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 neuromechanist/research-skills --skill grant-writinggit clone --depth 1 https://github.com/neuromechanist/research-skillsWrote 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/neuromechanist/research-skills/grant-writing)<a href="https://agentmods.dev/skills/neuromechanist/research-skills/grant-writing"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/grant-writing/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/neuromechanist/research-skills/grant-writing"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/grant-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 294 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 295 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
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 | $0.00252 | $0.04935 |
| Opus 5.5 | $0.00101 | $0.01974 |
| Sonnet 5.5 | $0.00050 | $0.00987 |
| Haiku 4.5 | $0.00025 | $0.00494 |
Grade A, and why
grant-writing 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 3d 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grant Writing Skill
Provides procedural knowledge for drafting NIH and NSF grant proposals with mechanism-specific formatting, section structure, and scientific writing best practices.
Supported Mechanisms
| Agency | Mechanism | Key Format |
|---|---|---|
| NIH | R01 | 1p aims + 12p strategy |
| NIH | R21 | 1p aims + 6p strategy |
| NIH | R03 | 1p aims + 6p strategy (2 years, $50K/year) |
| NIH | DP2 | 10p essay (no aims page) |
| NIH | K99/R00 | 1p aims + 12p strategy + 6p candidate + 6p mentoring |
| NIH | K08/K23 | 1p aims + 12p strategy + candidate section + career goals + mentoring plan |
| NIH | F31/F32 | 1p aims + 6p strategy + applicant background + sponsor info + training plan |
| NIH | R24 | 1p aims + 12p strategy (resource-focused) |
| NIH | R43/R41 (SBIR/STTR Phase I) | 1p milestone-driven aims + 6p strategy; no Commercialization Plan allowed |
| NIH | R44/R42 (SBIR/STTR Phase II, Fast-Track, Direct to Phase II) | 1p milestone-driven aims + 12p strategy + 12p Commercialization Plan |
| NSF | Standard | 1p summary + 15p project description |
| NSF | CAREER | Integrates research + education (see references/career-award-guide.md) |
Core Workflow
Step 0: Parse the NOFO/FOA
Before writing anything, read the Notice of Funding Opportunity (NOFO) or Funding Opportunity Announcement (FOA) thoroughly. Extract and record:
- Mechanism and agency: Determines page limits, required sections, and review criteria
- Specific objectives: Many NOFOs list required research areas, populations, or methods
- Page limits: Verify per-section limits (they vary by mechanism and can change between cycles)
- Review criteria and weights: Identify how the review panel will score the application
- Special requirements: Data sharing plans, milestones, letters of support, human subjects provisions
- Eligible PIs: Career stage, citizenship, institutional requirements
- Budget constraints: Direct cost caps, duration limits, cost-sharing restrictions
- Submission deadline and receipt date: Plan backward from the deadline
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/budget-justification-template.md 3.9 KB
- examples/nsfproposal.cls 3.1 KB
- examples/sbir-specific-aims-template.md 11 KB
- examples/specific-aims-template.md 3.4 KB
- references/budget-justification-guide.md 6.4 KB
- references/career-award-guide.md 6.7 KB
- references/commercialization-plan-guide.md 12 KB
- references/niaid-sample-applications.md 16 KB
- references/nih-requirements.md 9.1 KB
- references/nsf-requirements.md 4.0 KB
- references/research-strategy-guidelines.md 5.9 KB
- references/resubmission-guide.md 6.1 KB
- references/sbir-sttr-requirements.md 20 KB
- references/tone-guide.md 5.3 KB
- references/writing-style-guide.md 5.9 KB
- scripts/fetch-niaid-samples.sh 6.4 KB runs code
- scripts/niaid-samples.txt 1.1 KB
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.
- 3d ago Changed 3f9d0871ead3
- 7d ago Changed · +15 lines c7f1f13e5948
- 15d ago Changed · +1 lines c2ee2d6eee3b
- 1mo ago Changed 84b32156085b
- 2mo ago First seen · 297 lines · 252 tokens per session scan A a7cde3df21f9
grant-writing is a skill published in the GitHub repository neuromechanist/research-skills (51 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 252 tokens to every session and 4,935 once invoked, about $0.0010 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 2026-08-30.
grant-writing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| grant-writingneuromechanist/research-skills | Skill | 51 | yesterday | BSD-3-Clause | A | 252 | Claude Code |
| godot-optimizationjame581/GodotPrompter | Skill | 933 | 6d ago | MIT | A | 28 | Claude Code |
| food-analyzermickpletcher/AI-Skills | Skill | 20 | 3d ago | MIT | A | 41 | Claude Code, Codex |
| astrophotography-processingmickpletcher/AI-Skills | Skill | 20 | 3d ago | MIT | A | 44 | Claude Code |
| scienceworld-measurement-takerzjunlp/SkillNet | Skill | 1.4k | 5d ago | MIT | A | 81 | Claude Code, Codex |
| scienceworld-threshold-evaluatorzjunlp/SkillNet | Skill | 1.4k | 5d ago | MIT | A | 69 | Claude Code, Codex |
| scienceworld-animal-identifierzjunlp/SkillNet | Skill | 1.4k | 5d ago | MIT | A | 83 | Claude Code, Codex |