Borrowing it
Nothing to install: this file belongs to REMvisual/claude-workspace-snapshot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/REMvisual/claude-workspace-snapshot/master/CLAUDE.mdgit clone --depth 1 https://github.com/REMvisual/claude-workspace-snapshotWrote 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/remvisual/claude-workspace-snapshot/claude-md)<a href="https://agentmods.dev/instructions/remvisual/claude-workspace-snapshot/claude-md"><img src="https://agentmods.dev/badge/instructions/remvisual/claude-workspace-snapshot/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 | $0.00378 | $0.00378 |
| Opus 5 | $0.00189 | $0.00189 |
| Sonnet 5 | $0.00076 | $0.00076 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
claude-workspace-snapshot 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 6d 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
claude-workspace-snapshot
A pair of PowerShell scripts that snapshot live Claude Code sessions on Windows and restore them after a reboot. See README.md for the full overview.
Source of truth:
scripts/workspace-snapshot.ps1— detects and saves live sessions (with history-recovery fallback)scripts/workspace-restore.ps1— rebuilds Windows Terminal tabs from~/.claude/workspace.json
OpenViking Memory
This project uses OpenViking for persistent AI memory across sessions.
How It Works
- Session start: OpenViking loads relevant memories from past sessions automatically via hooks
- During session: Use
/memory-recall <query>to search past context when historical decisions, prior fixes, or patterns are relevant - Session end: Conversation is automatically compressed and stored as long-term memory (profiles, preferences, entities, events, cases, patterns)
Session Workflow
- Session start: Global hook loads relevant OpenViking memories
- Before changes:
/memory-recall <topic>if related work might have happened before - During work: OpenViking records decisions passively — no action needed
- Session end: Memory is committed automatically
Files (NOT committed to git)
ov.conf— OpenViking config with API keys.openviking/— Session state and memory cache
Note on Beads
Beads task tracking is intentionally NOT initialized in this project — the global bd binary on this machine was built with CGO_ENABLED=0, which blocks embedded Dolt initialization for new projects. The project does not currently require task tracking; if needed later, rebuild bd with embedded-mode support and run /beads init.
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.
- 6d ago First seen · 30 lines · 378 tokens per session scan A b246cbff0c53
claude-workspace-snapshot CLAUDE.md is an instructions file published in the GitHub repository REMvisual/claude-workspace-snapshot (2 stars, last pushed 1mo ago), licensed MIT. It adds 378 tokens to every session, about $0.0019 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
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.
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.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.