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 commands/reggiechan74/cc-plugins/authorgit clone --depth 1 https://github.com/reggiechan74/cc-pluginsWhat 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 | $0.00018 | $0.05045 |
| Opus 5 | $0.00009 | $0.02523 |
| Sonnet 5 | $0.00004 | $0.01009 |
| Haiku 4.5 | $0.00002 | $0.00505 |
Grade A, and why
author 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 — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Author a Math Paper
Create a new .model.md document through interactive ideation. You describe concepts — Claude formalizes them into complete paper sections with prose, display math, and validated Python blocks. Each section is written and validated before moving on.
Step 1: Initialize
New paper (no path given, or file doesn't exist):
- Check for review findings. If the user provides a
.review.mdfile as the path argument, or if a<basename>.review.mdfile exists adjacent to the target.model.mdpath, read the review findings. These contain a recommended template, outline, and key decisions from a prior/math-paper-creator:reviewsession. Tell the user: "I found review findings from a prior session. I'll use these to guide template selection and authoring." Skip items 1-3 below and proceed directly to Step 1.5 with the review context loaded. If no review file is found, continue with item 1. - Ask the user to describe the problem domain. Accept anything from a vague concept ("I want to model workforce optimization under constraints") to a specific sketch ("I have sets I, J, P and an allocation variable x_ijp").
- Create the
.model.mdfile with YAML frontmatter:--- title: <derived from user description> date: <today> author: <ask or infer> version: 0.1 --- - Initialize an empty running symbol name registry (a list you maintain across sections).
- Proceed to Step 2.
Resume (path to an existing .model.md file):
- Read the file.
- Run the meta-compiler check to rebuild the symbol state:
cd ${CLAUDE_PLUGIN_ROOT} && PYTHONPATH=src python3 -m meta_compiler.cli check "<file_path>" - Rebuild the running symbol name registry from the existing validate blocks (read all symbol names already registered).
- Show the user a summary: number of sections, symbol count by type, any warnings.
- Ask where they want to continue. Proceed to the authoring loop (Step 3).
Step 1.5: Template selection
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 · 420 lines · 18 tokens per session scan A da0fb0c21b3f
author is a command published in the GitHub repository reggiechan74/cc-plugins (6 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 5,045 once invoked, about $0.0001 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 commands, from other repositories
notebook-review
Comprehensive review of Jupyter notebooks and Python scripts.
cross-validate
Take a specific scientific claim and confirm or refute it across 3+ independent databases, then report concordance. Use before publishing, citing, or acting on a fact when you want to know how strongly it's supported. Forces multi-source verification that the agent doesn't naturally enforce.
translate-id
Resolve an identifier across all relevant namespaces (HGNC symbol, Ensembl, UniProt, NCBI Gene ID, RefSeq, MGI, OMIM, ChEMBL, PubChem, etc.). Detects the input namespace automatically, picks the right resolver tool, and returns a complete cross-reference table. Use when you have an ID in one namespace and need it in…
autoprove
Autonomous multi-cycle theorem proving with explicit stop budgets.
flow-nexus-neural
Train and deploy neural networks in distributed sandboxes.
paperfit-undo
作用: 恢复最近一次 PaperFit 自动写回前的备份版本,优先回滚主 .tex,必要时一并恢复 data/state.json。.