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 pyscyllagit 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/pyscylla)<a href="https://agentmods.dev/skills/batteryshark/rekit/pyscylla"><img src="https://agentmods.dev/badge/skills/batteryshark/rekit/pyscylla.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 | $0.00101 | $0.01344 |
| Opus 5 | $0.00051 | $0.00672 |
| Sonnet 5 | $0.00020 | $0.00269 |
| Haiku 4.5 | $0.00010 | $0.00134 |
Grade A, and why
pyscylla 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pyscylla — IAT Rebuilder (libscylla bindings)
Python bindings for libscylla — dump, realign, and rebuild Import Address Tables
of Windows PE binaries. The programmatic successor to the classic
Scylla GUI tool, designed for agent-driven
memory-dump cleanup workflows.
Windows-only. Rekit does not commit, download, or build libscylla. Keep a private
architecture-matched copy at skills/pyscylla/bin/libscylla-x64.dll or
libscylla-x86.dll; that directory is Git-ignored and the loader discovers it
automatically. You may instead set PYSCYLLA_DLL to an absolute path or put the DLL
on PATH. Obtain it from the external Scylla project
and review its license. Live operations use OpenProcess / ReadProcessMemory.
⚠️ The arch-match rule (read first)
sizeof(DWORD_PTR) is baked at libscylla compile time. A 64-bit libscylla only
correctly processes 64-bit targets; 32-bit only 32-bit. Wrong arch = silently
corrupt output (every IAT entry becomes its own import descriptor).
| Target arch | Required Python | Required DLL |
|---|---|---|
| x64 | 64-bit Python | libscylla-x64.dll |
| x86 | 32-bit Python | libscylla-x86.dll |
pyscylla selects the DLL by Python's arch at import time. Run arch first to
confirm the match before dump/fix.
Usage
This skill is a clean passthrough to pyscylla's CLI — the first positional is the
operation (op), followed by that op's args. --json is forced for rekit.
# check libscylla version + the arch match for a target
rekit run pyscylla version
rekit run pyscylla arch --pid 1234
# list processes
rekit run pyscylla procs
# find IAT → dump → fix → rebuild
rekit run pyscylla iat-find --pid 1234 --start 0x401000
rekit run pyscylla fix --pid 1234 --addr 0x405000 --size 0x100 --dump game.dmp --out game_fixed.exe
rekit run pyscylla rebuild --file game_fixed.exe
Op reference
| Op | Args | Does |
|---|---|---|
version |
— | print libscylla version |
arch |
--pid |
print target arch + Python arch + match status (run this first) |
procs |
— | list processes with arch + image base |
dump |
--pid|--name --out [--file] [--entry-point] |
dump a live process to a file |
iat-find |
--pid [--start] [--advanced] |
find the IAT region in a live process |
fix |
--pid --addr --size --dump --out |
dump + fix IAT (auto mode) |
rebuild |
--file [--backup] [--skip-checksum] |
realign + checksum a dumped PE |
tree |
--load|--save [--pid --addr --size --oep] |
Scylla XML tree load/save |
refs |
--pid --iat-addr --iat-size [--patch] |
scan for IAT references (trace bad imports) |
What ships with it
21 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.
- references/python-api.md 6.1 KB
- scripts/check-runtime.py 2.5 KB runs code
- scripts/pyscylla/__init__.py 2.2 KB runs code
- scripts/pyscylla/__main__.py 90 B runs code
- scripts/pyscylla/_loader.py 2.9 KB runs code
- scripts/pyscylla/_native.py 9.5 KB runs code
- scripts/pyscylla/cli.py 11 KB runs code
- scripts/pyscylla/debugger_bridge/__init__.py 1.4 KB runs code
- scripts/pyscylla/debugger_bridge/ghidra.py 2.9 KB runs code
- scripts/pyscylla/debugger_bridge/win32.py 4.3 KB runs code
- scripts/pyscylla/debugger_bridge/x64dbg.py 3.0 KB runs code
- scripts/pyscylla/dump.py 1.5 KB runs code
- scripts/pyscylla/errors.py 2.4 KB runs code
- scripts/pyscylla/iat.py 10 KB runs code
- scripts/pyscylla/mcp_server.py 9.6 KB runs code
- scripts/pyscylla/process.py 1.4 KB runs code
- scripts/pyscylla/rebuild.py 837 B runs code
- scripts/pyscylla/reference_scan.py 5.1 KB runs code
- scripts/pyscylla/tree.py 1.8 KB runs code
- scripts/pyscylla/types.py 3.8 KB runs code
- scripts/run.py 3.6 KB runs code
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 · 101 lines · 101 tokens per session scan A 37c550b788bb
pyscylla is a skill published in the GitHub repository batteryshark/rekit (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 101 tokens to every session and 1,344 once invoked, about $0.0005 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…