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/issol14/paper2code-skill/paper2codenpx skills add issol14/paper2code-skill --skill paper2codegit 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 | $0.00074 | $0.02688 |
| Opus 5 | $0.00037 | $0.01344 |
| Sonnet 5 | $0.00015 | $0.00538 |
| Haiku 4.5 | $0.00007 | $0.00269 |
Grade A, and why
paper2code scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -L "https://arxiv.org/pdf/xxxx.xxxxx.pdf" -o paper.pdf How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper2Code: 연구 논문을 코드로 변환하는 AI 에이전트
개요
이 Skill은 연구 논문을 체계적으로 분석하고, 실행 가능한 코드로 변환하는 4+2단계 파이프라인을 실행합니다.
핵심 원칙: 단순히 논문을 읽고 코드를 생성하는 것이 아니라, **구조화된 중간 표현(YAML)**을 먼저 생성한 후 코드를 작성합니다.
⚠️ 핵심 행동 제어 규칙 (CRITICAL)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
⚠️ MANDATORY BEHAVIORAL RULES
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
1. 한 번에 하나의 파일만 구현
2. 파일 구현 후 확인/허락 없이 다음 파일로 진행
3. 논문 원본 사양이 항상 참조 코드보다 우선
4. 완료 전 각 Phase의 Self-Check 필수 수행
5. 모든 중간 결과는 YAML 파일로 저장
DO:
✓ 논문에 명시된 것을 정확히 구현
✓ 간단하고 직접적인 코드 작성
✓ 작동하는 것 우선, 우아한 것은 나중
✓ 각 컴포넌트 즉시 테스트
✓ 구현 완료 후 바로 다음 파일로 이동
DON'T:
✗ 파일 사이에 "다음 파일을 구현할까요?" 묻지 말 것
✗ 핵심 기능에 필요하지 않은 광범위한 문서화
✗ 재현에 필요하지 않은 최적화
✗ 과도한 추상화나 디자인 패턴
✗ 지시만 제공하고 실제 코드를 작성하지 않는 것
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
입력 처리
지원 형식
- arXiv URL:
https://arxiv.org/abs/xxxx.xxxxx또는https://arxiv.org/pdf/xxxx.xxxxx.pdf - PDF 파일 경로:
/path/to/paper.pdf - 이미 변환된 텍스트/마크다운: 논문 내용이 텍스트로 제공된 경우
입력 처리 방법
arXiv URL인 경우:
# PDF URL로 변환하여 다운로드
curl -L "https://arxiv.org/pdf/xxxx.xxxxx.pdf" -o paper.pdf
# PDF를 텍스트로 변환 (pdftotext 사용)
pdftotext -layout paper.pdf paper.txt
PDF 파일인 경우:
pdftotext -layout "/path/to/paper.pdf" paper.txt
파이프라인 개요
[사용자 입력: 논문 URL/파일]
│
▼
┌─────────────────────────────────────────────┐
│ Step 0: 논문 텍스트 확보 │
│ - arXiv URL → PDF 다운로드 │
│ - PDF → 텍스트 변환 │
└─────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────┐
│ Phase 0: 참조 코드 검색 (선택적) │
│ @[05_reference_search.md] │
│ 출력: reference_search.yaml │
└─────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────┐
│ Phase 1: 알고리즘 추출 │
│ @[01_algorithm_extraction.md] │
│ 출력: 01_algorithm_extraction.yaml │
└─────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────┐
│ Phase 2: 개념 분석 │
│ @[02_concept_analysis.md] │
│ 출력: 02_concept_analysis.yaml │
└─────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────┐
│ Phase 3: 구현 계획 │
│ @[03_code_planning.md] │
│ 출력: 03_implementation_plan.yaml │
└─────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────┐
│ Phase 4: 코드 구현 │
│ @[04_implementation_guide.md] │
│ 출력: 완전한 프로젝트 디렉토리 │
└─────────────────────────────────────────────┘
What ships with it
7 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.
- 2d ago First seen · 303 lines · 74 tokens per session scan A b2832378a03a
paper2code is a skill published in the GitHub repository issol14/paper2code-skill (34 stars, last pushed 7mo ago), licensed MIT. It adds 74 tokens to every session and 2,688 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
build-discipline
A language- and domain-agnostic engineering discipline for building non-trivial software that actually survives real use — services, parsers, CLIs, data pipelines, simulators, interactive tools, agents, compilers, anything with state, logic, or behavior beyond a toy. Use this skill WHENEVER a task involves writing or…
ps2-recomp-Agent-SKILL
Expert PS2 game reverse engineering and PS2Recomp pipeline porting. Use for ISO/ELF extraction, MIPS R5900 analysis, TOML configuration, syscall stubbing, C++ runtime debugging, and GhydraMCP interaction. Use when the user mentions PS2Recomp, ps2xRuntime, cmake incremental build, SLES, SLUS, out.cpp, runner/.cpp, MIPS…
auth-web-cloudbase
CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.
fix-codesign-error
Slash command that inspects a macOS signing or entitlement failure and explains the minimum fix path. Invoke explicitly with /fix-codesign-error — this skill never self-triggers.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.