grant-budget

grant-budget is a skill for Claude Code from ddanntheman/GrantForge. It costs 57 tokens per session (589 once invoked), scanned A, original, MIT.

A grant-budgeting skill that creates an Excel budget workbook and a matching written explanation. A grant is funding awarded for a defined project, and the narrative explains how the requested money will be spent.

In plain words
What is it for?
Use it to prepare budget periods, personnel, fringe benefits, travel, equipment, supplies, indirect costs, and required grant forms without inventing salary or vendor figures.
Why use it?
It keeps the amounts in the written explanation aligned with the workbook and checks them against the funder's rules.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

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

Good fit Use it to prepare budget periods, personnel, fringe benefits, travel, equipment, supplies, indirect costs, and required grant forms without inventing salary or vendor figures.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ddanntheman/grantforge/grant-budget"><img src="https://agentmods.dev/badge/skills/ddanntheman/grantforge/grant-budget.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 589 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 $0.00057 $0.00589
Opus 5 $0.00028 $0.00295
Sonnet 5 $0.00011 $0.00118
Haiku 4.5 $0.00006 $0.00059

Measured 9d ago against content hash 639577384e8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

grant-budget 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 9d 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-budget/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grant Budget

Produce a budget the program officer can defend and an auditor cannot puncture: an Excel workbook plus a narrative where every number in the narrative matches the workbook exactly.

Inputs

Read the requirements matrix for: award ceiling/floor, match or cost-share percentage, indirect cost rules (de minimis 10% MTDC vs. negotiated rate), allowable/unallowable costs, budget period(s), and required forms (e.g., SF-424A). Read the project description draft so the budget funds exactly the activities the narrative promises — reviewers cross-check.

Gather from the user what the profile does not contain: salaries or salary bands for named roles, fringe rate, and real vendor quotes for major purchases. Never invent compensation figures.

Workbook (final/budget.xlsx)

Build with the spreadsheet toolchain, one budget period per sheet plus a summary sheet for multi-year awards. Standard categories (adapt to the funder's own form when one is prescribed):

Personnel (role, annual salary, FTE%, months, request), Fringe (rate applied to personnel), Travel (trips × people × cost basis), Equipment (per-unit ≥ the funder's capitalization threshold, usually $5,000), Supplies, Contractual (each consultant with day rate and days), Other, Total Direct, Indirect (show base and rate), Total, and Match columns where required.

Rules: every line computes from visible unit assumptions (formulas, not typed totals); match column shows source of match and whether cash or in-kind; indirect base excludes items the rate agreement excludes; grand total lands within the award range. Round to whole dollars.

Narrative (drafts/budget-narrative.md → docx)

One paragraph per line item, in the funder's category order: what it is, how the cost was computed (unit × rate × time, quote, or salary basis), and why it is necessary for the project — tie each item to an activity in the project narrative. Apply the house style; budget narratives are prose, not tables restated.

Verification pass

Read the full file on GitHub · 62 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. 9d ago First seen · 62 lines · 57 tokens per session scan A 639577384e8b

Subscribe to this mod's changes

grant-budget is a skill published in the GitHub repository ddanntheman/GrantForge (2 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 589 once invoked, about $0.0003 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.