grant-proposal

grant-proposal is a skill for Claude Code from pedrohcgs/claude-code-my-workflow. It costs 131 tokens per session (2,910 once invoked), scanned A, original, MIT.

A guided framework for drafting a research funding proposal for funders such as NSF, NIH, ERC, or foundations. It combines an existing research plan with sections on data management, facilities, prior work, budget, and timing.

In plain words
What is it for?
Use it to draft a proposal, assemble required boilerplate, or revise aims after reviewer feedback; it does not submit the proposal.
Why use it?
It helps keep the proposal's aims, methods, budget, timeline, and required supporting sections consistent.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Good fit Use it to draft a proposal, assemble required boilerplate, or revise aims after reviewer feedback; it does not submit the proposal.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pedrohcgs/claude-code-my-workflow/grant-proposal
About the project

claude-code-my-workflow is a forkable setup for using Claude Code to produce and review academic papers, slides, data analyses, and replication packages. Researchers use its agents, skills, rules, hooks, and quality checks to coordinate these tasks and verify their results. The catalogue entries define the reusable workflow components for Claude Code.

pedrohcgs/claude-code-my-workflow · 1,566 stars · on GitHub · psantanna.com

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 pedrohcgs/claude-code-my-workflow --skill grant-proposal
Clone the repo
git clone --depth 1 https://github.com/pedrohcgs/claude-code-my-workflow

Made for: Claude Code.

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-proposal

README.md
[![agentmods](https://agentmods.dev/badge/skills/pedrohcgs/claude-code-my-workflow/grant-proposal.svg)](https://agentmods.dev/skills/pedrohcgs/claude-code-my-workflow/grant-proposal)
Your own site
<a href="https://agentmods.dev/skills/pedrohcgs/claude-code-my-workflow/grant-proposal"><img src="https://agentmods.dev/badge/skills/pedrohcgs/claude-code-my-workflow/grant-proposal.svg" alt="Measured on agentmods" height="20"></a>
Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,910 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 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 Agent Snooping · line 131
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 132
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 133
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 134
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 135
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00131 $0.02910
Opus 5 $0.00066 $0.01455
Sonnet 5 $0.00026 $0.00582
Haiku 4.5 $0.00013 $0.00291

Measured 8d ago against content hash e37e24b48844, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

grant-proposal 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 8d 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.

.claude/skills/grant-proposal/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/grant-proposal — Research Grant Proposal Scaffolder

Compose a funder-shaped grant proposal draft from primitives you already have: an /interview-me research spec supplies the science, /data-management-plan supplies the DMP, /capture-environment supplies the facilities/computational statement, and /lit-review supplies the prior-work framing. This skill structures and stitches — it does not submit anywhere, and it does not invent identification strategy where a spec is absent.

Core principle: A proposal is a coherence artifact. Aims, methods, budget, timeline, and broader impacts must agree with each other and with the underlying research spec. The skill's main value-add over a blank template is the Phase 3 coherence pass (aims ↔ methods ↔ budget ↔ timeline).

When to use

  • Drafting an NSF / NIH / ERC / foundation proposal from an existing research idea.
  • Turning an /interview-me spec (or a /preregister PAP) into a fundable narrative.
  • Assembling the boilerplate-but-required pieces (DMP, facilities, data-sharing) so the human writes only the science.
  • During resubmission, re-scaffolding aims after a reviewer "revise and resubmit" round.

When NOT to use

  • You need the science itself invented — run /interview-me first; this skill refuses to fabricate an identification strategy.
  • The sponsor is a clinical-trial funder requiring its own protocol template (out of scope; use the sponsor's native forms).
  • You want a finished, submittable PDF — this writes Markdown sections + a checklist; final assembly into the sponsor's format is yours.

Funder profiles

Generic across sponsors via placeholder profiles. --funder selects the section set + naming; default is nsf.

Funder Core sections (named per sponsor) Page/format signals
nsf Project Summary (Overview/Intellectual Merit/Broader Impacts) · Project Description · Broader Impacts · Data Management & Sharing Plan · Facilities/Equipment · Budget Justification 15-page Project Description; DMSP required
nih Specific Aims (1 p.) · Research Strategy (Significance/Innovation/Approach) · Vertebrate/Human Subjects (if any) · Data Management & Sharing · Facilities & Other Resources · Budget Justification Aims page is load-bearing
erc Extended Synopsis (B1) · Scientific Proposal (B2: state-of-art, objectives, methodology) · CV + track record · Resources/Budget · Data Management PI-centric; "high-risk/high-gain" framing
foundation Project Summary · Statement of Need · Goals & Objectives · Methods/Approach · Evaluation Plan · Budget Justification · Sustainability Mission-fit framing; lighter methods

Read the full file on GitHub · 146 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. 8d ago First seen · 146 lines · 131 tokens per session scan A e37e24b48844

Subscribe to this mod's changes

grant-proposal is a skill published in the GitHub repository pedrohcgs/claude-code-my-workflow (1,566 stars, last pushed 14d ago), licensed MIT. It adds 131 tokens to every session and 2,910 once invoked, about $0.0007 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.

Related

Other skills, from other repositories