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.
git clone --depth 1 https://github.com/batteryshark/rekitnpx agentmods add skills/batteryshark/rekit/filesystem-recoverWrote 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/skills/batteryshark/rekit/filesystem-recover)<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>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 | $0.00089 | $0.00614 |
| Opus 5 | $0.00044 | $0.00307 |
| Sonnet 5 | $0.00018 | $0.00123 |
| Haiku 4.5 | $0.00009 | $0.00061 |
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.
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.
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
- Run
disk-image-scanand verify the candidate filesystem offset. - Use the candidate's
lba512orinferredStartLbaas--offset. Sleuth Kit offsets are sector counts, not byte offsets. - 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
- Preserve
recovery.json,tsk-recover.stdout.log,tsk-recover.stderr.log,metadata-names.jsonl,metadata-renames.jsonl, andmanifest.jsonl. The manifest hashes every recovered regular file unless--no-hashis set. - 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.
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.
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.
- 8d ago First seen · 51 lines · 89 tokens per session scan A 59944dba270f
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…