What is flashbacker CLAUDE.md?

A project guidance file for Flashbacker, a command-line tool that combines AI and computer operations. It documents how to build, test, lint, format, link, and check prerequisites for the project.

Use it to compile the TypeScript project, run its remaining tests, fix style issues, prepare releases, and verify the installed command-line version.

It puts the project’s development workflow in one place, including the required order for formatting, building, and linking changes.

flashbacker CLAUDE.md — Instructions file by agentsea

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/agentsea/flashbacker/claude-md

Clone the repo

git clone --depth 1 https://github.com/agentsea/flashbacker

Per session 3,623 This file is loaded in full into every session.

When invoked 3,623 The same file — it is already loaded in full.

Security scan C 1 finding. 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	$0.03623	$0.03623
Opus 5	$0.01811	$0.01811
Sonnet 5	$0.00725	$0.00725
Haiku 4.5	$0.00362	$0.00362

Measured 2d ago against content hash 6661bfa588db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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`

CLAUDE.md · 297 lines

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

Read the full file on GitHub · 297 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.

2d ago First seen · 297 lines · 3,623 tokens per session scan C 6661bfa588db

Subscribe to this mod's changes

flashbacker CLAUDE.md is an instructions file published in the GitHub repository agentsea/flashbacker (57 stars, last pushed 7mo ago), licensed MIT. It adds 3,623 tokens to every session, about $0.0181 per session on Opus 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.

Code review Languages Testing

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

flashbacker CLAUDE.md