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 agentmods add skills/camusgit/evoquant/paper-planningnpx skills add CamusGIT/EvoQuant --skill paper-planninggit clone --depth 1 https://github.com/CamusGIT/EvoQuantWrote 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/camusgit/evoquant/paper-planning)<a href="https://agentmods.dev/skills/camusgit/evoquant/paper-planning"><img src="https://agentmods.dev/badge/skills/camusgit/evoquant/paper-planning.svg" alt="Measured on agentmods" 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 | $0.00166 | $0.02054 |
| Opus 5 | $0.00083 | $0.01027 |
| Sonnet 5 | $0.00033 | $0.00411 |
| Haiku 4.5 | $0.00017 | $0.00205 |
Grade A, and why
paper-planning 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 3d 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
100% identical to paper-planning — 2 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Planning
A structured approach to planning academic papers before writing begins. Covers four key activities: Story design, Experiment planning, Figure design, and Timeline management.
When to Use This Skill
If you don't yet have an idea, use the
research-ideationskill first to find a problem and design a solution.
- User wants to plan a paper before writing
- User asks about structuring a paper's story or contributions
- User needs to plan experiments (comparisons, ablations)
- User wants to design pipeline figures or teaser figures
- User asks about writing timelines or submission schedules
Planning Overview
Paper planning follows four steps, ideally completed before writing begins:
Step 1: Story Design → What is the narrative? What are the contributions?
Step 2: Experiment Plan → What experiments prove our claims?
Step 3: Figure Design → How do we visually communicate the method?
Step 4: Timeline → When does each section get written?
Counterintuitive Planning First
Prioritize these counterintuitive rules before regular planning:
- Write your rejection letter first: Draft the top-5 likely rejection comments ("limited novelty", "missing baseline", "not robust", etc.), then plan experiments that directly preempt each one.
- Narrow claim before broad claim: Define the smallest defensible core claim first. Expand only after evidence is strong. Over-broad claims fail review more often than narrow strong claims.
- Design ablations before polishing method text: If a module cannot be ablated cleanly, its contribution claim is weak.
- Allocate compute to stress tests, not only benchmarks: A single convincing stress-test figure often contributes more than multiple small benchmark gains.
- Plan a fallback narrative now: If SOTA gain is marginal, predefine a secondary value proposition (efficiency, robustness, fewer assumptions, wider applicability).
What ships with it
6 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.
- 3d ago First seen · 196 lines · 166 tokens per session scan A f6729c5c1b29
paper-planning is a skill published in the GitHub repository CamusGIT/EvoQuant (215 stars, last pushed 17d ago), licensed Apache-2.0. It adds 166 tokens to every session and 2,054 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to paper-planning, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
error-recovery
Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.
security-review
How to review PRs for security — credentials, injection, workflow permissions, supply chain, git operation safety.
shogun-screenshot
スクリーンショットの取得・加工を行う。ローカルスクショから最新画像を取得、 PlaywrightでWebページをキャプチャ、画像のトリミング・リサイズ、機微情報を黒塗りマスキング。 記事執筆、レポート作成、UI確認、画像加工時に起動。 「スクショ」「スクリーンショット」「画面キャプチャ」「最新のスクショ」「画像加工」「トリミング」「マスク」「写メ」「写メ撮った」「スクショ撮った」で起動。 Do NOT use for: 画像生成(shogun-imagegenを使え)。.
creating-skills
Guide for creating Claude Code skills following Anthropic's official best practices. Use when user wants to create a new skill, build a skill, write SKILL.md, update an existing skill, or needs skill creation guidelines. Provides structure, frontmatter fields, naming conventions, and new features like dynamic context…