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/tmj-90/gaffer/python-conventionsnpx skills add tmj-90/gaffer --skill python-conventionsgit clone --depth 1 https://github.com/tmj-90/gafferWhat 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 | $0.00084 | $0.01128 |
| Opus 5 | $0.00042 | $0.00564 |
| Sonnet 5 | $0.00017 | $0.00226 |
| Haiku 4.5 | $0.00008 | $0.00113 |
Grade A, and why
python-conventions 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 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.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write idiomatic, typed Python
Add Python that reads as pythonic, is fully type-hinted, and matches the repo's existing idioms and tooling — clear and correct, not just runnable.
Steps
- Read the lore first. Call
search_lore(Memory MCP) for the repo's Python conventions and respect its config: the Python version,pyproject.toml(dependencies, tool config), the formatter/linter (ruff / black), and the type checker (mypy / pyright). Use the project's environment manager (poetry / venv / uv) — never install globally. - Find a sibling module and copy its patterns — package layout, import style, error handling, how data is modelled, and how tests are organised.
- Type everything. Add type hints on every function signature and public
attribute; prefer precise types (
Sequence,Mapping,Protocol,TypedDict,Literal) over bareAny. Justify anyAnyin a comment. Run the project's type checker and fix the cause of errors rather than# type: ignore-ing them. - Model data with
@dataclass(frozen where it should be immutable) or Pydantic when the repo already uses it for validation at boundaries — not loose dicts of stringly-typed keys. - Be pythonic. Comprehensions and generators over manual loops where readable;
context managers (
with) for resources;pathlibover string paths; f-strings for formatting;enumerate/zipover index juggling. - Handle errors explicitly. Catch the narrowest exception that fits — no bare
except:and no blanketexcept Exceptionthat swallows. Re-raise with context (raise X from err) or handle; never silently pass. Validate external input at the boundary. - Test with pytest. Use fixtures and
parametrizefor table-style cases; cover happy path, edge cases, and error conditions; assert behaviour, not incidental detail. - Verify + evidence. Run the project's tests + lint + type check, record
test_outputvia therecord-evidenceskill, and submit for review.
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 · 77 lines · 84 tokens per session scan A cadc4c6206c9
python-conventions is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 84 tokens to every session and 1,128 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
mobile-developer
Expert knowledge in mobile app development for iOS, Android, and cross-platform solutions.
skill-creator
Create or update AnkaLoop skills. Use when designing, structuring, or packaging skills with scripts, references, and assets. This skill should be used when users want to create a new skill (or update an existing skill) that extends AnkaLoop's capabilities with specialized knowledge, workflows, or tool integrations.
gh-ci-analyzer
使用 gh CLI 分析 GitHub Actions CI 日志，提供结构化的故障诊断和报告.
ai-engineer
Expert knowledge in AI/ML development, model deployment, and MLOps practices.
telegram-sender
Send and edit Telegram messages, and send photos via Bot API. Use when AnkaLoop needs to send text, reply to a specific message, edit an existing message, send an image, or push proactive notifications (cron results, heartbeat alerts, task status). Requires ANKATELEGRAMBOTTOKEN env var.
security-best-practices
Security best practices and vulnerability prevention guidelines.