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 yqi96/warranted --skill paper-reproducegit clone --depth 1 https://github.com/yqi96/warrantedWrote 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/yqi96/warranted/paper-reproduce)<a href="https://agentmods.dev/skills/yqi96/warranted/paper-reproduce"><img src="https://agentmods.dev/badge/skills/yqi96/warranted/paper-reproduce/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/yqi96/warranted/paper-reproduce"><img src="https://agentmods.dev/badge/skills/yqi96/warranted/paper-reproduce.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 | $0.00076 | $0.02622 |
| Opus 5.5 | $0.00030 | $0.01049 |
| Sonnet 5.5 | $0.00015 | $0.00524 |
| Haiku 4.5 | $0.00008 | $0.00262 |
Grade A, and why
paper-reproduce 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 1mo 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Reproduction
Treat reproduction as rebuilding the paper's evidential chain with independently produced evidence.
The reference paper tells you what must be reproduced. It is not evidence that its experimental results or conclusions are true. Reproduction succeeds only when a verified implementation and a fresh execution can positively establish the required core claims, either directly or through intermediate result propositions.
1. Extract the Paper's Argument
Read the paper, figures, tables, methods, and supplements before executing anything. Extract only the argument needed for the reproduction target.
Build the graph at the depth required by the paper's argument. This two-level shape is common, not mandatory:
fresh artifacts A ── evidence ──► experimental-result proposition A ─┐
├─ evidence ─► core claim
fresh artifacts B ── evidence ──► experimental-result proposition B ─┘
A single proposition is enough when fresh artifacts directly support the core claim and no intermediate assertion needs a separate judgment:
verified code + fresh execution logs + raw outputs
│ evidence
▼
core claim
Use additional layers when experimental results support sub-claims that in turn support broader conclusions:
fresh artifacts A → result proposition A → sub-claim 1 ┐
fresh artifacts B → result proposition B → sub-claim 2 ├→ core claim
fresh artifacts C → result proposition C → sub-claim 3 ┘
Here the core claim references sub-claims 1–3 in its evidence slot. Each sub-claim references the result propositions it depends on, and each result proposition carries the fresh artifacts that establish it. Every proposition states its own warrant for the inference from its immediate evidence; the core claim's warrant explains why the combination of sub-claims is sufficient for the broader conclusion. Branches may also share a result proposition by reference when the same result genuinely bears on more than one sub-claim.
What ships with it
1 file 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.
- 1mo ago Changed · +105 lines · +29 tokens per session 1d843a694898
- 1mo ago First seen · 86 lines · 47 tokens per session scan A df9a0b676eac
paper-reproduce is a skill published in the GitHub repository yqi96/warranted (2 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 2,622 once invoked, about $0.0003 per session on Opus 5.5. 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
proof-checker
A mathematical proof review and repair workflow for LaTeX documents. It checks whether a proof has valid reasoning, addresses identified gaps, reviews the fixes, and produces an audit report.
auto-paper-improvement-loop
An automated editing cycle for a compiled research paper: an external language model reviews it, fixes are applied, and the paper is compiled again.
paper-write
A workflow for writing a research paper section by section in LaTeX, a text format used to prepare structured technical documents. It starts from a paper outline and supports several academic venues and citation sources.
research-lit
Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.
paper-illustration
A workflow for generating academic illustrations, such as architecture diagrams and method visuals, with image generation and repeated review. Claude plans and checks the figure during the process.
citation-crosscheck
Double-blind bibliographic cross-check: one agent extracts each cited entry verbatim from the local .bib, a second independently re-fetches the same paper's record from the web while blind to the .bib, and a third extractor emits a mechanical field-by-field delta to catch dropped/re-ordered authors, wrong years, wrong…