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-section-playbookgit 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-section-playbook)<a href="https://agentmods.dev/skills/sidiangongyuan/codex-skills-library/paper-section-playbook"><img src="https://agentmods.dev/badge/skills/sidiangongyuan/codex-skills-library/paper-section-playbook/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-section-playbook"><img src="https://agentmods.dev/badge/skills/sidiangongyuan/codex-skills-library/paper-section-playbook.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 | $0.00064 | $0.01181 |
| Opus 5 | $0.00032 | $0.00590 |
| Sonnet 5 | $0.00013 | $0.00236 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
paper-section-playbook 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Section Playbook
Scope and complement
This skill answers "how should this section be structured and what should each paragraph do?" for papers in CV, 3D perception, and autonomous driving venues (CVPR / ICCV / ECCV / NeurIPS / CoRL).
For sentence-level prose polish (word choice, punctuation, terminology consistency, em-dash rules, etc.), defer to paper-refinement-skills instead. Both skills may be active at once; this one operates at the section and paragraph level, the other at the sentence level.
When to load this skill
- The user is planning or restructuring a paper section, not just polishing prose.
- The user asks "how do I write the Intro / Method / Experiments / etc."
- The user is rebutting a reviewer comment about section structure, motivation, or framing.
- The user wants exemplar-based guidance ("how do top papers do X").
Entry mode and settled decisions
- For a new section or a requested restructuring, use the structural routing below.
- For an approved draft's result refresh, caption correction, or local clarity fix, reuse its established story and section roles. Inspect only the relevant evidence and connected passages; do not repeat elicitation or a full exemplar search.
- A new claim or changed evidence boundary warrants a focused structural review, not automatic redesign of every section. Ask only when the unresolved choice materially changes the paper's contribution or the user's requested scope.
- A missing experiment is a limitation or a draft placeholder, not authorization to train a model. Continue supported writing without inventing missing evidence.
Routing
- Identify which section the user is working on.
- Read the matching file under
sections/for the structural playbook (paragraph functions, decision tree, common reviewer red flags). - If the user is choosing between writing styles, consult
decision-trees/paper-type-router.mdto identify their paper type (new method / new task / new analysis / system / dataset), then apply the corresponding branch in the section file. - For Related Work, method motivation, experiment framing, or exemplar-based guidance, use
$research-evidencewhen citation support or top-venue precedent is uncertain. Prefer CVPR, ICCV, ECCV, ICLR, NeurIPS/NIPS, and ICML before secondary autonomous-driving or robotics venues unless the topic requires them. - Use the worked skeletons and templates in the relevant section file when the user wants concrete patterns.
- After drafting, run the section file's self-review checklist and
checklists/reviewer-redflags.mdfor the relevant section.
What ships with it
11 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.
- agents/openai.yaml 275 B
- checklists/reviewer-redflags.md 26 KB
- decision-trees/paper-type-router.md 2.2 KB
- LICENSE 1.0 KB
- references/design-rationale.md 3.6 KB
- sections/abstract.md 13 KB
- sections/conclusion.md 11 KB
- sections/experiments.md 29 KB
- sections/introduction.md 19 KB
- sections/method.md 16 KB
- sections/related-work.md 9.7 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.
- 4d ago Changed · +17 lines 847e42294659
- 11d ago First seen · 74 lines · 64 tokens per session scan A b41e52edfdb0
paper-section-playbook is a skill published in the GitHub repository sidiangongyuan/codex-skills-library (8 stars, last pushed 5d ago), licensed MIT. It adds 64 tokens to every session and 1,181 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 2026-08-31.
Other skills, from other repositories
latchbio-integration
Build, register, debug, and operate bioinformatics workflows on Latch using the Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake, programmatic execution, and Latch MCP. Use when authoring or deploying Latch workflows, configuring resources or interfaces, moving data, integrating Registry, or launching and…
pubmed-database
Direct PubMed and NCBI E-utilities search workflows for biomedical literature, MeSH queries, PMID lookup, citation retrieval, and API-backed literature monitoring. Use when a task needs biomedical literature from PubMed rather than general web search.
zeroplot
Create editable charts, diagrams, figures, posters, or slides from intent, data, or references.
pathway-enrichment
Run pathway and gene-set enrichment analysis on gene lists or ranked gene data, then interpret the results. Use whenever the user has a set of genes (differentially expressed genes from PyDESeq2/Scanpy, CRISPR-screen hits, cluster marker genes, proteomics hits) and wants to know which biological pathways, GO terms, or…
polars-bio
High-performance genomic interval operations and bioinformatics file I/O on Polars DataFrames. Overlap, nearest, merge, coverage, complement, subtract for BED/VCF/BAM/GFF intervals. Streaming, cloud-native, faster bioframe alternative.
scientific-visualization
Create and audit truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly. Use for figure design, multi-panel layouts, uncertainty and missing-data displays, color/contrast review, image metadata validation, and journal export planning.