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 sparq-org/sparq --skill academic-papergit clone --depth 1 https://github.com/sparq-org/sparqWrote 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/sparq-org/sparq/academic-paper)<a href="https://agentmods.dev/skills/sparq-org/sparq/academic-paper"><img src="https://agentmods.dev/badge/skills/sparq-org/sparq/academic-paper/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/sparq-org/sparq/academic-paper"><img src="https://agentmods.dev/badge/skills/sparq-org/sparq/academic-paper.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 | $0.00160 | $0.06681 |
| Opus 5 | $0.00080 | $0.03341 |
| Sonnet 5 | $0.00032 | $0.01336 |
| Haiku 4.5 | $0.00016 | $0.00668 |
Grade A, and why
academic-paper 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 — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
academic-paper — the sparq paper-factory
This is the repeatable PROCESS for producing one paper from a sparq contribution. It is
factory machinery, not prose advice: it enforces sparq's empirical-honesty mandate at
the data layer, binds every number to live benchmark data, and emits a PDF + an in-site
HTML page from one Typst source. Design record: research/paper-factory-design.md
(consolidates the contribution inventory + the auto-gen/PDF research). Epic sq-gum8.
Two non-negotiable constraints govern every step. They are the point of the factory; do not soften them.
- No ZK/MPC security property may be claimed as proven. The single-prover ZK verifier has no external audit (bead sq-qhy4, open); the multi-prover path is re-open (sq-9hrn); the malicious-secure MPC layer is a stub. A ZK/MPC paper today is an honest design / limitations / negative-result contribution, arXiv/WIP only, and must cite sq-qhy4. Never write "secure" / "verifiable" / "private" as a proven property — only as a design goal.
- Work-box (EC2
-aws) wall-clock numbers are NON-CANONICAL. Only deterministic integer metrics are canonical today (W3C/OGC conformance floors, byte-identity, recall floors, gate/round/byte counts, differential-fuzz pass). A speed/memory claim needs the canonical runner (research/ci-ec2-design.md). Indicative numbers are never co-tabulated with canonical ones and never feed an aggregate figure-of-merit.
The factory has six stages. Stages 0/1/3/5 are the methodology this skill encodes; 2/4/6 are
scripted (see research/paper-factory-design.md §1–§2 for the script/route layout).
Stage 0 — Intake: identify a genuinely-novel contribution (re-runnable)
Run before claiming anything is publishable. This is the re-runnable identification process;
its current ranked output is research/paper-contributions-inventory.md — read it first and
diff against it rather than starting from scratch.
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 · 381 lines · 160 tokens per session scan A 8d794b7223a5
academic-paper is a skill published in the GitHub repository sparq-org/sparq (12 stars, last pushed today), licensed MIT. It adds 160 tokens to every session and 6,681 once invoked, about $0.0008 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
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…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
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…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…