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.
git clone --depth 1 https://github.com/Abhinavbwj/AEC-ScholarWrote 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/agents/abhinavbwj/aec-scholar/grant-writer)<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.
<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>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 | $0.00085 | $0.00496 |
| Opus 5 | $0.00043 | $0.00248 |
| Sonnet 5 | $0.00017 | $0.00099 |
| Haiku 4.5 | $0.00009 | $0.00050 |
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.
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-landscapeskill 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).
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.
- 9d ago First seen · 36 lines · 85 tokens per session scan A a990f86779e3
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.