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 darellchua2/opencode-config-template --skill research-paper-generation-skillgit clone --depth 1 https://github.com/darellchua2/opencode-config-templateWrote 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/darellchua2/opencode-config-template/research-paper-generation-skill)<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/research-paper-generation-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/research-paper-generation-skill.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
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 →
- medium MCP Rug Pull · line 88 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 240 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 243 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 756 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00053 | $0.08363 |
| Opus 5 | $0.00026 | $0.04182 |
| Sonnet 5 | $0.00011 | $0.01673 |
| Haiku 4.5 | $0.00005 | $0.00836 |
Grade A, and why
research-paper-generation-skill 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 4d 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 — 788 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Paper Generation Skill
This skill encodes the exact workflow used to produce three iterations of the HollowWall Inspector research paper. It is designed to be reusable across projects — any codebase with experimental results, datasets, and model artifacts can follow this pipeline to produce a submission-ready paper.
1. Workflow Overview
The pipeline is an 8-step sequential process. Do not skip steps or reorder them — each step's output feeds the next.
Step 1 — Source Data Gathering
Extract verified experimental facts from the codebase before writing a single sentence of the paper. Sources to mine:
- Dataset metadata: sample counts, class distribution, capture methods,
file paths (e.g.,
dataset/.../ground_truth.json). - Model results: accuracy, recall, false alarm rates, calibration error
(ECE), confidence intervals — from evaluation scripts output, JSON results,
or
RESULTS-*.mdfiles. - Code references: file paths with line numbers for key algorithms (feature
extraction, training loop, calibration). Example:
training_v2/src/hollowwall_v2/features.py:L42. - Configuration: model hyperparameters, thresholds, feature lists.
NEVER fabricate numbers. If a number cannot be traced to a codebase
artifact, mark it as [TODO: verify] and flag it for the user. Every
quantitative claim in the final paper MUST have a verifiable source.
Recommended tools: codegraph_explore (if indexed), grep, read, and
spawn an explore subagent for broad codebase surveys.
Step 2 — Framing Decision
Pick one of three framings based on the target venue. See §2 Framing Decision Tree below. The framing determines paper structure, tone, what to emphasize, and what to strip.
Step 3 — Literature Search & Validation
Delegate to autoresearch-research-subagent (Tier 2, web-only) with a
detailed prompt specifying:
- The paper's contribution claims (from Step 1 data).
- The framing (from Step 2).
- Specific comparison points needed (e.g., "find papers on pseudo-labeling with confidence thresholding", "find transfer learning benchmarks for audio classification with <1000 samples").
- Required: author list, title, venue, year, DOI or stable URL for every reference.
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.
- 4d ago First seen · 788 lines · 53 tokens per session scan A 2b0587e0e5f0
research-paper-generation-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 8,363 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 2026-09-03.
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…
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…
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.
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…