pyc-decompile

pyc-decompile is a skill for Claude Code, Codex from batteryshark/rekit. It costs 74 tokens per session (610 once invoked), scanned A, original, Apache-2.0.

A read-only tool that turns Python bytecode files, such as .pyc files, back into approximate Python source code. Python bytecode is the compiled form of Python that an interpreter normally runs.

In plain words
What is it for?
Use it on standalone .pyc files, Python cache files, or bytecode recovered from PyInstaller and py2exe bundles, then review or scan the reconstructed source.
Why use it?
It helps when you have compiled Python but not the original source, including bytecode extracted from bundled applications. It reads and disassembles the file without importing or running it, but works best with CPython 3.7–3.8 bytecode.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/batteryshark/rekit/pyc-decompile
Any agent
npx skills add batteryshark/rekit --skill pyc-decompile
Clone the repo
git clone --depth 1 https://github.com/batteryshark/rekit

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 pyc-decompile

README.md
[![agentmods](https://agentmods.dev/badge/skills/batteryshark/rekit/pyc-decompile.svg)](https://agentmods.dev/skills/batteryshark/rekit/pyc-decompile)
Your own site
<a href="https://agentmods.dev/skills/batteryshark/rekit/pyc-decompile"><img src="https://agentmods.dev/badge/skills/batteryshark/rekit/pyc-decompile.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 610 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00074 $0.00610
Opus 5 $0.00037 $0.00305
Sonnet 5 $0.00015 $0.00122
Haiku 4.5 $0.00007 $0.00061

Measured 4d ago against content hash 25176150de8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pyc-decompile 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 4d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/build.sh, 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/pyc-decompile/SKILL.md · 60 lines

What it actually says

Python Bytecode Decompiler

Decompile Python bytecode (.pyc / compiled code objects) back to source with decompyle3.

When to use

You have compiled Python but not the source: a stray .pyc, the __pycache__ of a suspicious package, or (most commonly) bytecode carved out of a PyInstaller / py2exe bundle. Decompiling recovers readable source you can then scan for the real behaviour.

When inventory finds .pyc artifacts with no matching source, decompile them and rescan the recovered .py.

What it does

Reads the bytecode statically (unmarshals the code object, disassembles it) and reconstructs equivalent Python source. It does not import, exec, or run the .pyc — safe on hostile bytecode.

Best on CPython 3.7–3.8 bytecode (decompyle3's target range). The runner detects the bytecode's version and tells you whether it's in range; for older bytecode use uncompyle6, and 3.9+ needs a version-matched decompiler.

Usage

rekit run pyc-decompile ./payload.pyc ./out
# or
python3 skills/pyc-decompile/scripts/run.py ./payload.pyc ./out

Writes out/decompiled.py and prints a JSON result:

{"ok": true, "outputFile": "out/decompiled.py", "detectedVersion": "3.8",
 "supported": true, "bytesOut": 412}

On an out-of-range or corrupt .pyc it fails honestly with the detected version and a pointer to the right tool — it does not emit a half-guessed decompilation.

Prerequisites

  • python3 ≥ 3.8 — to run the decompiler. The target .pyc may be a different version; decompyle3 (and its pure-Python deps) is installed under scripts/site, so no network/install at analysis time.

Rebuilding the payload

scripts/site is populated from a pinned scripts/requirements.txt by scripts/build.sh (uv pip install --target, build time only). Pure-Python, so the vendored tree is portable across OS/arch.

Files

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.

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. 4d ago First seen · 60 lines · 74 tokens per session scan A 25176150de8b

Subscribe to this mod's changes

pyc-decompile is a skill published in the GitHub repository batteryshark/rekit (11 stars, last pushed 26d ago), licensed Apache-2.0. It adds 74 tokens to every session and 610 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

agent-framework-azure-ai-py

Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.

sickn33/agentic-awesome-skills · 24 tokens

python-feature-lifecycle

Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.

microsoft/agent-framework · 43 tokens

python-development

Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.

microsoft/agent-framework · 35 tokens

dd-code-generation

Use pup CLI for immediate Datadog operations or generate code for integration into applications.

DataDog/pup · 16 tokens

python-code-reviewer

Review Python OpenInference instrumentation code for correctness and completeness. Use this skill when reviewing a Python instrumentor package — whether it's a new instrumentor, a PR that modifies one, or when the user asks to audit/review/check an existing instrumentor's code quality. Trigger on phrases like "review…

Arize-ai/openinference · 100 tokens

rocm-kernels

Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…

huggingface/kernels · 93 tokens