grant-intake

grant-intake is a skill for Claude Code from ddanntheman/GrantForge. It costs 86 tokens per session (883 once invoked), scanned A, original, MIT.

A skill that turns a grant announcement into a structured checklist of application requirements and a proceed-or-stop recommendation. A grant is funding offered for a defined project or purpose.

In plain words
What is it for?
Reviewing grant announcements, checking eligibility, organizing source documents, and preparing requirements for later research, drafting, budgeting, and review.
Why use it?
It helps reveal required documents, page limits, scoring rules, eligibility conditions, and other details that summaries can miss.

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 Reviewing grant announcements, checking eligibility, organizing source documents, and preparing requirements for later research, drafting, budgeting, and review.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/ddanntheman/grantforge/grant-intake.svg)](https://agentmods.dev/skills/ddanntheman/grantforge/grant-intake)
Your own site
<a href="https://agentmods.dev/skills/ddanntheman/grantforge/grant-intake"><img src="https://agentmods.dev/badge/skills/ddanntheman/grantforge/grant-intake.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 883 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 $0.00086 $0.00883
Opus 5 $0.00043 $0.00441
Sonnet 5 $0.00017 $0.00177
Haiku 4.5 $0.00009 $0.00088

Measured 7d ago against content hash f57e6081fa6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

grant-intake 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 7d 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/grant-intake/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grant Intake

Turn a funding announcement into a complete, testable specification of what the application must contain. Everything downstream (research, drafting, budget, review) works off the requirements matrix produced here.

Requires the .grantforge/ profile; if missing, run grant-setup first.

Step 1 — Acquire the full announcement

Accept an uploaded document (PDF/Word), a pasted excerpt, or a URL. If given a URL or partial text, fetch and read the complete announcement including all appendices — page limits and scoring rubrics often hide in attachments. For federal grants, check Grants.gov for the related documents package. Never proceed on a summary alone; ask for the full document if what was provided is clearly partial.

Step 2 — Create the grant workspace

Create .grantforge/grants/<funder>-<program>-<year>/ containing:

requirements.md      # The requirements matrix (this skill)
source/              # The announcement and attachments
research/            # Populated by grant-research
drafts/              # Populated by grant-draft
final/               # Submission-ready outputs

Register the opportunity in tracker.md with status intake.

Step 3 — Build the requirements matrix

Extract into requirements.md, as tables:

Overview: funder, program name, CFDA/ALN if federal, total pool, award range, match/cost-share requirement, indirect rate rules, period of performance, deadline (date, time, time zone), submission mechanism (portal, email, Grants.gov) and any registration lead time it implies.

Eligibility: every eligibility criterion as a row with columns Criterion | Our status | Evidence. Fill "Our status" from the org profile. Anything unverifiable becomes a question for the user.

Narrative requirements: one row per required section with columns Section | Prompt (verbatim) | Limit (pages/words/chars) | Points | Notes. Copy the funder's prompts verbatim — drafting will answer exactly these. Capture the scoring rubric weights if published; grant-review scores against them.

Read the full file on GitHub · 92 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. 7d ago First seen · 92 lines · 86 tokens per session scan A f57e6081fa6f

Subscribe to this mod's changes

grant-intake is a skill published in the GitHub repository ddanntheman/GrantForge (2 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 883 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.

Related

Other skills, from other repositories