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 yogsoth-ai/stress-test --skill elegance-trap-probegit clone --depth 1 https://github.com/yogsoth-ai/stress-testWrote 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/yogsoth-ai/stress-test/elegance-trap-probe)<a href="https://agentmods.dev/skills/yogsoth-ai/stress-test/elegance-trap-probe"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/elegance-trap-probe/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/yogsoth-ai/stress-test/elegance-trap-probe"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/elegance-trap-probe.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 | $0.00103 | $0.01423 |
| Opus 5 | $0.00051 | $0.00711 |
| Sonnet 5 | $0.00021 | $0.00285 |
| Haiku 4.5 | $0.00010 | $0.00142 |
Grade A, and why
elegance-trap-probe 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 9d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Elegance Trap Probe
The counter-intuitive attacker. Every other strategy attacks weaknesses; this one attacks a STRENGTH — the artifact's beauty. A common guiding aesthetic is Occam: a good result should be simple and elegant (LLM scaling laws replacing linguistics-inspired CNN/RNN; one principle of natural selection explaining all species). When we produce a beautiful unified result — one generator, a small number of projections, the key object as a symmetry — that is exactly what we hoped for. Which is precisely why it's dangerous. The same aesthetic that signals truth also seduces: a pretty story is easy to believe because it's pretty, not because it's right. This strategy interrogates whether the elegance was EARNED or is DECORATIVE, turning the aesthetic from a feeling into a falsifiable bar.
The distinction that does all the work
Earned simplicity buys its compression by FORBIDDING and PREDICTING more. Natural selection is elegant because it forbids vast swaths of observation (no species improves for its own sake; no inheritance of un-selected acquired traits at the population level) and predicts specifics (fossils in strata order, antibiotic resistance dynamics). Scaling laws are elegant because they PREDICT loss at unseen scale — risky, falsifiable, and they held. Earned simplicity is a compression of MANY constraints into ONE generator that then GENERATES those constraints back, plus new ones.
Decorative simplicity achieves its prettiness by RE-DESCRIBING what we already knew in a unifying vocabulary, forbidding nothing new. It "explains" every existing observation because it was fitted to them; it makes no risky prediction; remove it and we lose a nice story but no predictive content. Freud's framework "explained" every behavior — and forbade none. A unification that says "everything is a projection of one generator" is decorative IF, for any conceivable observation, it can always find SOME projection to call it — i.e. if it cannot say what it would look like for the unification to be FALSE.
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.
- 9d ago First seen · 49 lines · 103 tokens per session scan A ab37d17e91aa
elegance-trap-probe is a skill published in the GitHub repository yogsoth-ai/stress-test (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 103 tokens to every session and 1,423 once invoked, about $0.0005 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
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
bt6-provider-review
Audit an external AI/API provider and its integration into a BT6 repository for service reality, independent verification, trust boundaries, secret handling, API/model correctness, completeness, claim traceability, and merge readiness.
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
vertical-real-estate
Residential-proptech domain knowledge so architect / pm aren't naive when speccing real-estate products (listings, lead-crm, transaction-coordination, property-mgmt). Codifies MLS/IDX reality, listing status lifecycle + syndication canonical-source, long-cycle lead nurture, transaction-coordination as the high-pain…