
- Менять логику — в
src/, потомbash src/install.shдля синхронизации с~/.claude/hooks/, затемbash src/test.sh. - Связано с памятью: secrets-policy, backup-setup.
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.
- 5d ago First seen · 37 lines · 552 tokens per session scan A 43217571a280
claude-code-secrets-guard CLAUDE.md is an instructions file published in the GitHub repository dmitriyoproii-pixel/claude-code-secrets-guard (1 stars, last pushed 2mo ago), licensed MIT. It adds 552 tokens to every session, about $0.0028 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.
Other instructions, from other repositories
claude-bouncer CLAUDE.md
Claude Code instructions for karlkfi/claude-bouncer, covering working in claude-bouncer, never edit a vendored library copy, what belongs in the shared parser, one backlog, five plugins and checks.
vox-machina CLAUDE.md
Claude Code instructions for darkcrux/vox-machina, covering claude.md, project overview, architecture, key details and testing.
ralph CLAUDE.md
Claude Code instructions for SantanderAI/ralph, covering ralph — instrucciones del proyecto and paridad bash ↔ powershell (importante).
claude-code-statusline CLAUDE.md
Instructions for glauberlima/claude-code-statusline, covering claude.md, project overview, development commands, testing and run all tests (unit + integration).
auto-uv-env AGENTS.md
Instructions for ashwch/auto-uv-env, covering agents.md - the auto-uv-env story, what this repo is, architecture diagrams, runtime activation flow and repository lifecycle.
sandy CLAUDE.md
Instructions for jamestelfer/sandy, covering claude.md, voice, what is sandy, project layout and dev commands.