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/yqi96/warranted/overleaf-setupnpx skills add yqi96/warranted --skill overleaf-setupgit clone --depth 1 https://github.com/yqi96/warrantedWhat 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 | $0.00059 | $0.00825 |
| Opus 5 | $0.00030 | $0.00413 |
| Sonnet 5 | $0.00012 | $0.00165 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
overleaf-setup 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 2d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Configure automatic Overleaf push so that every .tex edit triggers a push without further agent involvement. The skill ends when the hook is written to settings.local.json and the user has been told to restart Claude Code.
Step 1 — Install
uv tool install overleaf-for-agents
Verify:
leaf --version
Step 2 — Authenticate
leaf login
A browser window opens. Tell the user: "Log in to Overleaf and wait for your project dashboard to appear. Let me know when ready."
Verify after confirmation:
leaf list
Fallback — if leaf login fails (no Chrome / CDP error):
- Ask the user to open https://www.overleaf.com, log in, then go to DevTools → Application → Cookies → copy the value of
overleaf_session2(starts withs%3A) - Write the value to
~/.olauth - Retry
leaf list
Step 3 — Choose or create project, and local directory
Ask the user whether they want to sync to an existing project or create a new one.
Existing project: run leaf list, show the output, ask which project to use. Record PROJECT_ID (24-char hex).
New project: ask for a project name, then run:
leaf create "NAME"
Record PROJECT_ID from the output.
Also ask which local directory contains the LaTeX files. Record LATEX_DIR (absolute path).
Step 4 — Init
leaf init --project PROJECT_ID --dir LATEX_DIR
This writes leaf.toml into LATEX_DIR. The push script copies it into staging on each run.
Step 5 — Write the hook
Determine SKILL_DIR (absolute path to ${CLAUDE_PLUGIN_ROOT}/skills/overleaf-sync) and DB_PATH (absolute path to .toulmin/argument.db).
Merge the following into .claude/settings.local.json, preserving any existing hooks:
{
"hooks": {
"Stop": [{
"hooks": [{
"type": "command",
"command": "uv run SKILL_DIR/scripts/overleaf-push.py --dir LATEX_DIR --db DB_PATH --require-statement-cites",
"timeout": 120,
"statusMessage": "Checking citations and pushing to Overleaf..."
}]
}]
}
}
What ships with it
1 file 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.
- 2d ago First seen · 118 lines · 59 tokens per session scan A 51e533783e1c
overleaf-setup is a skill published in the GitHub repository yqi96/warranted (2 stars, last pushed 12d ago), licensed MIT. It adds 59 tokens to every session and 825 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
proof-checker
Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (external reviewer backend, ultra reasoning), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明"…
citation-audit
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations. Use when user says "审查引用", "check citations"…
idea-creator
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
idea-discovery
Workflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", or wants the complete idea exploration workflow.
paper-illustration
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.
meta-optimize
Analyze ARIS usage logs and propose optimizations to SKILL.md files, reviewer prompts, and workflow defaults. Outer-loop harness optimization inspired by Meta-Harness (Lee et al., 2026). Use when user says "优化技能", "meta optimize", "improve skills", "分析使用记录", or wants to optimize ARIS's own harness components based on…