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.
npx skills add batteryshark/rekit --skill native-liftgit clone --depth 1 https://github.com/batteryshark/rekitWrote 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/native-lift)<a href="https://agentmods.dev/skills/batteryshark/rekit/native-lift"><img src="https://agentmods.dev/badge/skills/batteryshark/rekit/native-lift.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 | $0.00062 | $0.00820 |
| Opus 5 | $0.00031 | $0.00410 |
| Sonnet 5 | $0.00012 | $0.00164 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
native-lift 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 7d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Native Code Lifter
Lift one bounded raw machine-code region into LLVM IR or bitcode using Remill. This adds an instruction-semantics representation between Rekit's assembly listing and its decompilation or emulation tools.
When to use
Use native-lift for an extracted function, decoder stub, shellcode region, or a
small compiler-output fixture when you want explicit register and memory semantics.
The skill accepts at most 64 KiB and requires the architecture and virtual address.
Do not pass an ELF, PE, or Mach-O file. Remill's example trace lifter does not recover
a whole program, its loader, imports, or complete interprocedural control flow. Use
native-disassemble, native-decompile, or ghidra-decompile for complete native
containers. A future Anvill or McSema integration would be a separate capability.
Install
The pinned Remill and LLVM runtime is intentionally not built on the analysis host. Install the published multi-platform image explicitly:
rekit install native-lift
rekit doctor native-lift
Installation pulls the immutable image and therefore uses the network. Analysis never pulls or builds an image; it fails clearly when Docker, the daemon, the expected image, or the runtime health check is unavailable.
Usage
rekit run native-lift ./function.bin ./out --arch amd64 --address 0x401000
rekit run native-lift ./stub.bin ./out --arch aarch64 --emit both --format json
Inputs are x86, amd64, or aarch64; representative OS choices are linux,
macos, windows, and solaris. The entry address defaults to the base address and
must point inside the supplied region. The default timeout is 300 seconds and may be
set from 1 through 3600 seconds.
Outputs are written atomically as lifted.ll, lifted.bc, or both. The JSON result
records the input digest, addresses, target, immutable image reference, runtime
identity, and artifact paths.
Safety and reproducibility
The target bytes are copied into a temporary read-only mount. The pinned image runs without networking, Linux capabilities, privilege escalation, or a writable root filesystem, and with CPU, memory, process, wall-clock, and temporary-storage bounds. Only the temporary output mount is writable. Remill translates the bytes but never executes or emulates them.
What ships with it
5 files 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.
- 7d ago First seen · 80 lines · 62 tokens per session scan A 51d7b1522606
native-lift is a skill published in the GitHub repository batteryshark/rekit (10 stars, last pushed 28d ago), licensed Apache-2.0. It adds 62 tokens to every session and 820 once invoked, about $0.0003 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.