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 skills add avanturer/claude-bestpractice --skill founder-defaultsgit clone --depth 1 https://github.com/avanturer/claude-bestpracticeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/avanturer/claude-bestpractice/founder-defaults)<a href="https://agentmods.dev/skills/avanturer/claude-bestpractice/founder-defaults"><img src="https://agentmods.dev/badge/skills/avanturer/claude-bestpractice/founder-defaults/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/avanturer/claude-bestpractice/founder-defaults"><img src="https://agentmods.dev/badge/skills/avanturer/claude-bestpractice/founder-defaults.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00031 | $0.01103 |
| Opus 5 | $0.00015 | $0.00551 |
| Sonnet 5 | $0.00006 | $0.00221 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
founder-defaults 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 9d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standing defaults
Every choice below is already made. Making it again per task is how a codebase ends up with three date libraries and four error-handling styles, none of which is wrong on its own. Deviate when the task genuinely requires it, and say why in the code.
Anything a gate already enforces is marked [enforced] — those are not advice, and arguing with them costs a blocked turn.
Language and style
- Formatter, never hand-formatting. Prettier for JS/TS, Black or Ruff-format for Python, gofmt, rustfmt. Run it; do not discuss it.
- Types at every boundary. Function signatures, exported values, API payloads. Not
any, notdict, not untyped JSON crossing a module edge. [enforced for docstrings] - Errors are values or exceptions, consistently, never both in one layer. Pick per
language: exceptions in Python,
Result/tagged unions in Rust and TS where the codebase already does,errorreturns in Go. - No swallowed exceptions. [enforced, permanent budget zero] Catch what you can act on; let the rest travel.
- Names say what, not how.
charge_in_minor_units, notprocess_data_v2. - A file is one idea. When you cannot name it in three words it is two files.
Comments and docstrings [enforced]
Full rules in the llm-first-code skill. The short version: a comment carries what the
code cannot — why this and not the obvious alternative, what breaks if it changes, which
measurement drove it. Args: / Returns: / :param: are banned; the types say it.
Structure
- Feature-first, not layer-first.
billing/containing its routes, logic and tests beatscontrollers/ services/ models/split three ways across the tree. - Depend inward. Domain logic imports nothing from the framework. A test for it needs no server, no database and no network.
- One place to read configuration, at startup, typed and validated. Never
process.env.Xscattered through the code. - Migrations are additive. Expand, backfill, contract — never a destructive change in one step. [enforced past prototype]
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.
- 9d ago First seen · 96 lines · 31 tokens per session scan A 41bb7b0a7146
founder-defaults is a skill published in the GitHub repository avanturer/claude-bestpractice (2 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 1,103 once invoked, about $0.0002 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
wowerpoint
Turn one document into a kawaii NotebookLM slide-deck PDF. Use for "wowerpoint this", "make a deck about ", "turn this report into slides", or any request to render a single document as shareable narrative slides.
version-bump
Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, build verification, git tagging, GitHub releases, and changelog generation. NPM publishing is the final human-required handoff because the maintainer…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
claude-md-review
Audit a CLAUDE.md file for the patterns that actually degrade Claude Code's output — vagueness, unnamed files, stale facts, and bloat. Use when asked to review, audit, improve, shrink, or fix a CLAUDE.md, and when a project's results feel inconsistent or Claude keeps rediscovering the same context.
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.
summarize-transcript
Analyze and summarize a transcript, meeting notes, or discussion thread into a clear actionable document.