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 grant-setupgit 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-setup)<a href="https://agentmods.dev/skills/ddanntheman/grantforge/grant-setup"><img src="https://agentmods.dev/badge/skills/ddanntheman/grantforge/grant-setup/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/grant-setup"><img src="https://agentmods.dev/badge/skills/ddanntheman/grantforge/grant-setup.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 | $0.00091 | $0.01103 |
| Opus 5.5 | $0.00036 | $0.00441 |
| Sonnet 5.5 | $0.00018 | $0.00221 |
| Haiku 4.5 | $0.00009 | $0.00110 |
Grade A, and why
grant-setup 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 1mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grant Setup
Build the organization's persistent GrantForge workspace. Every other skill in this plugin reads from it, so completeness here pays off on every future application.
Prerequisite: a working folder
The profile must persist across sessions, so it lives in a folder on the user's computer, not in temporary session storage. If no folder is connected, ask the user to connect one (their grants folder, or wherever they want GrantForge to live) before proceeding.
Workspace structure
Create this inside the connected folder:
.grantforge/
├── profile/
│ ├── organization.md # The org dossier
│ ├── voice.md # Writing voice preferences
│ └── boilerplate/ # Reusable answer library
│ ├── need-statement.md
│ ├── org-capacity.md
│ ├── evaluation-plan.md
│ └── ...
├── grants/ # One subfolder per application (created by grant-intake)
└── tracker.md # Pipeline tracker (created by grant-tracker)
The interview
Conduct the interview conversationally, in stages, using multiple-choice questions where options are predictable and free text where they are not. Do not ask for everything at once; group related items. If the user uploads existing documents (annual report, past applications, 990, capability statement, website URL), extract answers from them first and only ask about gaps. Offer document upload before starting the question list — past grant applications are the single richest source.
Stage 1 — Identity and legal
- Legal name, dba if any, entity type (501(c)(3), government, school district, university, for-profit, fiscal sponsorship arrangement)
- EIN, UEI, SAM.gov registration status and expiration, DUNS legacy if known
- Founding year, headquarters, service area (be geographic and specific)
- Website, primary contact for grants
Stage 2 — Mission and programs
- Mission statement (verbatim)
- Each major program: name, what it does, who it serves, scale (people served per year), evidence of effectiveness
- Population served: demographics, geography, need indicators the org already tracks
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.
- 1mo ago First seen · 122 lines · 91 tokens per session scan A bc77fd07a8e9
grant-setup is a skill published in the GitHub repository ddanntheman/GrantForge (2 stars, last pushed 3mo ago), licensed MIT. It adds 91 tokens to every session and 1,103 once invoked, about $0.0004 per session on Opus 5.5. 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
merge-review
Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.
workspace
Multi-repo campaign coordinator. Same lifecycle as fleet -- scope claims, discovery relay, wave-based execution -- but the unit of work is a repo, not a file. Coordinates campaigns across repositories with shared context.
decision-map
Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big for a single intake item. Resolved tickets graduate into .planning/intake/ for…
unharness
Safely leave Citadel using the active adoption receipt. Produces a no-write, reviewable plan, preserves a portable archive, removes only exact owned material, and reports modified or externally registered surfaces as retained or unknown. Legacy installs must be imported before exact leave is claimed.
grants
Use when pursuing non-dilutive public or foundation funding — money you neither repay nor give equity for: finding a fit call, go/no-go, registration (UEI/PIC/BDNS), or writing the rubric-scored application, logic model, budget justification, or LOI. NOT an equity round (that is fundraising), NOT a paying-customer SOW…
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.