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 ralfyishere/rules-with-receipts --skill divergent-ideationgit clone --depth 1 https://github.com/ralfyishere/rules-with-receiptsWrote 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/ralfyishere/rules-with-receipts/divergent-ideation)<a href="https://agentmods.dev/skills/ralfyishere/rules-with-receipts/divergent-ideation"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/divergent-ideation/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/ralfyishere/rules-with-receipts/divergent-ideation"><img src="https://agentmods.dev/badge/skills/ralfyishere/rules-with-receipts/divergent-ideation.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 | $0.00136 | $0.01596 |
| Opus 5 | $0.00068 | $0.00798 |
| Sonnet 5 | $0.00027 | $0.00319 |
| Haiku 4.5 | $0.00014 | $0.00160 |
Grade A, and why
Divergent Ideation 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 12d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Divergent Ideation
Purpose
The default failure of idea generation isn't bad ideas — it's narrow ones: the first workable concept arrives, and everything after is that concept wearing different hats. Real option value comes from ideas with different core mechanisms. This skill separates divergence (generate wide, judgment off) from convergence (filter hard, judgment on), because doing both at once does both badly.
When to use this skill
- Explicit generation asks: brainstorms, naming, campaign concepts, feature ideas, alternative designs.
- The first attempt at any open-ended problem — before committing to an approach that arrived unexamined (
plan-gate's risk section deserves real alternatives). - Mid-task, when stuck: circling one approach that isn't working is a divergence trigger, not a push-harder trigger.
- Open / improve / turnaround mandates ("improve this", "what would you do", "do what you think"): generate unplanted angles proactively instead of waiting to be handed a direction — this is where the first idea most silently becomes the only idea. (Distinct from
open-mandate, which chooses the direction; this skill first widens the option set the choice is made from.)
When NOT to use this skill
- Problems with a verifiable correct answer — go verify, don't ideate.
- Established-convention decisions (code formatting, standard patterns) where novelty is a cost, not a value.
- When the user has chosen and wants execution: re-opening the option space uninvited is
scope-fenceterritory.
Operating procedure
1 — Frame the actual problem (one line, from intent-clarity): what the ideas must accomplish and the 2–3 real constraints. Under-constrained ideation produces volume without relevance; over-constrained reproduces the status quo.
2 — Diverge with judgment OFF. Generate 8–15 raw options. The count is functional, not decorative: the first ~3 ideas are the obvious ones everyone has; the different-mechanism ideas live past them. No evaluating, no "but that wouldn't work" — evaluation mid-generation kills exactly the unusual candidates this phase exists to surface.
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.
- 12d ago First seen · 75 lines · 136 tokens per session scan A 0a0e44f941c6
Divergent Ideation is a skill published in the GitHub repository ralfyishere/rules-with-receipts (2 stars, last pushed 2mo ago), licensed MIT. It adds 136 tokens to every session and 1,596 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 2026-08-31.
Other skills, from other repositories
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
setup-matt-pocock-skills
A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.
frontend-design
A design guide for building polished web interfaces such as pages, dashboards, forms, navigation, and reusable UI components. It covers HTML, CSS, JavaScript, and common frontend frameworks.
alterlab-cobrapy
Build and analyze genome-scale constraint-based metabolic models with COBRApy — flux balance analysis (FBA), flux variability analysis (FVA), gene and reaction knockouts, flux sampling, and SBML model I/O. Use when simulating metabolic networks, predicting growth or knockout phenotypes, or running systems-biology and…
alterlab-depmap
Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use when identifying cancer-specific genetic vulnerabilities, finding synthetic lethal interactions, checking whether a gene is essential in given cell lines, or…
alterlab-qutip
Simulates open quantum systems with QuTiP, the Quantum Toolbox in Python, solving Lindblad master equations (mesolve), Monte Carlo trajectories (mcsolve), and unitary dynamics (sesolve). Use when studying master-equation or Lindblad dynamics, decoherence, dissipation, quantum optics, cavity QED, or open-system time…