filesystem-recover

filesystem-recover is a skill for Claude Code, Codex from batteryshark/rekit. It costs 89 tokens per session (614 once invoked), scanned A, original, Apache-2.0.

A file-recovery tool for disk images, which are files containing a copy of storage media. It uses Sleuth Kit to recover existing or deleted files from ext, NTFS, FAT, and other supported filesystems without mounting the image.

In plain words
What is it for?
Use it after locating a filesystem inside a disk image to recover allocated files, deleted files, or both, then compare and analyze the recovered files.
Why use it?
It recovers evidence while avoiding changes to the source image. It also records offsets, names, hashes, and other details needed to track where each file came from.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bin/rekit run filesystem-recover evidence.img ./forensics/partition-1 \.

Good fit Use it after locating a filesystem inside a disk image to recover allocated files, deleted files, or both, then compare and analyze the recovered files.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/batteryshark/rekit
agentmods
npx agentmods add skills/batteryshark/rekit/filesystem-recover

Made for: Claude Code, Codex.

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 filesystem-recover

README.md
[![agentmods](https://agentmods.dev/badge/skills/batteryshark/rekit/filesystem-recover.svg)](https://agentmods.dev/skills/batteryshark/rekit/filesystem-recover)
Your own site
<a href="https://agentmods.dev/skills/batteryshark/rekit/filesystem-recover"><img src="https://agentmods.dev/badge/skills/batteryshark/rekit/filesystem-recover.svg" alt="Measured on agentmods" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 614 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00089 $0.00614
Opus 5 $0.00044 $0.00307
Sonnet 5 $0.00018 $0.00123
Haiku 4.5 $0.00009 $0.00061

Measured 8d ago against content hash 59944dba270f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

filesystem-recover 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/filesystem-recover/SKILL.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.

Filesystem Recovery

Recover through Sleuth Kit without mounting the evidence image. The output directory must be new or empty; recovered files go beneath files/, while logs and manifest.jsonl remain separate.

Workflow

  1. Run disk-image-scan and verify the candidate filesystem offset.
  2. Use the candidate's lba512 or inferredStartLba as --offset. Sleuth Kit offsets are sector counts, not byte offsets.
  3. Select provenance explicitly:
    • allocated: named allocated files (tsk_recover -a);
    • deleted: recoverable unallocated files (Sleuth Kit default);
    • all: allocated and deleted files (tsk_recover -e).
bin/rekit run filesystem-recover evidence.img ./forensics/partition-1 \
  --offset 1590435 --mode all
  1. Preserve recovery.json, tsk-recover.stdout.log, tsk-recover.stderr.log, metadata-names.jsonl, metadata-renames.jsonl, and manifest.jsonl. The manifest hashes every recovered regular file unless --no-hash is set.
  2. Compare recovered trees with intellidiff folder-compare ... --binary. Analyse recovered artifacts with the format-specific Rekit skills; never execute them merely because recovery succeeded.

NTFS MFT names

Keep metadata naming enabled by default. tsk_recover writes paths exposed by the filesystem. The runner also invokes fls -r -p and records every Sleuth Kit metadata address; for NTFS, the first numeric component is the MFT record number.

When recovery produces $OrphanFiles/OrphanFile-<record>, rename it only if the same MFT record has exactly one safe, non-reallocated regular-file path in the fls results. Record ambiguous names, collisions, unsafe paths, and missing names without guessing or overwriting another recovered file. Use --no-metadata-names only when explicitly accepting the loss of this map and rename pass. Bound the parsed map with --max-name-records.

Use --fstype only when Sleuth Kit auto-detection is wrong. --sector-size describes the device sector size used by Sleuth Kit; --offset is still counted in those sectors. Timeout and manifest-file limits are bounded and reported honestly.

Read the full file on GitHub · 51 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 51 lines · 89 tokens per session scan A 59944dba270f

Subscribe to this mod's changes

filesystem-recover is a skill published in the GitHub repository batteryshark/rekit (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 89 tokens to every session and 614 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens