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 sidiangongyuan/codex-skills-library --skill paper-review-panelgit clone --depth 1 https://github.com/sidiangongyuan/codex-skills-libraryWrote 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/sidiangongyuan/codex-skills-library/paper-review-panel)<a href="https://agentmods.dev/skills/sidiangongyuan/codex-skills-library/paper-review-panel"><img src="https://agentmods.dev/badge/skills/sidiangongyuan/codex-skills-library/paper-review-panel/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/sidiangongyuan/codex-skills-library/paper-review-panel"><img src="https://agentmods.dev/badge/skills/sidiangongyuan/codex-skills-library/paper-review-panel.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 | $0.00071 | $0.01187 |
| Opus 5 | $0.00036 | $0.00593 |
| Sonnet 5 | $0.00014 | $0.00237 |
| Haiku 4.5 | $0.00007 | $0.00119 |
Grade A, and why
paper-review-panel 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 12d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Review Panel
Core Rule
This skill owns pre-submission paper review and readiness assessment. Review by default. Do not edit the paper, mutate LaTeX, change figures, rerun experiments, or patch files unless the user separately asks for implementation. The output is an official-review-style synthesis plus compact revision priorities.
Once official reviews arrive, stop using this skill as the workflow owner. Use
$rebuttal-response-skills for exact concern mapping, evidence integration,
author-response drafting, and response audits.
Workflow
-
Ground the review in artifacts.
- Prefer the compiled PDF first when available; inspect layout, figures, tables, appendix, and references as a reviewer would see them.
- Read the source text, bibliography, figure/table sources, logs, or result artifacts only as needed to verify claims and locate concrete anchors.
- Use
$research-evidencefor citation/reference sanity checks or literature positioning when a review finding depends on external evidence. - For novelty, related-work, score-prediction, reviewer-risk,
submission-readiness, or final-submission reviews, run a recent-literature
audit through
$research-evidencebefore finalizing novelty or acceptance risk. Do not require this extra pass for casual local or prose-only reviews unless novelty or missing citations are part of the ask. - If that audit is incomplete or source coverage is weak, state the coverage limit before assigning novelty confidence or acceptance risk.
- If only a section is provided, label the result as a partial review and do not score the full paper as if all sections were available.
-
Apply the three-reviewer lens in the main review.
- Reviewer 1: contribution, novelty, positioning, motivation, venue fit.
- Reviewer 2: method, technical correctness, experiments, metrics, evidence.
- Reviewer 3: writing, figures, tables, consistency, reproducibility, appendix, reviewer readability.
- Read
references/reviewer-roles.mdfor detailed role prompts.
What ships with it
5 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.
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.
- 12d ago First seen · 109 lines · 71 tokens per session scan A 419fd54bb46d
paper-review-panel is a skill published in the GitHub repository sidiangongyuan/codex-skills-library (8 stars, last pushed 6d ago), licensed MIT. It adds 71 tokens to every session and 1,187 once invoked, about $0.0004 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
skills-manager-cli
Drive the Skills Manager CLI (skm) to initialize the hub, adopt unmanaged skills, list/enable/disable skills per AI tool, and doctor/fix symlink sync. Use whenever the user or an agent needs to manage skills from a terminal, SSH session, CI job, or headless machine; when a skill is missing in Claude Code, Codex…
superloopy-loop
Use Superloopy's lightweight strict-evidence loop for Codex tasks that need durable progress, criteria, and artifact-backed completion.
superloopy-frontend
Use only after explicit Codex $superloopy:superloopy-frontend or Claude Code /superloopy:superloopy-frontend invocation for supported screen-based application UI across browser-hosted Web, interactive deployed content-led Web, desktop, mobile/tablet, embedded/hybrid, Qt, custom-rendered, or mixed targets, such a task…
say-it-straight
Use only after explicit Codex $superloopy:say-it-straight or Claude Code /superloopy:say-it-straight invocation to make supplied or requested prose direct, concise, and natural without changing facts or protected text.
superloopy-research
Use only after explicit Codex $superloopy:superloopy-research or Claude Code /superloopy:superloopy-research invocation, a research task started with a leading loopy or 루피 (such as loopy research), or an active Superloopy loop explicitly routing a research deliverable here. Evidence-backed Superloopy research…
codex-delegate
Delegates implementation-heavy or repetitive coding work (batch edits, boilerplate, multi-file refactors with clear patterns, test scaffolding) from Claude to OpenAI Codex CLI. Use when token cost outweighs judgment cost. Trigger phrases include "delegate to codex", "let codex do this", "batch refactor across files"…