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 jmsktm/claude-settings --skill grant-writergit clone --depth 1 https://github.com/jmsktm/claude-settingsWrote 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/jmsktm/claude-settings/grant-writer)<a href="https://agentmods.dev/skills/jmsktm/claude-settings/grant-writer"><img src="https://agentmods.dev/badge/skills/jmsktm/claude-settings/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/skills/jmsktm/claude-settings/grant-writer"><img src="https://agentmods.dev/badge/skills/jmsktm/claude-settings/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 | $0.00014 | $0.01138 |
| Opus 5 | $0.00007 | $0.00569 |
| Sonnet 5 | $0.00003 | $0.00228 |
| Haiku 4.5 | $0.00001 | $0.00114 |
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 6d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 6d ago First seen · 105 lines · 14 tokens per session scan A 2c7b337c3003
Grant Writer is a skill published in the GitHub repository jmsktm/claude-settings (9 stars, last pushed 7mo ago), with no licence file. It adds 14 tokens to every session and 1,138 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
grant-intake
Parse a grant opportunity into a structured requirements matrix and issue a go/no-go recommendation. This skill should be used when the user says "here's a grant we want to apply for", "respond to this RFP", "parse this NOFO", "we're applying for X grant", "are we eligible for this?", or uploads a funding…
grant-setup
First-run setup for GrantForge. This skill should be used when the user says "set up GrantForge", "set up my organization", "enter my company information", "create my org profile", or when any other GrantForge skill runs and no .grantforge/ profile exists yet. Conducts a structured interview about the organization and…
grant-draft
Write the grant application narrative. This skill should be used when the user says "draft the application", "write the need statement", "draft the project narrative", "write our response to section X", or after research is complete for a grant in the pipeline. Produces section drafts that answer the funder's prompts…
house-style
GrantForge's shared writing standard. This skill should be read by every GrantForge skill that produces prose (grant-draft, grant-review, grant-budget, grant-research). It defines the professional grant-writing voice, the list of banned AI writing patterns, and the humanization pass that removes machine tells from…
grant-discover
Find open funding opportunities that match the organization's profile. This skill should be used when the user says "find grants for us", "what grants are we eligible for", "search for funding opportunities", "any new grants this month", or asks about funding sources for a specific program or project idea.
grant-research
Gather the evidence base and funder intelligence for a grant application. This skill should be used when the user says "research this grant", "find statistics for our need statement", "research the funder", "who has this foundation funded before", "find citations to support X", or after grant-intake completes and…