house-style

house-style is a skill for Claude Code from ddanntheman/GrantForge. It costs 96 tokens per session (1,046 once invoked), scanned A, original, MIT.

A shared writing guide for GrantForge's grant-related skills. It sets standards for clear, evidence-based, human-sounding grant applications and reviews.

In plain words
What is it for?
Use it when drafting or reviewing grants, budgets, research, or other GrantForge materials.
Why use it?
It keeps grant documents consistent and helps remove vague claims and writing patterns that can make them sound automated.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the grantforge plugin — 9 skills, 1 command shipped together

Good fit Use it when drafting or reviewing grants, budgets, research, or other GrantForge materials.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ddanntheman/grantforge/house-style
Install

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.

Any agent
npx skills add ddanntheman/GrantForge --skill house-style
Clone the repo
git clone --depth 1 https://github.com/ddanntheman/GrantForge

Made for: Claude Code.

Or install grantforge, the plugin that ships this one along with the rest of its 9 skills, 1 command.

Wrote 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.

agentmods badge for house-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/ddanntheman/grantforge/house-style/github.svg)](https://agentmods.dev/skills/ddanntheman/grantforge/house-style)
Your own site
<a href="https://agentmods.dev/skills/ddanntheman/grantforge/house-style"><img src="https://agentmods.dev/badge/skills/ddanntheman/grantforge/house-style/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.

agentmods 80×15 button for house-style

Your own site · 80×15
<a href="https://agentmods.dev/skills/ddanntheman/grantforge/house-style"><img src="https://agentmods.dev/badge/skills/ddanntheman/grantforge/house-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,046 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00096 $0.01046
Opus 5 $0.00048 $0.00523
Sonnet 5 $0.00019 $0.00209
Haiku 4.5 $0.00010 $0.00105

Measured 8d ago against content hash e712d925e076, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

house-style 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 8d 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.

plugins/grantforge/skills/house-style/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GrantForge House Style

The purpose of this standard is simple: a reviewer reading the finished application should conclude that an experienced, careful human wrote it. Apply this standard to every sentence of every deliverable.

Voice

Write like a senior grant writer with subject-matter depth, not like a marketing department and not like a language model.

  • Confident and direct. State what the organization does and will do. Avoid hedges ("we hope to," "we aim to strive toward").
  • Concrete over abstract. Numbers, place names, program names, dates, and named staff beat generalities every time. "Served 412 students across three Title I schools in 2025" not "served many students in under-resourced communities."
  • Evidence-forward. Claims of need or effectiveness carry a citation or an internal data point. Never invent statistics; if a figure is not in the org profile or research file, ask for it or find it.
  • Warm but never saccharine. The reader should sense real people doing real work, without emotional manipulation.
  • Funder's vocabulary. Mirror the terminology of the RFP/NOFO (their program names, their priority labels, their defined terms). Reviewers score against their own language.

Banned AI patterns

Never use the following. During the humanization pass, hunt for them and rewrite any sentence containing one.

Banned punctuation and formatting

  • Em-dashes (—). Restructure the sentence or use a comma, colon, or period.
  • Emoji, decorative symbols, checkmark/status characters.
  • Bolded phrase followed by a colon as a pseudo-heading inside paragraphs.
  • Overuse of triads ("efficient, effective, and equitable") — one triad per page maximum, and only when the content genuinely comes in threes.

Banned words and stock phrases delve, leverage (as a verb), robust, holistic, seamless, cutting-edge, state-of-the-art, innovative solutions, transformative journey, empower (when vague), foster (when vague), landscape (metaphorical), tapestry, testament to, underscore, spearhead, synergy, paradigm, "it's important to note", "in today's world", "in an ever-changing", "at the end of the day", "a wide range of", "plays a vital/crucial role", "is committed to excellence", "we are excited to", "stands as", "serves as a beacon", "moreover/furthermore" as paragraph openers, "not only X but also Y" (more than once per document), "whether X or Y" constructions used as filler.

Read the full file on GitHub · 103 lines

Changes

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.

  1. 8d ago First seen · 103 lines · 96 tokens per session scan A e712d925e076

Subscribe to this mod's changes

house-style is a skill published in the GitHub repository ddanntheman/GrantForge (2 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 1,046 once invoked, about $0.0005 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.