Borrowing it
Nothing to install: this file belongs to agentsea/flashbacker. 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/agentsea/flashbacker/main/CLAUDE.mdgit clone --depth 1 https://github.com/agentsea/flashbackerWrote 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/agentsea/flashbacker/claude-md)<a href="https://agentmods.dev/instructions/agentsea/flashbacker/claude-md"><img src="https://agentmods.dev/badge/instructions/agentsea/flashbacker/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.
<a href="https://agentmods.dev/instructions/agentsea/flashbacker/claude-md"><img src="https://agentmods.dev/badge/instructions/agentsea/flashbacker/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03623 | $0.03623 |
| Opus 5.5 | $0.01449 | $0.01449 |
| Sonnet 5.5 | $0.00725 | $0.00725 |
| Haiku 4.5 | $0.00362 | $0.00362 |
Grade C, and why
flashbacker CLAUDE.md scanned grade C with 1 finding 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 2mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Solution**: Use supported version (18.x-22.x), clean install: `rm -rf node_modules && npm install` How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Development Commands
# Build and development
npm run build # Compile TypeScript to lib/
npm run dev # Watch mode compilation
npm link # Link for global CLI testing
# Testing (Most tests deleted as obsolete)
npm test # Build + run remaining tests (main command to use)
npm run test:unit # Unit tests (if any remain)
npm run test:coverage # Coverage report
# Code quality (Run before commits)
npm run lint # ESLint TypeScript files
npm run lint:fix # Auto-fix ESLint issues (use this first)
npm run format # Prettier formatting
# Prerequisites checking
npm run setup:prereqs # Check Node.js/npm compatibility before development
# Development workflow
npm run build && npm link # After changes, rebuild and relink globally
flashback --version # Verify installation (should show 2.2.6)
Development Pattern: Always run npm run lint:fix before npm run build to auto-fix style issues.
Architecture Overview
Hybrid AI+Computer Operations Pattern (CRITICAL)
This codebase implements a breakthrough pattern that separates programmatic operations (handled by CLI) from intelligence operations (handled by Claude/subagents):
Programmatic Operations → flashback CLI:
- File management (archive, prune, directory creation)
- Data extraction (JSONL parsing, git status, session detection)
- System operations (file paths, formatting, structural tasks)
- Why CLI: Claude does these differently each time, creating inconsistency
Intelligence Operations → Claude Subagent Prompts:
- Analysis (code review, architectural assessment, security)
- Content creation (session summaries, documentation, recommendations)
- Decision making (prioritization, strategic planning, creative work)
- Why prompts: Require domain expertise, context understanding, intelligence
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.
- 2mo ago First seen · 297 lines · 3,623 tokens per session scan C 6661bfa588db
flashbacker CLAUDE.md is an instructions file published in the GitHub repository agentsea/flashbacker (57 stars, last pushed 9mo ago), licensed MIT. It adds 3,623 tokens to every session, about $0.0145 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
flashbacker CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| flashbacker CLAUDE.mdagentsea/flashbacker | Instructions file | 57 | 9mo ago | MIT | C | 3,623 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |