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 uchicago-dsi/ai-sci-skills --skill rut-breakergit clone --depth 1 https://github.com/uchicago-dsi/ai-sci-skillsWrote 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/uchicago-dsi/ai-sci-skills/rut-breaker)<a href="https://agentmods.dev/skills/uchicago-dsi/ai-sci-skills/rut-breaker"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/rut-breaker/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/uchicago-dsi/ai-sci-skills/rut-breaker"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/rut-breaker.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 | $0.00050 | $0.00519 |
| Opus 5 | $0.00025 | $0.00260 |
| Sonnet 5 | $0.00010 | $0.00104 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
rut-breaker 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 11d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rut Breaker
Treat A Rut As A Pattern
- A rut is not just slow progress.
- A rut exists when similar actions keep recurring without sharper understanding, better evidence, or a changed plan.
- Compose this skill with domain skills after enough evidence suggests the current loop is low-yield.
Use This Output Contract
When using this skill, report:
- Repeating loop.
- Evidence the loop is low-yield.
- Stuck assumption.
- Reset move.
- Cheapest test after the reset.
Detect Common Ruts
- Repeated relaunches with no new diagnosis.
- Repeated parameter sweeps that do not narrow uncertainty.
- Repeated code tweaks aimed at the same symptom with no mechanism.
- Repeated notebook updates that add detail but not a sharper conclusion.
- Repeated status checks on a job that is neither clearly healthy nor clearly failed.
Apply These Rules
- Name the loop concretely.
- State what has actually been learned from the last few cycles.
- Identify the assumption keeping the loop alive.
- Choose a reset move that changes the information structure, not just the parameter values.
- Prefer reset moves that simplify, isolate, or compare against a stronger reference.
Good Reset Moves
- reduce to one slice, one case, one batch, or one toy setup
- compare against the nearest known-good artifact or baseline
- inspect the raw artifact instead of the summary metric
- freeze all but one variable
- replace a broad sweep with one discriminative check
- change from post hoc interpretation to direct instrumentation or dumping
- stop a branch and return to the strongest open decision
Avoid Fake Resets
- Do not call it a reset if it is the same move with a wider range.
- Do not add more logging unless the new log can falsify something.
- Do not launch more jobs just to feel active.
- Do not keep a branch alive solely because a lot of work has already gone into it.
End With A Concrete Pivot
- State the reset move.
- State what you are stopping.
- State the first cheap test that will tell you whether the reset helped.
What ships with it
2 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.
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.
- 11d ago First seen · 66 lines · 50 tokens per session scan A 925b96bff740
rut-breaker is a skill published in the GitHub repository uchicago-dsi/ai-sci-skills (17 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 519 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…