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 Mexregkan/claude-for-researchers --skill simple-case-gategit clone --depth 1 https://github.com/Mexregkan/claude-for-researchersWrote 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/mexregkan/claude-for-researchers/simple-case-gate)<a href="https://agentmods.dev/skills/mexregkan/claude-for-researchers/simple-case-gate"><img src="https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/simple-case-gate/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/mexregkan/claude-for-researchers/simple-case-gate"><img src="https://agentmods.dev/badge/skills/mexregkan/claude-for-researchers/simple-case-gate.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 | $0.00045 | $0.00501 |
| Opus 5 | $0.00023 | $0.00251 |
| Sonnet 5 | $0.00009 | $0.00100 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
simple-case-gate 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 6d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simple-case gate
Use this whenever proposing or evaluating a mathematical or physical mechanism, proof architecture, ansatz, recursion, or claim intended to hold across a family.
Non-negotiable rule
Identify the simplest admissible nondegenerate case and make the exact proposal work there before increasing order, weight, depth, rank, spin, loop number, or the number of free parameters. A genuine failure in that case forbids trying harder cases in the hope that added complexity will repair a proposal that was claimed to work in every case.
Gate
- State the proposal and its domain precisely. If a simple case is excluded, derive the exclusion from the proposal rather than adding it after seeing a failure.
- Choose the lowest-complexity case inside that domain. Verify that it is nondegenerate and that the test is sensitive to the proposed mechanism.
- Test the complete proposal, with the same definitions, normalization, and conventions intended for the general case. Preserve the first exact residual or counterexample.
- If it fails, stop escalation. Diagnose whether the cause is an implementation error, convention mismatch, degeneracy, false auxiliary assumption, or failure of the idea.
- Either modify the proposal for a principled reason that explains the residual and retest the modified proposal on the same simple case, or abandon/narrow the claim.
- Proceed to harder cases only after the simple gate passes. A modified proposal is a new proposal and must pass the gate again from the beginning.
Forbidden responses to failure
- Moving directly to a higher order, weight, depth, rank, spin, or loop number.
- Adding parameters or correction terms available only in the harder case without first deriving why they must already resolve the simple residual.
- Calling the failed case “too simple” unless it is proved to lie outside the stated domain.
- Replacing the exact failed gate with a looser numerical, projected, or averaged test.
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.
- 6d ago First seen · 43 lines · 45 tokens per session scan A bcd2c8aab3b1
simple-case-gate is a skill published in the GitHub repository Mexregkan/claude-for-researchers (52 stars, last pushed 8d ago), licensed MIT. It adds 45 tokens to every session and 501 once invoked, about $0.0002 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 2026-09-05.
Other skills, from other repositories
pre-submission-report
Run the final, comprehensive submission-readiness gate and consolidate all checks into one dated report; citation-integrity-only mode is also supported. Use when a paper and submission package are nearly final. Not for a mid-draft adversarial review; use $review-cluster.
proof-readability
Improve the exposition and readability of a mathematical proof already verified as correct without changing its mathematics. Use when polishing a lemma, theorem, proof, or appendix after correctness checks. Not for verifying the proof; use $verify-math.
latex
Compile one specified LaTeX document, resolve build errors, audit citations, and report build quality. Use when a .tex source must be built or a concrete compilation failure repaired. Not for corpus-wide build checks, visual polish after a clean build, or creating a project; use $latex-health-check, $latex-polish, or…
beamer-deck
Create an academic presentation as a LaTeX Beamer source and reviewed PDF with an original theme. Use when the requested deliverable is a conference, seminar, or lecture deck in Beamer. Not for PowerPoint or RevealJS; use $pptx or $quarto-deck.
bib-parse
Extract citations from a PDF and generate a validated .bib file. Use when the user asks to extract citations from a PDF and generate a validated .bib file. Reads the PDF, identifies referenced works, constructs BibTeX entries, and verifies metadata.
computational-experiments
Scaffold, execute, analyse, and publish computational research experiments through a reproducible staged workflow. Use when a research question requires simulations or computational sweeps rather than a one-off script.