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/alphabravo-oss/guild/house-rulesnpx skills add alphabravo-oss/guild --skill house-rulesgit clone --depth 1 https://github.com/alphabravo-oss/guildWrote 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/alphabravo-oss/guild/house-rules)<a href="https://agentmods.dev/skills/alphabravo-oss/guild/house-rules"><img src="https://agentmods.dev/badge/skills/alphabravo-oss/guild/house-rules.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.03626 |
| Opus 5 | $0.00024 | $0.01813 |
| Sonnet 5 | $0.00010 | $0.00725 |
| Haiku 4.5 | $0.00005 | $0.00363 |
Grade A, and why
house-rules 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
House rules
The four plugins this replaces could all write documentation. None of them could tell you which sentences were true. These are the rules that close that gap.
1. The governing rule
A sentence about behaviour needs a source, or it needs a tag. There is no third option and no exemption for sentences that are obviously true.
A source is one of:
- a
file:lineanchor that resolves in the current tree - a command plus the output it actually produced
- a named test that covers the behaviour
- the screen, for a claim about what a reader sees. "The Deployments page has a New button"
is checked by looking at it, and the anchor is the component that renders it or a screenshot
in the page. This class exists because without it every sentence on a user page has to be
justified against source code, and a writer who spends the day in source writes about source.
survey.pyreturns the product's own on-screen wording underuser_surface
Write the anchor down as you go. Reconstructing sources afterwards does not work, because by then you no longer remember which sentences you checked and which ones you assumed.
2. Working notation, and where it stops
While drafting, mark what you have not verified. Four tags, borrowed from HADS:
[SPEC] Authoritative. Sourced. Terse.
[NOTE] Human context, history, reasoning. Not a behavioural claim.
[BUG] A verified failure. Requires symptom, cause, fix.
[?] Inferred, not verified. Says what would settle it.
None of it ships. These tags are for the draft and for the plan. A reader who opens a
product's documentation and finds [?] in the middle of a sentence is being shown the tooling
that produced the page, and no product does that.
The honesty the tag carries is not optional, only the notation is. Before publishing, every [?]
resolves one of three ways:
- Go and check it. Then it is a plain sentence.
- Say it in ordinary words. "This has not been tested against a live server" is honest, readable, and belongs on the page.
- Cut the sentence. Silence is better than a claim nobody stands behind.
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 · 273 lines · 48 tokens per session scan A 4f5842e1c372
house-rules is a skill published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 3,626 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…