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 skills/aaronbassett/agent-foundry/python-corenpx skills add aaronbassett/agent-foundry --skill python-coregit 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 | $0.00078 | $0.00826 |
| Opus 5 | $0.00039 | $0.00413 |
| Sonnet 5 | $0.00016 | $0.00165 |
| Haiku 4.5 | $0.00008 | $0.00083 |
Grade A, and why
devs:python-core scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Reference hub for Python work. Verify versions and APIs against PyPI (`curl -s https://pypi.org/pypi/<pkg>/json | jq -r .info.version`) and the installed interpreter — never from trained knowledge. How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Core Development
Reference hub for Python work. Verify versions and APIs against PyPI (curl -s https://pypi.org/pypi/<pkg>/json | jq -r .info.version) and the installed interpreter — never from trained knowledge.
Reference routing
Load references on demand — not all at once.
| Reference | Use when |
|---|---|
| type-hints.md | Modern typing: PEP 695 generics, TypeIs, Protocol, strict mypy config |
| async-patterns.md | TaskGroup, timeouts, queues, blocking-call escape hatches |
| testing.md | pytest config, fixtures, pytest-asyncio, coverage, async FastAPI tests |
| fastapi-guide.md | FastAPI services: lifespan, pydantic v2, SQLAlchemy 2 async, auth, CORS |
| dependencies.md | uv workflow, PEP 735 dependency groups, auditing, moving a project to uv |
| common-libraries.md | Curated library selection with versions, gotchas, and a do-not-use list |
For code-review checklists use the devs:code-review skill; for dependency auditing workflows use devs:deps-core.
Decision guides
Package manager: uv for anything new. In existing projects, detect from the lockfile (poetry.lock → poetry, etc.) and conform — details in dependencies.md.
Data modeling: dataclasses by default; pydantic when runtime validation/serialization is actually needed.
Sync vs async: async only for I/O-bound concurrency (servers, fan-out HTTP); CPU-bound work uses processes or asyncio.to_thread; simple scripts stay sync. Details: async-patterns.md.
Library selection: the curated table (with a do-not-use list) in common-libraries.md.
Performance: profile first (py-spy, scalene); functools.cache for memoization.
Scripts
${CLAUDE_SKILL_DIR}/scripts/init_python_project.sh <name> [package|fastapi]— scaffold viauv init(src layout), append the[tool.*]policy tables, dev tools in the PEP 735 dev group, starter test; self-verifies with ruff + mypy + pytest before reporting success.${CLAUDE_SKILL_DIR}/scripts/setup_logging.sh—uv add structlogplus alogging_config.py(console on TTY, JSON otherwise); refuses to overwrite an existing one.${CLAUDE_SKILL_DIR}/scripts/audit_dependencies.sh—uv audit(falling back with instructions when the installed uv predates it) plusuv tree --outdated; non-zero exit on findings or when the vulnerability check cannot run.
What ships with it
10 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.
- assets/configs/pyproject-tools.toml 1.1 KB
- references/async-patterns.md 3.5 KB
- references/common-libraries.md 2.8 KB
- references/dependencies.md 3.5 KB
- references/fastapi-guide.md 7.0 KB
- references/testing.md 3.8 KB
- references/type-hints.md 3.3 KB
- scripts/audit_dependencies.sh 1.6 KB runs code
- scripts/init_python_project.sh 3.3 KB runs code
- scripts/setup_logging.sh 1.8 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.
- yesterday First seen · 46 lines · 78 tokens per session scan A d47ceb4e370c
devs:python-core is a skill published in the GitHub repository aaronbassett/agent-foundry (4 stars, last pushed 16d ago), licensed MIT. It adds 78 tokens to every session and 826 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…