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 gaasher/Agent-Loop-Skills --skill scientific-writergit clone --depth 1 https://github.com/gaasher/Agent-Loop-SkillsWrote 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/gaasher/agent-loop-skills/scientific-writer)<a href="https://agentmods.dev/skills/gaasher/agent-loop-skills/scientific-writer"><img src="https://agentmods.dev/badge/skills/gaasher/agent-loop-skills/scientific-writer.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium Agent Snooping · line 83 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00139 | $0.03455 |
| Opus 5 | $0.00069 | $0.01728 |
| Sonnet 5 | $0.00028 | $0.00691 |
| Haiku 4.5 | $0.00014 | $0.00346 |
Grade A, and why
scientific-writer 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 8d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scientific Writer Loop
The artifact is a piece of scientific writing (draft + its dataset + figures + optional code).
Each iteration critiques → grades → revises: five specialist judges produce concrete findings,
an independent peer_reviewer turns the paper into a graded 0-100 score on the same axes, and a
scientific_writer fixes the prose, figures, and code — running the user's <plot_command> to
regenerate figures. The loop runs until the score clears <pass_threshold> or the budget is hit. All
work happens on copies inside a sandbox; the user's originals are never touched.
The cast (all in this folder):
roles/figures_judge.md,roles/scientific_judge.md,roles/style_judge.md,roles/formatting_judge.md,roles/code_reviewer.md— the five critics; each emits the sharedschemas/finding.schema.json.roles/peer_reviewer.md— the summative grader (its own honesty rules); emitsschemas/peer_review.schema.jsonand decidespass.roles/scientific_writer.md— the reviser; fixes code → regenerates figures → updates prose.schemas/finding.schema.json,schemas/peer_review.schema.json— the two validated outputs.
Spawn-or-degrade. On Claude Code, spawn the active judges as real Agent subagents in
parallel, then one fresh peer_reviewer, then the scientific_writer; otherwise adopt each role
inline. You are the orchestrator.
Why the grader is built this way (the honesty problem)
The peer_reviewer grades on the same axes the judges critique — which invites echoing, inflation
under loop-termination pressure, and a writer that games the rubric. roles/peer_reviewer.md
counters this: it (1) grades independently, re-deriving each axis from the paper + dataset before
reading the critiques, (2) verifies a sample of numbers/citations itself rather than trusting
"it's fixed", (3) must surface issues the judges missed, (4) holds a fixed, anchored,
reproducible bar with no credit for effort or elapsed iterations, (5) applies hard gates (a
confirmed block fails the paper regardless of the average), and (6) runs a substance check against
surface compliance. The writer optimizes the judges' concrete findings; the grader judges
holistically — so "address every finding" does not mechanically buy a pass.
What ships with it
10 files 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.
- examples/run.example.yaml 2.4 KB
- roles/code_reviewer.md 3.2 KB
- roles/figures_judge.md 3.5 KB
- roles/formatting_judge.md 3.2 KB
- roles/peer_reviewer.md 6.2 KB
- roles/scientific_judge.md 4.4 KB
- roles/scientific_writer.md 4.5 KB
- roles/style_judge.md 2.7 KB
- schemas/finding.schema.json 2.5 KB
- schemas/peer_review.schema.json 4.2 KB
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.
- 8d ago First seen · 182 lines · 139 tokens per session scan A 7a6697458c3b
scientific-writer is a skill published in the GitHub repository gaasher/Agent-Loop-Skills (164 stars, last pushed 2mo ago), licensed MIT. It adds 139 tokens to every session and 3,455 once invoked, about $0.0007 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
sn-search-academic
An academic research tool for finding papers and encyclopedia entries, reading papers in full or by section, and tracing references and citations. It supports structured literature research.
arbor-agent-orchestrator
Top-level controller for recreating the open-source AutoResearch workflow as a suite of skills. Use when the user asks to run, emulate, extract, validate, or refine Arbor/AutoResearch behavior, especially when a coordinator must load phase skills for setup, ideation, executors, merge evaluation, novelty search…
automated-soap-note-generator
Generate structured SOAP notes from clinical narratives, transcripts, or existing notes; use when the user needs de-identified clinical documentation organized into Subjective, Objective, Assessment, and Plan sections, with clear assumptions and review points.
estimate-immune-score-analysis
Use this skill to compute ESTIMATE immune-related microenvironment scores from a bulk expression matrix, generate an ESTIMATE score heatmap, and optionally generate group-wise ESTIMATE score boxplots plus significance tables when a sample group file is supplied. Trigger keywords: ESTIMATE, immune score, stromal score…
external-model-validation
Use when validating an existing prognostic risk signature on an external bulk expression cohort with survival outcomes, producing risk scores, Kaplan-Meier curves, risk distribution plots, heatmap, and time-dependent ROC curves. NOT for: model training, feature selection, nomogram construction, calibration analysis…
gsva-analysis-and-visualization
Use this skill to run GSVA or ssGSEA pathway-level differential analysis from a bulk expression matrix and a sample group file, then generate a heatmap from the saved GSVA result object. Trigger keywords: GSVA, ssGSEA, pathway enrichment, KEGG pathway analysis, MSigDB. NOT for: gene-level differential expression…