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 ddanntheman/GrantForge --skill house-stylegit clone --depth 1 https://github.com/ddanntheman/GrantForgeWrote 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/ddanntheman/grantforge/house-style)<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.
<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>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 | $0.00096 | $0.01046 |
| Opus 5 | $0.00048 | $0.00523 |
| Sonnet 5 | $0.00019 | $0.00209 |
| Haiku 4.5 | $0.00010 | $0.00105 |
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.
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.
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.
- 8d ago First seen · 103 lines · 96 tokens per session scan A e712d925e076
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.
Other skills, from other repositories
inno-grant-proposal
A writing aid for preparing and improving research grant proposals for US and Chinese funding agencies.
Grant Writer
Craft compelling grant proposals that secure funding for nonprofits and research.
kami-deck
A lab-meeting deck on gut-microbiome links to sleep quality — the design, the results, the caveats, and the next experiment. Built as a decision-grade academic research deck for lab group, PI.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.