physics-erdos-loop

A persistent workflow for physics research that tests possible results with proofs, calculations, simulations, or formal mathematics. The Erdős-style approach means continuing through failed attempts instead of treating an unsuccessful route as the final result.

In plain words
What is it for?
Use it for physics derivations, equations, differential equations, symbolic or numerical checks, simulations, Lean formalization, and consistency reviews across a research framework.
Why use it?
It separates useful evidence about a failed approach from a finished scientific conclusion and helps prevent unsupported or trivial claims from being accepted.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/vantasnerdan/substrate-framework/physics-erdos-loop
Any agent
npx skills add vantasnerdan/substrate-framework --skill physics-erdos-loop
Clone the repo
git clone --depth 1 https://github.com/vantasnerdan/substrate-framework

Made for: Claude Code, Codex.

Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,519 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00109 $0.05519
Opus 5 $0.00055 $0.02759
Sonnet 5 $0.00022 $0.01104
Haiku 4.5 $0.00011 $0.00552

Measured yesterday against content hash d7ad2e626cf8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

physics-erdos-loop 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 yesterday.

The scan reads SKILL.md. This mod also ships 4 executable files (assets/verify_claim.py, assets/verify_pde.py, scripts/preflight.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.

.agents/skills/physics-erdos-loop/SKILL.md · 329 lines

How it starts

The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Physics Erdős Loop

Use this loop to produce a positive, framework-consistent, verified result—not merely an articulate account of why one attempt failed. It adapts the Erdős-style persistent proof loop to physics while adding claim governance and software reuse.

Non-negotiable outcome

Honesty is required but is not itself success. Classify a failed candidate, no-go, obstruction, residual, bound, or inconclusive computation as attempt evidence and continue. Do not close the effort on it. Equally, do not turn honest review into a ratchet toward trivial claims: preserve the strongest meaningful positive result, make the minimum truthful scope repair, and leave the larger objective open when it is not yet met. Weakening is subject to the same persistence discipline as failure-chasing. Each attempt must change something material — candidate concept, numerical method, oracle class, formalism, or target statement — rather than re-examine a known route under tighter standards; repeating a route with only stricter evidence thresholds is drift, not diligence. A new acceptance criterion invented mid-campaign must name the observed failure it prevents, be recorded once, and bind future attempts rather than retroactively invalidating finished ones. Close each attempt with two typed fields: route_verdict is established, refuted with mechanism, or blocked with that route's missing construction; evidence_scope states the strongest earned scientific meaning, such as NUMERICALLY_UNRESOLVED or REPRESENTATION_SCOPED. Neither field propagates automatically to the obligation or campaign. The next attempt inherits a direction, not a smaller question.

Success requires the requested object plus all of these gates:

  • accepted dependency closure and declared imports;
  • natural compatibility with framework invariants, or a separately accepted minimal foundational revision;
  • strongest practical oracle and claim-appropriate sensitivity evidence;
  • preregistered comparison of plausible candidates when a mechanism is being selected;
  • impact-bounded downstream replay;
  • reusable importable implementation;
  • claim-by-claim review and release promotion;
  • synchronized generated docs and memory;
  • empty debt ledger.

Read the full file on GitHub · 329 lines

Files

What ships with it

8 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. yesterday First seen · 329 lines · 109 tokens per session scan A d7ad2e626cf8

Subscribe to this mod's changes

physics-erdos-loop is a skill published in the GitHub repository vantasnerdan/substrate-framework (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 109 tokens to every session and 5,519 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens