System Prompts Leaks is a collection of captured system instructions used to guide AI chatbots and coding agents before they receive user messages. It serves researchers and developers studying how different AI assistants are directed.
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 asgeirtj/system_prompts_leaks --skill python-envgit clone --depth 1 https://github.com/asgeirtj/system_prompts_leaksWrote 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/asgeirtj/system_prompts_leaks/python-env)<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/python-env"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/python-env/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/asgeirtj/system_prompts_leaks/python-env"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/python-env.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00089 | $0.00635 |
| Opus 5.5 | $0.00036 | $0.00254 |
| Sonnet 5.5 | $0.00018 | $0.00127 |
| Haiku 4.5 | $0.00009 | $0.00064 |
Grade A, and why
python-env 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 11d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python environments
The environment is part of the project, not scratch space. A user who opens the project tomorrow, or clones it on another machine, should find the environment where their editor, their tooling, and their habits expect it.
Where it goes
Create it inside the project directory — .venv at the project root is the
convention nearly every editor and tool auto-detects:
python3 -m venv .venv
source .venv/bin/activate
pip install -e .
For a greenfield project, prefer uv, which manages a project-local .venv for
you and is much faster:
uv venv
uv pip install -e . # or `uv sync` when there is a lockfile
uv run python -m yourpkg # runs in the project env without activating
Never put the environment in /tmp, ~/envs, or any other scratch location
outside the project. It is invisible to the user's tooling, it is not what they
will look for, and on /tmp it is deleted out from under them.
PEP 668: "externally-managed-environment"
Homebrew, Debian, and Ubuntu mark the system interpreter as externally managed,
so pip install outside a virtualenv refuses with:
error: externally-managed-environment
That is the signal to create the project environment — not an obstacle to work
around. Do not pass --break-system-packages, set
PIP_BREAK_SYSTEM_PACKAGES, or delete the EXTERNALLY-MANAGED marker: those
mutate an interpreter the OS owns, leave the project with no environment of its
own, and can break other software on the machine.
Hand off commands the user can run
Write the run instructions against the project environment, so they work from a fresh shell in the project directory:
source .venv/bin/activate
python -m yourpkg ...
or, with uv, uv run python -m yourpkg ....
Do not hand back absolute paths into an environment outside the project
(/tmp/whatever/bin/python -m yourpkg). Even when they work right now, they
tell the user their project has no environment of its own.
Respect what is already there
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.
- 11d ago First seen · 73 lines · 89 tokens per session scan A e9566702bb1f
python-env is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (69,707 stars, last pushed 2d ago), licensed CC0-1.0. It adds 89 tokens to every session and 635 once invoked, about $0.0004 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 2026-10-05.
Other skills, from other repositories
accelerate
Run PyTorch training across GPUs with minimal changes.
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
python-repl
Interactive Python REPL automation with common helpers and best practices.
django-patterns
Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
fastapi-patterns
FastAPI patterns for async APIs, dependency injection, Pydantic request and response models, OpenAPI docs, tests, security, and production readiness.