grants

grants is a skill for Claude Code, Codex from ericrisco/rsc-harness. It costs 87 tokens per session (2,666 once invoked), scanned A, original, MIT.

A guide for handling the hiring process from defining a role through screening, interviews, and the final hire decision.

In plain words
What is it for?
Use it to write job posts, screen candidates, design structured interviews, score applicants, and decide Hire, On-Hold, or No-Hire.
Why use it?
It replaces informal judgment with shared criteria and written evidence, making selection decisions more consistent and defensible.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to write job posts, screen candidates, design structured interviews, score…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ericrisco/rsc-harness/grants
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 ericrisco/rsc-harness --skill grants
Clone the repo
git clone --depth 1 https://github.com/ericrisco/rsc-harness

Made for: Claude Code, Codex.

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 grants

README.md
[![agentmods](https://agentmods.dev/badge/skills/ericrisco/rsc-harness/grants.svg)](https://agentmods.dev/skills/ericrisco/rsc-harness/grants)
Your own site
<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/grants"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/grants.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,666 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 $0.00087 $0.02666
Opus 5 $0.00044 $0.01333
Sonnet 5 $0.00017 $0.00533
Haiku 4.5 $0.00009 $0.00267

Measured 3d ago against content hash 9588b79ee2ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

grants 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/verify.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/grants/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grants — Win Money You Neither Repay Nor Give Equity For

Find the fit call, kill the weak ones early, register before the clock runs out, and write each section to clear the threshold the reviewer scores it against.

You are a reviewer-minded application writer. Before you write a word, reconstruct the scoring grid the evaluator will use and write backwards from the threshold they must clear to fund you. The output is never "a nice document" — it is a needs statement, a logic model, SMART objectives, an impact narrative, and a costed budget that each survive their own line of the rubric. Above-threshold is the bar; everything below it scores zero no matter how good the prose.

Route elsewhere

The ask Owner
Equity/VC round, cap table, term sheet, investor data room fundraising
The pitch deck / one-pager that sells the vision to a room pitch-deck
Company financial model, projections, runway, scenario P&L financial-model
Commercial B2B proposal / SOW that gets a paying buyer to sign proposals
The grant agreement's binding legal clauses (IP, liability, law) contracts
Post-award ledgers, fund accounting, spend tracking bookkeeping
Pricing, packaging, what to charge customers pricing

The non-dilutive landscape

Three lanes, and the rules live in different documents in each. Read the rule-document and the deadline-document before you draft — eligibility lives in one, the clock in the other.

Lane Where the rules live Where the deadline lives
Government grant (EU/US) The call text / solicitation / work programme The same call's submission deadline
Public subsidy (Spain) The bases reguladoras (who/what/requirements) The convocatoria (opens the window, fixes the year's pot)
Foundation award The funder's published priorities & guidelines The LOI / full-proposal deadlines

Calibrate effort to the odds. Horizon Europe overall success runs ~12–16%, the most competitive calls under 10% (some ~2%), and roughly 7 of 10 above-threshold proposals still go unfunded for lack of budget. Foundation LOIs are a hard filter: ~20–40% are invited to a full proposal on average, some funders ~10%. Above-threshold is necessary and nowhere near sufficient — which is exactly why go/no-go and rubric-maxing earn their keep.

Read the full file on GitHub · 154 lines

Files

What ships with it

6 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.

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. 3d ago First seen · 154 lines · 87 tokens per session scan A 9588b79ee2ef

Subscribe to this mod's changes

grants is a skill published in the GitHub repository ericrisco/rsc-harness (65 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 2,666 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 2026-09-03.