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/color4-alt/citecheck/claude-mdgit clone --depth 1 https://github.com/color4-alt/CiteCheckWrote 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/instructions/color4-alt/citecheck/claude-md)<a href="https://agentmods.dev/instructions/color4-alt/citecheck/claude-md"><img src="https://agentmods.dev/badge/instructions/color4-alt/citecheck/claude-md.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 5.1 | $0.00675 | $0.00675 |
| Opus 5 | $0.00338 | $0.00338 |
| Sonnet 5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
CiteCheck CLAUDE.md 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 6d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CiteCheck — Project Context for Claude Code
CiteCheck is a Python CLI tool and agent skill for verifying academic paper citations. This repository contains both the installable Python package (pip install CiteCheck) and the agent skill definitions.
When This Context Applies
Load this context when working on:
- The
citecheckPython package (src/citecheck/) - The agent skill definitions (
skills/,references/) - CLI behavior, parsing logic, or report generation
- Bug fixes or feature additions to the citation verification pipeline
Project Structure
CiteCheck/
├── src/citecheck/ # Python package source
│ ├── cli.py # CLI entry point
│ ├── parser.py # LaTeX / PDF dispatcher
│ ├── bibtex_parser.py # BibTeX .bib parser
│ ├── pdf_parser.py # PDF text extraction
│ ├── verifier.py # Crossref / Semantic Scholar verification
│ ├── matcher.py # Thematic & semantic scoring (heuristic + LLM)
│ ├── reporter.py # Markdown report generator
│ └── models.py # Shared dataclasses
├── skills/citecheck/ # Agent skill (cross-platform)
│ └── SKILL.md # Skill entry point
├── references/ # Skill reference docs
│ ├── format-check-rules.md
│ ├── api-reference.md
│ └── semantic-matching-prompt.md
├── scripts/ # Standalone utility scripts
├── tests/ # pytest suite
├── examples/ # Example outputs
├── pyproject.toml # Package config
└── README.md # Human-facing docs
Architecture Decisions
- LaTeX-first, PDF-fallback:
.tex+.bibparsing is precise; PDF extraction is lossy - Skill vs CLI separation: The CLI handles parsing/format/querying; the agent (Claude) handles thematic/semantic evaluation using its own reasoning
- Zero mandatory API keys: Crossref and Semantic Scholar are public APIs; LLM matching is optional (
--api-key) or delegated to the agent - Models extracted to
models.py: Prevents circular imports betweenparser.py,bibtex_parser.py, andpdf_parser.py
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.
- 6d ago First seen · 66 lines · 675 tokens per session scan A 6a5dff24e2d8
CiteCheck CLAUDE.md is an instructions file published in the GitHub repository color4-alt/CiteCheck (59 stars, last pushed 3mo ago), licensed MIT. It adds 675 tokens to every session, about $0.0034 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 instructions, from other repositories
med-paper-assistant AGENTS.md
AGENTS.md instructions for u9401066/med-paper-assistant, covering agents.md - vs code copilot agent 指引, 核心價值：逐步多輪演進, 運行模式, 檔案保護（normal/research） and 專案規則.
sourceright AGENTS.md
AGENTS.md instructions for edithatogo/sourceright, covering sourceright codex instructions, codev - ai agent instructions, project overview, available protocols and file resolution (how codev finds protocols and templates).
scientific-writing CLAUDE.md
Instructions for koljaschoepe/scientific-writing, covering scientific writing framework, schnellstart, workflow, befehle and regeln für generierte texte.
scitex-python CLAUDE.md
Claude Code instructions for scitex-ai/scitex-python, covering workflow orchestration, 1. plan mode default, 2. subagent strategy, 3. self-improvement loop and 4. verification before done.
avoid-overkill AGENTS.md
AGENTS.md instructions for 6Kmfi6HP/avoid-overkill: This repository packages a reusable Agent Skill and plugin manifests.
academic-writer-skills AGENTS.md
AGENTS.md instructions for muhammad1438/academic-writer-skills, covering academic writer skills — multi-agent workflow guide, skill dependency map, pipeline patterns, pattern 1: full research paper and pattern 2: grant application pipeline.