Borrowing it
Nothing to install: this file belongs to eunomia-bpf/ActPlane. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/eunomia-bpf/ActPlane/master/.claude/skills/paper-logic/SKILL.mdgit clone --depth 1 https://github.com/eunomia-bpf/ActPlaneWrote 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/eunomia-bpf/actplane/paper-logic)<a href="https://agentmods.dev/skills/eunomia-bpf/actplane/paper-logic"><img src="https://agentmods.dev/badge/skills/eunomia-bpf/actplane/paper-logic/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/eunomia-bpf/actplane/paper-logic"><img src="https://agentmods.dev/badge/skills/eunomia-bpf/actplane/paper-logic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 71 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00039 | $0.05557 |
| Opus 5 | $0.00019 | $0.02779 |
| Sonnet 5 | $0.00008 | $0.01111 |
| Haiku 4.5 | $0.00004 | $0.00556 |
Grade A, and why
paper-logic 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 9d 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 — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Academic Writing: Logic & Consistency Review
Review the paper at $ARGUMENTS (a directory of sections or specific files)
for argument-level logic and cross-section consistency. If no argument is
given, locate the paper sources (e.g., sections/*.tex plus the main file
containing the abstract) and confirm the file set with the user.
This skill checks the whole-paper layer: does the argument hold together,
do the numbers reconcile, is the terminology stable. For sentence-level prose
(nominalizations, weak openings, word choice), run /paper-review per
section; for applying fixes, run /paper-fix. Do not duplicate their
sentence-level findings. The one exception is section M's mechanical greps
(punctuation, agreement), which enforce house style at whole-paper scope
because they catch drift that per-section review misses.
All examples below are from a fictional paper about a fictional adaptive caching system. They illustrate the shape of each antipattern; never copy them into your report. Every finding must quote the actual paper under review.
Output contract (non-negotiable)
Your report is incomplete unless ALL of the following hold. Re-walk the checklists until they do.
- Every checklist ID (A1–A7, B1–B5, C1–C7, M, P) appears in the report,
either with findings or with the line
[Xn] checked — no findings, plus one sentence saying what you looked at. Silent skips are not allowed. - Every finding has all four parts:
file:line, a verbatim quote from the paper under review, a problem statement that names the reasoning error (not "this is unclear"), and a concrete fix — for prose problems, a full rewritten sentence, not "consider rephrasing". - The three working tables are filled in and printed (term, number, promise), built from the paper under review. Do not write any finding before the tables are complete: most logic findings fall out of the tables, and skipping them is how reviews end up shallow.
- The mechanical greps in section M were actually run and each hit triaged (finding / false positive, one line each).
- Calibration: a mature 5-section systems paper typically yields 15–30 findings across severities. If you have fewer than 10, you have under-checked — re-walk A and B with the tables in front of you. If you have zero Must-fix findings, explicitly state which Must-fix categories you verified and how.
- Findings are sorted Must fix → Should fix → Consider, and the report ends with the three tables, the top-5 list, and the verdict paragraph.
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.
- 9d ago First seen · 485 lines · 39 tokens per session scan A 8379a447141b
paper-logic is a skill published in the GitHub repository eunomia-bpf/ActPlane (98 stars, last pushed 4d ago), licensed MIT. It adds 39 tokens to every session and 5,557 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 2026-08-30.
Other skills, from other repositories
sciverse-paper-search
Use this skill for scientific literature search, evidence retrieval, paper metadata screening, and cited research synthesis with Sciverse. This LazyLLM-adapted version supports SciverseSearch search, metasearch, metacatalog, and getcontent only; it does not assume full Sciverse MCP resource or attachment APIs are…
paper-search
Primary skill for searching, retrieving, and reading academic papers from arXiv.
paper-to-code
Implement an academic paper (arXiv or any quantitative source) as verifiable code without inventing unstated details. Use when asked to implement, reproduce, or prototype a method from a paper. Produces an ambiguity audit before code, citation-anchored decisions, and machine-checkable sanity verification.
arxiv-paper-search
A paper-search skill that uses arXiv's official public API, a free service for finding research papers, to retrieve academic publications without a token.
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…