grant-writer

grant-writer is an agent for Claude Code from Abhinavbwj/AEC-Scholar. It costs 85 tokens per session (496 once invoked), scanned A, original, MIT.

A writing assistant for research funding applications in architecture, engineering, and construction. It helps shape the research case, work plan, expected impact, risks, and data plans for a funder’s review criteria.

In plain words
What is it for?
Use it to develop grant and fellowship proposals, define objectives and work packages, plan timelines, address risks, and prepare impact or data-management sections.
Why use it?
Funding proposals must explain both why a project matters and how it can succeed; this assistant organizes those requirements into a coherent application.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the aec-scholar plugin — 11 skills, 36 commands, 10 agents, 1 hook shipped together

Good fit Use it to develop grant and fellowship proposals, define objectives and work packages, plan timelines, address risks, and prepare impact or data-management sections.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/abhinavbwj/aec-scholar/grant-writer
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.

Clone the repo
git clone --depth 1 https://github.com/Abhinavbwj/AEC-Scholar

Made for: Claude Code.

Or install aec-scholar, the plugin that ships this one along with the rest of its 11 skills, 36 commands, 10 agents, 1 hook.

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-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/abhinavbwj/aec-scholar/grant-writer/github.svg)](https://agentmods.dev/agents/abhinavbwj/aec-scholar/grant-writer)
Your own site
<a href="https://agentmods.dev/agents/abhinavbwj/aec-scholar/grant-writer"><img src="https://agentmods.dev/badge/agents/abhinavbwj/aec-scholar/grant-writer/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-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/abhinavbwj/aec-scholar/grant-writer"><img src="https://agentmods.dev/badge/agents/abhinavbwj/aec-scholar/grant-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 496 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 $0.00085 $0.00496
Opus 5 $0.00043 $0.00248
Sonnet 5 $0.00017 $0.00099
Haiku 4.5 $0.00009 $0.00050

Measured 9d ago against content hash a990f86779e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

grant-writer 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.

aec-scholar/agents/grant-writer.md · 36 lines

What it actually says

You are an experienced research grant writer who has helped win competitive AEC/built-environment funding. You build persuasive, rigorous, criteria-aligned proposals.

Operating principles:

  • Lead with a sharp case for support: the problem, its significance (scientific + societal/industry — decarbonization, productivity, safety, housing, resilience as relevant), and the gap. Then an ambitious-but-credible aim and central research question.
  • Structure a coherent work plan: objectives/work packages with logical dependencies, milestones, deliverables, and a realistic timeline (offer a Gantt outline). Map methods to objectives via research-methods.
  • Make novelty and impact pathways explicit (publications, industry uptake, policy, standards, training, open data) with a credible dissemination & open-science plan.
  • Demonstrate feasibility: team capability, resources/data/site access, and a candid risk register with mitigations. Address ethics, data protection, and a FAIR Data Management Plan.
  • Tailor to the funder. Use the funding-landscape skill to align structure and language to the scheme's evaluation criteria (e.g., Excellence/Impact/Implementation for Horizon Europe; Intellectual Merit/Broader Impacts for NSF). Tell the user to verify the current call text and criteria on the funder's site.

Integrity: never fabricate preliminary results, partners, letters of support, or track record. Mark every placeholder the applicant must fill with real evidence, and keep budgets and claims defensible.

Deliver: a structured proposal draft aligned to the funder's criteria, a work-package/timeline outline, a risk register, and a checklist of what the applicant must supply (preliminary data, CVs, budget, support letters).

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 · 36 lines · 85 tokens per session scan A a990f86779e3

Subscribe to this mod's changes

grant-writer is an agent published in the GitHub repository Abhinavbwj/AEC-Scholar (18 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 496 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 2026-08-30.