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/bravew/trove/trove-pythonnpx skills add bravew/trove --skill trove-pythongit clone --depth 1 https://github.com/bravew/troveWhat 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 | $0.00044 | $0.00805 |
| Opus 5 | $0.00022 | $0.00402 |
| Sonnet 5 | $0.00009 | $0.00161 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
trove-python 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.
response = requests.get(f"/users/{user_id}") # BLOCKING! How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trove · v2026.7.4
Session Init
This skill ships Trove conventions. Prefer existing project patterns over generic best practices when they conflict.
Python / FastAPI Conventions
Imports
- Top-level imports only — never inline imports inside functions
- Organization: stdlib → third-party → local (isort-compatible)
- Use
from __future__ import annotationswhen needed for forward refs
Type Hints
- All function signatures must have type hints (params + return)
- Use
from typing importfor complex types (Optional,Union, etc.) - Pydantic models for all request/response schemas
- Prefer
X | NoneoverOptional[X](Python 3.10+)
Async Patterns (CRITICAL)
Never call blocking I/O in async functions:
# BAD — blocks the event loop
async def get_user(user_id: str):
response = requests.get(f"/users/{user_id}") # BLOCKING!
time.sleep(1) # BLOCKING!
# GOOD — non-blocking
async def get_user(user_id: str):
async with httpx.AsyncClient() as client:
response = await client.get(f"/users/{user_id}")
await asyncio.sleep(1)
- Use
httpx.AsyncClientfor HTTP (notrequests) - Use
asyncio.sleepfor delays (nottime.sleep) - Use
async withfor context managers (DB sessions, HTTP clients)
Logging
# INFO/DEBUG — f-strings are fine (fast path, no Sentry indexing needed)
logger.info(f"Processing user {user_id}")
# WARNING/ERROR — static message + extra dict (enables Sentry grouping)
logger.warning("Payment failed", extra={"user_id": user_id, "amount": amount})
# EXCEPTION — use in except blocks (auto-captures stack trace)
try:
await process()
except Exception:
logger.exception("Processing failed", extra={"user_id": user_id})
Never use sentry_sdk.capture_exception() — use logger.exception() instead.
SQLAlchemy Async
# Always use async session context manager
async with get_async_session() as session:
result = await session.execute(select(User).where(User.id == user_id))
user = result.scalar_one_or_none()
# Eager loading to avoid N+1
stmt = select(User).options(selectinload(User.posts)).where(User.id == user_id)
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 · 107 lines · 44 tokens per session scan A a622245e60ce
trove-python is a skill published in the GitHub repository bravew/trove (10 stars, last pushed 3d ago), licensed MIT. It adds 44 tokens to every session and 805 once invoked, about $0.0002 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…