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 agentmods add skills/batteryshark/rekit/emulate-codenpx skills add batteryshark/rekit --skill emulate-codegit clone --depth 1 https://github.com/batteryshark/rekitWhat 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 | $0.00085 | $0.00545 |
| Opus 5 | $0.00043 | $0.00272 |
| Sonnet 5 | $0.00017 | $0.00109 |
| Haiku 4.5 | $0.00009 | $0.00055 |
Grade A, and why
emulate-code 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 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.
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.
What it actually says
Code Emulator (Unicorn)
Emulate a raw code / shellcode blob on a virtual CPU and see what it computes — the contained member of the dynamic tier (the bytes run on Unicorn, not the host).
When to use
You have a chunk of machine code — shellcode carved out of a payload, an obfuscated decoder stub, an isolated function — and you want to know what it does without running it natively. Emulation gives you the register/memory effects safely.
What it does
Maps memory + a stack, writes the blob at a base address, and emulates it (x86/x64/ arm/arm64) with an instruction-count and timeout cap. Reports:
- final register state,
- instruction count and stop reason (completed / fault / instruction-limit),
- memory writes (address ← value).
- emulator/backend provenance (version, host/process architecture, native/Rosetta, and library digest).
Contained: memory-only, no host syscalls unless explicitly wired. Because it can't
touch the host, it is not behind the --allow-dynamic gate (unlike exec-observe
and the tracer skills, which run the target natively).
Usage
rekit run emulate-code ./shellcode.bin --arch x64
rekit run emulate-code ./stub.bin --arch arm64 --base 0x400000 --format json
Prerequisites
- python3 ≥ 3.8 — Unicorn is installed under
scripts/site(native; the local tree is platform-specific — rebuild withscripts/build.shon a new platform). - On Apple Silicon, the build also vendors an x86_64 Unicorn runtime when Rosetta is available. Doctor probes x87 execution and register access in crash-isolated child processes and selects this lane explicitly if native Unicorn is unsafe.
See ../../docs/UNICORN-X87.md for the macOS ARM64
root cause, reproducer, fallback contract, and qualified environment.
What ships with it
3 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.
- 2d ago First seen · 49 lines · 85 tokens per session scan A b3c526fb0175
emulate-code is a skill published in the GitHub repository batteryshark/rekit (11 stars, last pushed 23d ago), licensed Apache-2.0. It adds 85 tokens to every session and 545 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…