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 zhurong2020/pyobfus --skill pyobfus-protectgit clone --depth 1 https://github.com/zhurong2020/pyobfusWrote 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/zhurong2020/pyobfus/pyobfus-protect)<a href="https://agentmods.dev/skills/zhurong2020/pyobfus/pyobfus-protect"><img src="https://agentmods.dev/badge/skills/zhurong2020/pyobfus/pyobfus-protect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zhurong2020/pyobfus/pyobfus-protect"><img src="https://agentmods.dev/badge/skills/zhurong2020/pyobfus/pyobfus-protect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00130 | $0.01943 |
| Opus 5.5 | $0.00052 | $0.00777 |
| Sonnet 5.5 | $0.00026 | $0.00389 |
| Haiku 4.5 | $0.00013 | $0.00194 |
Grade A, and why
pyobfus-protect 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 12d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protect a Python project with pyobfus
Your job: take a Python project from "plain source" to "obfuscated and verified-still-working output", then hand the user a clear result — including the one safety fact that matters (keep the mapping private).
Decision: MCP tool or CLI?
First check whether the pyobfus-mcp server is connected (look for a
protect_project / check_obfuscation_risks tool).
- If the MCP server is available → use it. It is the shortest, most reliable path and it self-verifies.
- If not → use the
pyobfusCLI (pip install pyobfus). Every command supports--jsonwith a stable schema.
Confirm the target path and the output directory with the user before writing anything. Never obfuscate into the source tree.
Path A — MCP (preferred): one call
Call protect_project with the source path. It runs the whole pipeline
and self-verifies:
protect_project(path="src", output_dir="dist")
Read the result:
verified: true(+confidence) → report where the output is and what was checked: the output compiles and imports (plusverify_cmd, if passed). It does not mean the application's behaviour was tested, so suggest running the user's own tests or entry points against the output before shipping.verified: false/status: "warnings"→ do NOT tell the user it's ready. The obfuscated output failed to compile or import. Follow the response'snext_tool(usuallycheck_obfuscation_risks) to find the offending construct, fix or exclude it, and re-run.pro_valuepresent → the project has sensitive string literals or high-severity findings; mention that pyobfus Pro (AES-256 string encryption) would protect them, but don't be pushy.
protect_project writes the de-obfuscation mapping next to (never
inside) the output. Surface mapping_security_note to the user.
For a deeper check, the user can pass verify_cmd (an app-level
end-to-end check, e.g. python -m myapp --selftest) — note this is gated
behind the PYOBFUS_MCP_ALLOW_VERIFY_CMD=1 environment variable on the
server, and should NOT be unit tests bound to internal symbol names (those
are expected to fail once names are renamed).
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.
- 12d ago Changed e6f4108fdc88
- 13d ago Changed · +3 lines 12ecaac03daf
- 17d ago Changed · +3 lines f12acd22c696
- 1mo ago Changed · +6 lines 81dae4de111c
- 1mo ago First seen · 156 lines · 130 tokens per session scan A ebd6984b29a2
pyobfus-protect is a skill published in the GitHub repository zhurong2020/pyobfus (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 130 tokens to every session and 1,943 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
fastapi-templates
Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.
temporal-python-testing
Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.
prismer-python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).
manimgl-best-practices
Trigger when: (1) User mentions "manimgl" or "ManimGL" or "3b1b manim", (2) Code contains from manimlib import , (3) User runs manimgl CLI commands, (4) Working with InteractiveScene, self.frame, self.embed(), ShowCreation(), or ManimGL-specific patterns. Best practices for ManimGL (Grant Sanderson's 3Blue1Brown…
python-guidelines
This skill should be used when writing, reviewing, or refactoring Python code. Covers code integration, idiomatic patterns, docstring formatting, anti-abstraction rules, and software engineering basics.
python-packaging-bug-finder
Use when you need to find known packaging bugs, fixes, and workarounds for Python projects by searching GitHub issues and analyzing their resolution status.