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/ddanntheman/grantforge/grant-draftnpx skills add ddanntheman/GrantForge --skill grant-draftgit 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/grant-draft)<a href="https://agentmods.dev/skills/ddanntheman/grantforge/grant-draft"><img src="https://agentmods.dev/badge/skills/ddanntheman/grantforge/grant-draft.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 | $0.00076 | $0.00948 |
| Opus 5 | $0.00038 | $0.00474 |
| Sonnet 5 | $0.00015 | $0.00190 |
| Haiku 4.5 | $0.00008 | $0.00095 |
Grade A, and why
grant-draft 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 4d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grant Draft
Write narrative that a reviewer scores highly and a skeptic cannot identify as machine-written. Draft section by section, never the whole application in one pass.
Before writing
Read, in order: the requirements matrix (requirements.md), the research
files (research/evidence.md, research/funder.md), the org profile
(.grantforge/profile/organization.md), the voice profile
(profile/voice.md if present), relevant boilerplate
(profile/boilerplate/), and the house-style skill. If research files are
missing, run grant-research first — drafting without an evidence base
produces assertions, not arguments.
Section discipline
For each narrative section in the requirements matrix:
- Answer the verbatim prompt. Reviewers score against their question, not against what the writer wished they had asked. Open the section by directly addressing the prompt's core ask; never open with org history unless the prompt asks for it.
- Respect the limit with headroom. Draft to ~95% of the word/page/ character limit. Report the count to the user with every draft. For portal submissions, count characters the way portals do (spaces included, unless the funder says otherwise).
- Load-bearing evidence. Every claim of need or effectiveness cites an
entry from
research/evidence.md. Every capability claim traces to the org profile. Nothing invented, ever. Missing support becomes a question to the user, asked before drafting continues. - Mirror the rubric. Where the funder published scoring criteria, check the draft covers every scored element, weighted roughly by points.
- Adapt boilerplate, never paste it. The answer library provides raw material; rewrite it to this funder's vocabulary, this project's facts, and this prompt's angle.
Standard section craft
- Need/problem statement: local data first, national context second, one to two sentences of human texture. End with the gap this project fills — not with a pitch.
- Project description: what, who, where, when, how many, delivered by whom. Activities map visibly to objectives; objectives are measurable and time-bound (SMART without using the acronym).
- Goals/objectives/outcomes: distinguish outputs (what the org does) from outcomes (what changes). Give each objective a target, a measure, and a data source.
- Evaluation plan: who collects what data, with what instrument, on what schedule, and how findings feed back into the program. Name an evaluator if the budget includes one.
- Organizational capacity: prove it with track record, named staff qualifications, and financial stewardship facts (clean audits, past federal awards managed) — not adjectives.
- Sustainability: name realistic funding continuation paths; funders read "we will seek other grants" as no plan.
- Timeline/logic model: build as a table or exhibit when allowed; offer a logic model whenever the funder is federal or education-sector.
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.
- 4d ago First seen · 91 lines · 76 tokens per session scan A d4a8b8ef647b
grant-draft is a skill published in the GitHub repository ddanntheman/GrantForge (2 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 948 once invoked, about $0.0004 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
Help professors and researchers write, revise, adapt, and polish grant proposals for US agencies (NSF, NIH, DOE, DARPA, NASA) and Chinese agencies (NSFC 国自然).
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…
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.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.