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 instructions/issol14/paper2code-skill/agents-mdgit clone --depth 1 https://github.com/issol14/paper2code-skillWhat 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 | $0.00998 | $0.00998 |
| Opus 5 | $0.00499 | $0.00499 |
| Sonnet 5 | $0.00200 | $0.00200 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade D, and why
paper2code-skill AGENTS.md scanned grade D with 2 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 yesterday.
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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls ~/.claude/skills/paper2code/SKILL.md && echo "✅ Skill is ready" Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/paper2code-skill && \ How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - For LLM Agents
This file is specifically designed for LLM agents (Claude, GPT, etc.) to quickly understand and work with this repository.
QUICK SUMMARY
paper2code-skill is a Claude Code Skill that converts research papers (PDF/arXiv) into executable code using a structured 4-phase pipeline.
REPOSITORY STRUCTURE
paper2code-skill/
├── README.md # Human-readable documentation
├── AGENTS.md # This file - for LLM agents
├── LICENSE # MIT License
├── CONTRIBUTING.md # Contribution guidelines
├── .gitignore
└── skills/
└── paper2code/ # ← The actual skill files
├── SKILL.md # Main entry point
├── 01_algorithm_extraction.md # Phase 1
├── 02_concept_analysis.md # Phase 2
├── 03_code_planning.md # Phase 3
├── 04_implementation_guide.md # Phase 4
├── 05_reference_search.md # Phase 0 (optional)
├── 06_memory_management.md # Memory guide
└── README.md # Skill-specific docs
INSTALLATION COMMANDS
# One-liner installation
git clone https://github.com/issol14/paper2code-skill.git /tmp/paper2code-skill && \
cp -r /tmp/paper2code-skill/skills/paper2code ~/.claude/skills/ && \
rm -rf /tmp/paper2code-skill && \
echo "✅ Installed successfully"
Verification
ls ~/.claude/skills/paper2code/SKILL.md && echo "✅ Skill is ready"
WHAT THIS SKILL DOES
When a user provides a research paper (PDF or arXiv URL), this skill guides Claude through:
| Phase | File | Purpose |
|---|---|---|
| 0 (opt) | 05_reference_search.md |
Find similar implementations on GitHub |
| 1 | 01_algorithm_extraction.md |
Extract algorithms, equations, hyperparameters |
| 2 | 02_concept_analysis.md |
Analyze paper structure, components, experiments |
| 3 | 03_code_planning.md |
Create detailed implementation plan (YAML) |
| 4 | 04_implementation_guide.md |
Generate code file-by-file |
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.
- yesterday First seen · 122 lines · 998 tokens per session scan D 9ee4139b2df4
paper2code-skill AGENTS.md is an instructions file published in the GitHub repository issol14/paper2code-skill (34 stars, last pushed 7mo ago), licensed MIT. It adds 998 tokens to every session, about $0.0050 per session on Opus 5. A static security scan graded it D with 2 findings (enumerates other installed skills, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
webfetch-camouflage-mcp AGENTS.md
AGENTS.md instructions for tianhuil/webfetch-camouflage-mcp, covering rules for python repos, general, coding style and validation.
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.
llm-safe-haven CLAUDE.md
Instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.