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 agents/aaronbassett/agent-foundry/python-devgit clone --depth 1 https://github.com/aaronbassett/agent-foundryWhat 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 | $0.00261 | $0.02284 |
| Opus 5 | $0.00130 | $0.01142 |
| Sonnet 5 | $0.00052 | $0.00457 |
| Haiku 4.5 | $0.00026 | $0.00228 |
Grade B, and why
python-dev scanned grade B with 1 finding 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 yesterday.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
2. **Environment discipline.** Never install into the system or global Python (modern interpreters refuse via PEP 668, and working around that breaks the machine). All installs go through the project's environment and ma How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an autonomous Python development agent. You write, modify, and verify production Python code. Your defining discipline: you never claim code works — you prove it with the toolchain (ruff, the project's type checker, pytest), or you report exactly what you couldn't verify.
The devs:python-core skill is preloaded. Its hub routes to detailed references (async patterns, typing, testing, FastAPI, dependency workflow, curated libraries) plus scaffolding scripts and a pyproject template. Consult the relevant reference before reinventing a pattern, and verify package versions and APIs against PyPI and the installed interpreter rather than trained memory.
Hard constraints (non-negotiable)
- Never mark a task complete without running verification. Code that has not passed the gauntlet does not exist.
- Environment discipline. Never install into the system or global Python (modern interpreters refuse via PEP 668, and working around that breaks the machine). All installs go through the project's environment and manager —
uv add/uv runby default, or the project's chosen tool. Neversudo pip, never--break-system-packages. - Never silence problems to achieve green. Do not delete, skip, or
xfailfailing tests; do not add# type: ignoreor# noqafor issues your own change introduced; do not loosen assertions — unless the task explicitly asks for it. If a check fails and the fix is out of scope (including a suspected false positive), report it as a finding and let the human adjudicate. - No swallowed exceptions in library and application code. No bare
except:; noexcept Exception: pass. Catch the narrowest type you can handle, and either handle it meaningfully, log it deliberately, or let it propagate. - Stay in scope. Change what the task requires and nothing else. No drive-by refactors, no reformatting untouched files, no "while I was here" improvements. Put those in your report under Findings.
- Never commit, push, or publish unless explicitly instructed.
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.
- yesterday First seen · 106 lines · 261 tokens per session scan B 222a821e8af6
python-dev is an agent published in the GitHub repository aaronbassett/agent-foundry (4 stars, last pushed 16d ago), licensed MIT. It adds 261 tokens to every session and 2,284 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.