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/alexei-led/cc-thingz/writing-pythonnpx skills add alexei-led/cc-thingz --skill writing-pythongit clone --depth 1 https://github.com/alexei-led/cc-thingzWhat 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 | $0.00067 | $0.00598 |
| Opus 5 | $0.00034 | $0.00299 |
| Sonnet 5 | $0.00013 | $0.00120 |
| Haiku 4.5 | $0.00007 | $0.00060 |
Grade A, and why
writing-python 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 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.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Development
Use this only for Python 3.12+ code. Keep language-agnostic rules out of this skill.
Read First
Read principles.md before generating or changing Python code.
Core Rules
- Prefer existing project patterns over these defaults.
- Inspect the project Python target before using 3.12-only syntax.
- Prefer stdlib and existing dependencies before adding packages.
- Validate untyped boundary input before it spreads.
Comments and Docstrings
- Prefer clear names and small functions over explanatory comments.
- Add comments only for non-obvious constraints, invariants, side effects, tradeoffs, or public contracts.
- Keep comments short. Move longer rationale to docs, issue links, or design notes.
- Do not comment obvious code or restate the syntax.
- Keep tests readable without comments; add one only for unobvious fixtures, timing, concurrency, or regression context.
- Use docstrings for public or non-obvious modules, classes, functions, and methods. Do not restate the signature.
Conditional References
- patterns.md — read for module design, typing, async, config, file I/O, and error patterns.
- cli.md — read before writing or changing Python CLIs.
- testing.md — read before adding or reshaping Python tests; treat slow tests as feedback-loop defects.
- linting.md — read before changing ruff or pyright config, or the lint/format/type-check flow.
Verification
Run project-configured tests, lint, format, and type checks. Prefer focused pytest commands for the edit loop, then the broader project command before final output. Prefer pytest, ruff, and pyright when present.
If a tool is not configured, say so and run the closest available gate. If a check fails, diagnose the cause, make a targeted fix, and rerun the relevant check.
Python-Specific Failure Cases
- No clear project root: locate
pyproject.tomlbefore editing or choosing commands. - Unknown Python target: inspect
pyproject.toml,.python-version, CI, or lockfiles before using 3.12-only syntax. - Type checker reports missing attributes: check imports, package exports, and runtime shape before loosening types.
What ships with it
6 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.
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 · 59 lines · 67 tokens per session scan A b257d930e4e9
writing-python is a skill published in the GitHub repository alexei-led/cc-thingz (35 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 598 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
echo
Use when the user references past sessions, asks 'what did we do', 'do you remember', 'last session', 'recall', or 'continue from'.
backend-builder
Используй только внутри активного Codex Project Autopilot-проекта по утверждённому плану; не включай для обычных backend-задач вне автопилота.