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/pledgeandgrow/pledge-skills/pythonnpx skills add pledgeandgrow/pledge-skills --skill pythongit clone --depth 1 https://github.com/pledgeandgrow/pledge-skillsWhat 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 | $0.00251 | $0.02360 |
| Opus 5 | $0.00125 | $0.01180 |
| Sonnet 5 | $0.00050 | $0.00472 |
| Haiku 4.5 | $0.00025 | $0.00236 |
Grade A, and why
python-docs 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| threading, multiprocessing, concurrent.futures, queue, socket, ssl, http, socketserver, sqlite3, hashlib/hmac, base64, struct, decimal, fractions, statistics, time, inspect, traceback, gc, weakref, types, operator, zip How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Expert (3.13)
Official Documentation: https://docs.python.org/3/
Quick Reference
| Topic | File |
|---|---|
| Variables, built-in types, strings, bytes/bytearray/memoryview, control flow, f-strings, pattern matching, keywords, constants, special attributes, dict views, set methods | basics-syntax.md |
| Functions, lambda, *args/**kwargs, decorators, generators, closures, scope resolution (LEGB) | functions-lambdas.md |
| Classes, inheritance, dataclasses, enums, metaclasses, properties, slots, dunder methods | classes-objects.md |
| List, dict, set, tuple, comprehensions, collections module, sequences | collections.md |
| Imports, packages, pip, venv, pyproject.toml, packaging, distribution | modules-packages.md |
| try/except, custom exceptions, exception groups, context managers, warnings | exceptions.md |
| Type hints, generics, protocols, TypedDict, mypy, pyright, narrowing | typing.md |
| async/await, asyncio, tasks, streams, synchronization, async generators | async-asyncio.md |
| os, sys, math, itertools, functools, datetime, json, re, argparse, random | stdlib-core.md |
| File I/O, pathlib, io, csv, pickle, logging, shutil, tempfile | stdlib-io.md |
| threading, multiprocessing, concurrent.futures, queue, socket, ssl, http, socketserver, sqlite3, hashlib/hmac, base64, struct, decimal, fractions, statistics, time, inspect, traceback, gc, weakref, types, operator, zipfile/tarfile, configparser, tomllib, ipaddress, urllib, ctypes, email/smtplib/imaplib/poplib, html.parser/entities, xml.etree/dom/sax/expat, string, textwrap, difflib, unicodedata, codecs, numbers, pdb, cProfile, timeit, tracemalloc, faulthandler, atexit, signal, mmap, sched, tkinter, turtle, curses, gettext/locale, copyreg, pkgutil, importlib, contextvars, graphlib, zoneinfo, calendar, pprint, cmath, logging.config/handlers, select/selectors, stat, reprlib, filecmp, fileinput, cmd, readline, rlcompleter, stringprep, netrc, plistlib, mailbox, binascii, quopri, wsgiref, ftplib, http.cookies/cookiejar, xmlrpc, wave, colorsys, bdb, trace, sys.monitoring, code/codeop, modulefinder, zipimport, optparse, _thread, shared_memory, builtins, warnings, os.path, audit events, devmode, IDLE, test, dis, py_compile, compileall, tokenize, tabnanny, symtable, keyword, ast, removed modules (imghdr, sndhdr, crypt, aifc, sunau, chunk, nntplib, telnetlib, uu, xdrlib, cgi, cgitb, distutils, formatter), descriptors, GIL | stdlib-extended.md |
| pytest, unittest, mocking, fixtures, coverage, hypothesis, doctest | testing.md |
| PEP 8, idioms, patterns, performance, EAFP, duck typing, naming | idioms-best-practices.md |
| Python 3.13 features, free-threaded, JIT, REPL, error messages, 3.12/3.11 changes | whats-new.md |
What ships with it
14 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.
- async-asyncio.md 14 KB
- basics-syntax.md 22 KB
- classes-objects.md 17 KB
- collections.md 12 KB
- exceptions.md 11 KB
- functions-lambdas.md 10 KB
- idioms-best-practices.md 9.3 KB
- modules-packages.md 6.1 KB
- stdlib-core.md 14 KB
- stdlib-extended.md 71 KB
- stdlib-io.md 11 KB
- testing.md 9.7 KB
- typing.md 15 KB
- whats-new.md 9.5 KB
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.
- 2d ago First seen · 263 lines · 251 tokens per session scan A b1e2eaa3c686
python-docs is a skill published in the GitHub repository pledgeandgrow/pledge-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 251 tokens to every session and 2,360 once invoked, about $0.0013 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
python
Python programming patterns and best practices.
docetl
Build and run LLM-powered data processing pipelines with DocETL. Use when users say "docetl", want to analyze unstructured data, process documents, extract information, or run ETL tasks on text. Helps with data collection, pipeline creation, execution, and optimization.
data-formats
Working with diverse data formats: binary, text, structured, and custom.
fin-data-acquisition
根据REFINEDDESIGN.md中的变量定义，自动获取所需数据并生成可执行的回归分析脚本（Python/Stata）。.
narwhals
Effectively use Narwhals to write dataframe-agnostic code that works seamlessly across multiple Python dataframe libraries. Write correct type annotations for code using Narwhals.
syrupy
Use syrupy for pytest snapshot testing to ensure the immutability of computed results, manage snapshots, customize serialization, and handle complex data structures with built-in matchers and filters.