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 LiXin97/agora-lab --skill student-write-papergit clone --depth 1 https://github.com/LiXin97/agora-labWrote 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/lixin97/agora-lab/student-write-paper)<a href="https://agentmods.dev/skills/lixin97/agora-lab/student-write-paper"><img src="https://agentmods.dev/badge/skills/lixin97/agora-lab/student-write-paper/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/lixin97/agora-lab/student-write-paper"><img src="https://agentmods.dev/badge/skills/lixin97/agora-lab/student-write-paper.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 | $0.00020 | $0.00562 |
| Opus 5 | $0.00010 | $0.00281 |
| Sonnet 5 | $0.00004 | $0.00112 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
student-write-paper 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 9d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Student Write Paper
Student-specific extensions
Write around a claim-evidence structure:
- claim
- evidence
- limitation
- next question
Every draft should contain:
- contribution bullets
- explicit limitations
- no result statement without a matching artifact or citation
Do not write a stronger story than the experiments can defend.
Purpose
Draft paper sections for eventual publication, following standard ML/AI conference format.
Paper Structure
{artifact_dir}/{your-name}/
├── paper_draft_v1.md
├── paper_draft_v2.md (revised after review)
└── figures/
├── main_results.png
└── architecture.png
Standard Sections
1. Abstract
- Problem statement (1-2 sentences)
- Approach (1-2 sentences)
- Key results (1-2 sentences)
- Significance (1 sentence)
2. Introduction
- Motivation and problem context
- Limitations of existing approaches
- Our contribution (bulleted list)
- Paper organization
3. Related Work
- Organized by theme, not chronologically
- Position our work relative to prior art
- Note what we borrow vs. what is novel
4. Method
- Formal problem definition
- Proposed approach with mathematical notation
- Algorithm pseudocode if applicable
- Complexity analysis
5. Experiments
- Experimental setup (datasets, baselines, metrics, implementation details)
- Main results table
- Ablation studies
- Analysis and discussion
6. Conclusion
- Summary of contributions
- Limitations
- Future work
Writing Rules
- Use precise language — avoid vague claims ("significantly better" → "3.2% improvement in F1")
- Every claim must be supported by evidence (experiments or citations)
- Define all notation on first use
- Tables and figures must be self-contained (readable without main text)
- Use consistent notation throughout
Versioning
- Save each major revision as a new version:
paper_draft_v1.md,paper_draft_v2.md - After reviewer feedback, create a new version addressing all comments
- Include a changelog at the top of each new version
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.
- 9d ago First seen · 98 lines · 20 tokens per session scan A fec4af918ef8
student-write-paper is a skill published in the GitHub repository LiXin97/agora-lab (49 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 562 once invoked, about $0.0001 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
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
recording
Capture screen recordings and screenshots on any registered computer (macOS, Windows, Linux, HarmonyOS) and manage the recording library.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
plan
Turn a sufficiently understood task into an ordered implementation plan with dependencies and verification. Orchestrate Codewhale’s native plan state; do not build a parallel planner.