agentmods.dev

claude-file-recovery: Instructions file for Claude Code

CLAUDE.md

claude-file-recovery CLAUDE.md is an instructions file for Claude Code from hjtenklooster/claude-file-recovery. It costs 777 tokens per session, scanned A, original, MIT.

Instructions for recovering files that Claude Code created or changed from its JSONL session transcripts, which are structured log files. The related tool can list recoverable files, extract them, or open them in a text interface.

In plain words
What is it for?
Listing recovered files, filtering them by filename pattern, exporting selected files to disk, and browsing recovery data interactively.
Why use it?
Files may be recoverable even after they are no longer present in the working directory. These instructions explain how to install and use the recovery tool.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is hjtenklooster/claude-file-recovery's own configuration. It tells Claude Code how to work on claude-file-recovery itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-file-recovery configures →

not rated 109repo +1 8mo ago A scan 777 tokens original MIT
View source ↗ hjtenklooster/claude-file-recovery pypi.org
Reuse

Borrowing it

Nothing to install: this file belongs to hjtenklooster/claude-file-recovery. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/hjtenklooster/claude-file-recovery/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/hjtenklooster/claude-file-recovery

Made for: Claude Code.

Wrote 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.

agentmods badge for claude-file-recovery CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hjtenklooster/claude-file-recovery/claude-md/github.svg)](https://agentmods.dev/instructions/hjtenklooster/claude-file-recovery/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hjtenklooster/claude-file-recovery/claude-md"><img src="https://agentmods.dev/badge/instructions/hjtenklooster/claude-file-recovery/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.

agentmods 80×15 button for claude-file-recovery CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hjtenklooster/claude-file-recovery/claude-md"><img src="https://agentmods.dev/badge/instructions/hjtenklooster/claude-file-recovery/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 777 This file is loaded in full into every session.
When invoked 777 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00777 $0.00777
Opus 5.5 $0.00311 $0.00311
Sonnet 5.5 $0.00155 $0.00155
Haiku 4.5 $0.00078 $0.00078

Measured 1mo ago against content hash 4c9b5e908c66, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-file-recovery 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 1mo 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.

CLAUDE.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 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.

What This Project Does

claude-file-recovery is a CLI/TUI tool that recovers files created and modified by Claude Code from its JSONL session transcripts (~/.claude/projects/). It parses Write, Edit, and Read tool-use entries, reconstructs file contents by replaying operations in order, and lets users browse/extract them.

Commands

# Install in development mode (uses uv + hatch)
uv pip install -e .

# Run the TUI (default command)
claude-file-recovery
claude-file-recovery --claude-dir ./claude-backup

# List recoverable files
claude-file-recovery list-files
claude-file-recovery list-files --filter '*.ts' --csv

# Extract files to disk
claude-file-recovery extract-files --output ./recovered --filter '*.py'

There are no tests yet. No linter or formatter is configured.

Architecture

Entry point: src/claude_file_recovery/cli.py — Typer app with three commands: list-files, extract-files, and tui (also the default when invoked without a subcommand).

Core pipeline (src/claude_file_recovery/core/):

  • scanner.py — Discovers JSONL files under projects/<slug>/, parses them line-by-line with orjson, and extracts FileOperation objects from assistant entries (Write/Edit/Read tool_use blocks) and user entries (toolUseResult enrichment). Uses ThreadPoolExecutor to scan sessions in parallel. The two-pass correlation works via tool_use_id: tool_use blocks in assistant messages create pending ops, then toolUseResult in user messages enriches them with actual content and originalFile.
  • reconstructor.py — Replays a RecoverableFile's operations in chronological order to rebuild content. Write/Read ops set content directly; Edit ops apply string replacements. The originalFile field on Edit ops serves as a fallback base when no prior Write/Read exists.
  • models.py — OpType enum (WRITE_CREATE, WRITE_UPDATE, EDIT, READ, FILE_HISTORY), FileOperation dataclass (content fields populated during scanning), RecoverableFile dataclass (groups ops by absolute file path, provides has_full_content and latest_timestamp properties).

Read the full file on GitHub · 51 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.

  1. 1mo ago First seen · 51 lines · 777 tokens per session scan A 4c9b5e908c66

Subscribe to this mod's changes

claude-file-recovery CLAUDE.md is an instructions file published in the GitHub repository hjtenklooster/claude-file-recovery (109 stars, last pushed 8mo ago), licensed MIT. It adds 777 tokens to every session, about $0.0031 per session on Opus 5.5. 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 2026-08-30.

Claude CodeDocumentsclaudeclideveloper-toolsfile-recovery
Related

Other instructions, from other repositories

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 · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

vscode model-prompts.instructions.md

Model-specific prompt authoring and registry guidelines.

microsoft/vscode · 2,022 tokens