Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/raja21068/AutoResearchnpx agentmods add skills/raja21068/autoresearch/research-refineWrote 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/raja21068/autoresearch/research-refine)<a href="https://agentmods.dev/skills/raja21068/autoresearch/research-refine"><img src="https://agentmods.dev/badge/skills/raja21068/autoresearch/research-refine/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/raja21068/autoresearch/research-refine"><img src="https://agentmods.dev/badge/skills/raja21068/autoresearch/research-refine.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 | $0.00101 | $0.07474 |
| Opus 5 | $0.00051 | $0.03737 |
| Sonnet 5 | $0.00020 | $0.01495 |
| Haiku 4.5 | $0.00010 | $0.00747 |
Grade A, and why
research-refine 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.
This is a copy
95% identical to research-refine — 58 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 743 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Refine: Problem-Anchored, Elegant, Frontier-Aware Plan Refinement
Refine and concretize: $ARGUMENTS
Overview
Use this skill when the research problem is already visible but the technical route is still fuzzy. The goal is not to produce a bloated proposal or a benchmark shopping list. The goal is to turn a vague direction into a problem -> focused method -> minimal validation document that is concrete enough to implement, elegant enough to feel paper-worthy, and current enough to resonate in the foundation-model era.
Four principles dominate this skill:
- Do not lose the original problem. Freeze an immutable Problem Anchor and reuse it in every round.
- The smallest adequate mechanism wins. Prefer the minimal intervention that directly fixes the bottleneck.
- One paper, one dominant contribution. Prefer one sharp thesis plus at most one supporting contribution.
- Modern leverage is a prior, not a decoration. When LLM / VLM / Diffusion / RL / distillation / inference-time scaling naturally fit the bottleneck, use them concretely. Do not bolt them on as buzzwords.
User input (PROBLEM + vague APPROACH)
-> Phase 0 (Claude): Freeze Problem Anchor
-> Phase 1 (Claude): Scan grounding papers -> identify technical gap -> choose the sharpest route -> write focused proposal
-> Phase 2 (Codex/GPT-5.4): Review for fidelity, specificity, contribution quality, and frontier leverage
-> Phase 3 (Claude): Anchor check + simplicity check -> revise method -> rewrite full proposal
-> Phase 4 (Codex, same thread): Re-evaluate revised proposal
-> Repeat Phase 3-4 until OVERALL SCORE >= 9 or MAX_ROUNDS reached
-> Phase 5: Save full history to refine-logs/
-> Optional handoff: /experiment-plan for a detailed execution-ready experiment roadmap
Constants
- REVIEWER_MODEL =
gpt-5.4— Reviewer model used via Codex MCP. - MAX_ROUNDS = 5 — Maximum review-revise rounds.
- SCORE_THRESHOLD = 9 — Minimum overall score to stop.
- OUTPUT_DIR =
refine-logs/— Directory for round files and final report. - MAX_LOCAL_PAPERS = 15 — Maximum local papers/notes to scan for grounding.
- MAX_CORE_EXPERIMENTS = 3 — Default cap for core validation blocks inside this skill.
- MAX_PRIMARY_CLAIMS = 2 — Soft cap for paper-level claims. Prefer one dominant claim plus one supporting claim.
- MAX_NEW_TRAINABLE_COMPONENTS = 2 — Soft cap for genuinely new trainable pieces. Exceed only if the paper breaks otherwise.
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 · 743 lines · 101 tokens per session scan A 7f2a14b7c2aa
research-refine is a skill published in the GitHub repository raja21068/AutoResearch (2 stars, last pushed 3mo ago), licensed MIT. It adds 101 tokens to every session and 7,474 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to research-refine, differing in 58 lines, and is treated as a copy.
Other skills, from other repositories
content-refinement-agent
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules, deterministic 0-100 decision bands (Accept/Minor/Major/Reject) that drive a target-met early stop, and a Devil's Advocate…
section-writing-agent
Step 4 of the PaperOrchestra pipeline (arXiv:2604.05018). ONE single multimodal LLM call that drafts the remaining paper sections (Abstract, Methodology, Experiments, Conclusion), extracts numeric values from experimentallog.md into LaTeX booktabs tables, splices the generated figures from Step 2, and merges…
outline-agent
Step 1 of the PaperOrchestra pipeline (arXiv:2604.05018). Convert (idea.md, experimentallog.md, template.tex, conferenceguidelines.md) into a strict JSON outline containing a plotting plan, literature search plan (Intro + Related Work), and section-level writing plan with citation hints. TRIGGER when the orchestrator…
paper-autoraters
Run the four paper-quality autoraters from PaperOrchestra (arXiv:2604.05018, App. F.3) — Citation F1 (P0/P1 partition + Precision/Recall/F1), Literature Review Quality (6-axis 0-100 with anti-inflation rules), SxS Overall Paper Quality (side-by-side), and SxS Literature Review Quality (side-by-side). TRIGGER when the…
plotting-agent
Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimentallog.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER…
paper-writing-bench
Reverse-engineer raw materials (Sparse idea, Dense idea, experimental log) from an existing AI research paper to build a benchmark case for evaluating paper-writing pipelines. Replicates the PaperWritingBench dataset construction procedure from arXiv:2604.05018 §3 / App. C. TRIGGER when the user asks to "build a…