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 isomorphism-falsificationgit 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/isomorphism-falsification)<a href="https://agentmods.dev/skills/yogsoth-ai/stress-test/isomorphism-falsification"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/isomorphism-falsification/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/isomorphism-falsification"><img src="https://agentmods.dev/badge/skills/yogsoth-ai/stress-test/isomorphism-falsification.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 | $0.00094 | $0.01222 |
| Opus 5 | $0.00047 | $0.00611 |
| Sonnet 5 | $0.00019 | $0.00244 |
| Haiku 4.5 | $0.00009 | $0.00122 |
Grade A, and why
isomorphism-falsification scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
For each language in which the artifact claims the same object lives, write down EXACTLY what that object is: its ambient space, what "zero/null/kernel/curl" means there, and what structure (group action, vector space, o How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Isomorphism Falsification
A dedicated attacker for the single most suspicious kind of claim an artifact can make: "X = Y = Z = W" asserted across multiple mathematical languages. "Isomorphism" is a precise mathematical word with a heavy burden of proof. "These things rhyme" is an analogy with almost none. The danger is that a pleasing analogy gets promoted to "isomorphism" because it FEELS unifying — pure elegance-trap. This strategy forces the claim to pay its burden or be demoted.
Why this needs its own strategy
Generic debate/red-team will poke at it, but they don't know the specific bar an isomorphism must clear. This strategy encodes that bar. The burden of proof for "A ≅ B" is NOT "A and B share some features." It is: a map Φ: A → B that is (1) well-defined on all of A, (2) preserves the relevant structure (the operations/relations that matter — the composition of symmetries, the action of the generator, or whatever structure the artifact asserts is shared), (3) is invertible (or at least: the claimed correspondence is bijective on the objects we care about — the kernel/null/zero sets). Anything less is a homomorphism, a functor, an embedding, a loose analogy — each strictly weaker, and we must say which.
The ladder of strength (assign the claim its true rung)
From strongest to weakest. The attack's job is to find the highest rung the claim can actually defend, then demote our wording to match:
- Isomorphism — bijective, structure-preserving both ways. The full claim.
- Isomorphism on a substructure — true only for the kernel/zero-mode sets, not the whole spaces. (Plausibly where many multi-language claims actually land — and that would still be a real, strong result if stated honestly.)
- Homomorphism / functor — structure-preserving one way, not invertible. Maps objects to objects but loses information.
- Shared invariant — all claimed sides have a quantity that coincides (e.g. all "zero sets" have the same dimension) but no map is exhibited. Numerical coincidence, not identity.
- Analogy — suggestive parallel, no formal correspondence. The honest label if 1–4 all fail.
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.
- 7d ago First seen · 52 lines · 94 tokens per session scan A b028cfa666c3
isomorphism-falsification is a skill published in the GitHub repository yogsoth-ai/stress-test (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 94 tokens to every session and 1,222 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
relax-dev-debug
Develop and debug the Relax reinforcement learning project. Use this skill whenever modifying code in the relax/ directory, or running remote training jobs on a Ray cluster for validation. Also use it when the user mentions training, debugging training runs, submitting Ray jobs, or fixing training errors.
research-ideation
Quant-focused research ideation pipeline: scope selection (3 stages) → anchor-first literature grounding → single-core idea generation → iterative refinement → ELO tournament ranking (Final = N+R+C−D) → update evo-memory → user selects direction → expand into manuscript-quality proposal. Optimized for incremental…
quant-experiment-runtime
Quant research experiment executor: discover an offline source database under the workdir's code-repo, build a panel, run a Research Artifact's entry point to compute research-object values, and evaluate IC/ICIR/RANKIC/coverage metrics. Runtime = Experiment Executor; it runs a Research Artifact via a Python-native…
local-paper-navigator
Find and read papers from the local papers library (repo papers/, mounted at /papers/). Three native tools form a reading funnel: papersearch (one line per paper), paperread (card + section outline), papersection (one verbatim section — the only full-text access). Use when: find papers in the local library, read a…
experiment-pipeline
Guides structured 4-stage experiment execution with attempt budgets and gate conditions: Stage 1 initial implementation (reproduce baseline), Stage 2 hyperparameter tuning, Stage 3 proposed method validation, Stage 4 ablation study. Integrates with evo-memory (load prior strategies, trigger IVE/ESE) and…
paper-review
Guides self-review of YOUR OWN academic paper before submission with adversarial stress-testing. Core method: 5-aspect checklist (contribution sufficiency, writing clarity, results quality, testing completeness, method design), counterintuitive protocol (reject-first simulation, delete unsupported claims, score trust…