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 andreaswasita/copilot-agents-dojo --skill demand-elegancegit clone --depth 1 https://github.com/andreaswasita/copilot-agents-dojoWrote 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/andreaswasita/copilot-agents-dojo/demand-elegance)<a href="https://agentmods.dev/skills/andreaswasita/copilot-agents-dojo/demand-elegance"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/demand-elegance/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/andreaswasita/copilot-agents-dojo/demand-elegance"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/demand-elegance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00016 | $0.01079 |
| Opus 5 | $0.00008 | $0.00540 |
| Sonnet 5 | $0.00003 | $0.00216 |
| Haiku 4.5 | $0.00002 | $0.00108 |
Grade A, and why
demand-elegance 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 10d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demand Elegance Skill
Forces the agent to challenge its own non-trivial diff before presenting it: fewer moving parts, standard patterns over custom abstractions, boring over clever. Does NOT apply to typos, one-line fixes, or hotfixes — over-engineering trivial work is the failure mode this skill explicitly avoids.
When to Use
- A fix feels hacky, fragile, or "barely working".
- Multiple solutions exist and the tradeoffs aren't obvious.
- The diff is large and includes infrastructure the original task didn't ask for.
- Refactoring with simplification as the explicit goal.
- Self-review before presenting any non-trivial solution.
- NOT for: typos, one-line bugfixes, comment edits, formatting, production hotfires.
Prerequisites
- A working solution (or near-working) to challenge — don't run this on a blank canvas.
- The full diff visible (
git diffvia thepowershelltool). - Willingness to throw work away if a simpler approach exists.
How to Run
1. Confirm the change is non-trivial. If trivial, skip — see Pitfalls.
2. Run the Elegance Check (4 questions in Procedure §1).
3. Apply the Simplicity Ladder (Procedure §2) to choose between options.
4. Self-review the diff as if it were someone else's PR.
5. If hacky, restart with the elegant approach — don't deodorize the smell.
Quick Reference
| Question | If answer is "yes" → action |
|---|---|
| Is there a more elegant way? | Try it before shipping. |
| Knowing what I know now, would I build it this way? | If no, refactor before presenting. |
| Can I reduce moving parts? | Cut them. |
| Would a senior engineer raise an eyebrow? | They would. Fix it. |
| Choose | Over |
|---|---|
| Fewer lines | More lines (all else equal) |
| Standard patterns | Custom abstractions |
| Fewer dependencies | More dependencies |
| Readable | Clever |
| Boring & correct | Exciting & fragile |
Procedure
Step 1: The Elegance Check
For non-trivial work, before presenting the diff, ask in order:
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.
- 10d ago First seen · 110 lines · 16 tokens per session scan A 437891b200fc
demand-elegance is a skill published in the GitHub repository andreaswasita/copilot-agents-dojo (52 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 1,079 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 2026-08-30.
Other skills, from other repositories
sage-review
Deep, platform-neutral code review for PRs and CRs in ONE thorough single pass — design reasoning (Problem Worth Solving & Solution Fit) as one dimension alongside the 9 code-level dimensions, with chain-of-consequences, self-critique, and draft-only comments. The single app-owned source of truth.
code-review
Use to judge a concrete diff, branch, or GitHub PR on its own merits with no rsc-SDD spec/plan chain to key off — the spec-less giving pass behind /code-review: only findings you can defend, one verdict, read-only unless --comment or --fix. NOT the SDD gate keyed to 02-DOCS/wiki/sdd/ that also processes incoming…
design-loop
Use when something must be built well and there is a real reference it should beat: turn what makes the reference good into measured mechanisms, then run a builder and three fresh-context critics until all three pass. Fires on 'design loop', 'make it as good as ', 'it looks generic'. NOT keeping an already-won look…
ss-learn
Capture a human-approved UI design lesson as a privacy-minimized local StyleSeed candidate, review it, and prepare an opt-in share package without transmitting project code, prompts, screenshots, or brand data. Use when a person asks StyleSeed to remember, learn from, generalize, review, or prepare a reusable rule…
ss-lint
Quick automated lint — detects common design system violations in seconds.
nw-fp-usable-design
Naming conventions, API ergonomics, and usability patterns for functional code.