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/agents-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/agents-md)<a href="https://agentmods.dev/instructions/color4-alt/citecheck/agents-md"><img src="https://agentmods.dev/badge/instructions/color4-alt/citecheck/agents-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 | $0.00499 | $0.00499 |
| Opus 5 | $0.00249 | $0.00249 |
| Sonnet 5 | $0.00100 | $0.00100 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
CiteCheck AGENTS.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 5d 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.
What it actually says
@./skills/citecheck/SKILL.md @./references/api-reference.md @./references/format-check-rules.md @./references/thematic-scoring-prompt.md @./references/semantic-matching-prompt.md
CiteCheck — Development & Testing Rules
Pre-Push Testing Requirement
Every feature change MUST be validated against the demo test fixtures before committing.
The latex_paper/ directory (sibling to CiteCheck/) contains intentionally flawed references used as the canonical integration test:
# From inside CiteCheck/
cd CiteCheck
# 1. Test LaTeX source parsing
citecheck ../latex_paper/main.tex --skip-verification --skip-semantic -o /tmp/test_latex.md
# Expected baseline:
# - 19 references parsed
# - 18 citation markers detected
# - 7 format issues (preprints, wrong entry type, missing author, future year)
# - Uncited list: only [3] touvron2023llama
# 2. Test PDF fallback parsing
citecheck ../latex_paper/main.pdf --skip-verification --skip-semantic -o /tmp/test_pdf.md
# Expected baseline:
# - 18 references parsed (PDF loses incomplete entry metadata)
# - 18 citation markers detected
# - 0 format issues (PDF parser has limited format checking)
Regression Checklist
- LaTeX test produces expected reference count (±0)
- LaTeX test produces expected citation marker count (±0)
- Uncited references list shows ONLY truly uncited entries (e.g.,
touvron2023llama) - PDF test runs without crashing
- pytest
tests/test_parser.pypasses (8/8) -
python -m citecheck --helpworks
Known Improvements (Post-0.1.0)
- arXiv year parsing (
pdf_parser.py): arXiv IDs likearXiv:2004.05150are no longer mistaken for publication years. - Crossref false-match filtering (
verifier.py): Low-similarity matches are now rejected; large year mismatches (>2 years) are flagged separately from small mismatches.
If any baseline metric shifts unexpectedly, investigate before pushing.
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.
- 5d ago First seen · 52 lines · 499 tokens per session scan A d2fed4be7b99
CiteCheck AGENTS.md is an instructions file published in the GitHub repository color4-alt/CiteCheck (59 stars, last pushed 3mo ago), licensed MIT. It adds 499 tokens to every session, about $0.0025 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.
scientific-writing CLAUDE.md
Instructions for koljaschoepe/scientific-writing, covering scientific writing framework, schnellstart, workflow, befehle and regeln für generierte texte.
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).
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.