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/vynazevedo/first-plan/lens-pythonnpx skills add vynazevedo/first-plan --skill lens-pythongit clone --depth 1 https://github.com/vynazevedo/first-planWhat 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 | $0.00054 | $0.00983 |
| Opus 5 | $0.00027 | $0.00491 |
| Sonnet 5 | $0.00011 | $0.00197 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
first-plan-lens-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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lens Python
Detecção fina
| Sinal | Variante |
|---|---|
manage.py na raiz |
Django |
fastapi em deps |
FastAPI |
flask em deps |
Flask |
litestar em deps |
Litestar |
celery em deps |
Worker |
streamlit em deps |
Data app |
dagster, airflow, prefect |
Data pipeline |
setup.py apenas |
lib legacy |
pyproject.toml com [tool.poetry] |
Poetry |
pyproject.toml com [tool.uv] ou uv.lock |
uv |
pyproject.toml com [build-system] setuptools |
setuptools moderno |
Pipfile |
pipenv |
Extração de padrões
Packaging
- Layout
src/vs flat - Namespace package vs regular
- Versão Python suportada (
requires-python) - Optional dependencies / extras
Type checking
- mypy / pyright / pyre / ty
- Configuração strictness (
strict = true?) - Cobertura de tipos visível
Validação
- Pydantic (v1 ou v2?) - dominante em FastAPI
- attrs (validação opcional)
- marshmallow
- dataclasses + manual validation
Async
asynciodiretoanyio(compatibilidade)trio- async libs (httpx vs requests, asyncpg vs psycopg)
Testing
- pytest (dominante) ou unittest stdlib
conftest.pyem pasta tests/ -> fixtures globais- Markers customizados (
pytest.mark.integration) - Coverage tool (coverage.py)
- Mocks:
unittest.mock,pytest-mock,responses(HTTP)
Web frameworks - padrões
FastAPI:
- Routers em
app/routers/ - Dependency injection via
Depends() - Pydantic schemas em
app/schemas/ - ORM tipicamente SQLAlchemy + Alembic migrations
Django:
- Apps em
app/<name>/commodels.py,views.py,urls.py,admin.py - Settings em
<project>/settings.py - Migrations geradas
- Templates em
templates/
Flask:
- Application factory pattern (
create_app())? - Blueprints
- Extensions (Flask-SQLAlchemy, Flask-Login, etc)
ORM
- SQLAlchemy 1.x vs 2.x (style mudou drasticamente)
- Django ORM
- Tortoise ORM (async)
- Peewee
- Raw SQL via psycopg / sqlite3
Logging
- stdlib
logging(dominante) - structlog (estruturado)
- loguru (alternativa moderna)
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 · 133 lines · 54 tokens per session scan A fb1c7b2626f4
first-plan-lens-python is a skill published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 8d ago), licensed MIT. It adds 54 tokens to every session and 983 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
RecallMax
Enhances AI memory capabilities with long-context support.
agent-memory
Persistent memory system for AI coding agents. Use when you need to save facts about the user, store interaction preferences, log session events, or search previously saved memories. Triggers on remembering, saving context, recalling past decisions, or when the user says "remember this". Also use proactively when the…
snip
You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.
arch-check
架构与实现审查 —— 基于「概念建模 → 职责划分 → 机制/策略分离 → 因果与不变量 → 属性建模 → 模块化 → SOLID → GRASP → YAGNI」的全维度审查，带置信度门控与假阳性抑制（对抗"过度工程建议"这类 AI slop）。触发于：要求 review/审查架构、检查目录结构/依赖关系/职责划分、重构前评估、技术债盘点、判断是否过度设计，或问「这个设计合理吗 / 该怎么拆 / 有没有循环依赖 / 这个改动架构上 OK 吗」。一律按最高强度审查。用法：arch-check [范围] [--fix|--plan]。范围可为目录/文件/PR；缺省审当前分支相对基线的全部变更。.
gh-merge
Completes the AgentsMesh GitHub pull-request workflow: commits scoped changes, rebases on the authoritative GitHub branch, opens or reuses a PR, monitors required checks, fixes failures, and merges only after verification. Use when the user asks to merge, submit, or land repository changes.
github-gitlab-mirror
Audits or synchronizes the authoritative GitHub main branch to the internal GitLab mirror without importing GitLab-only history back into GitHub. Use when checking GitHub/GitLab consistency, updating the internal mirror, or resolving a divergence between the two remotes.