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/onboardgit 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 | $0.00016 | $0.02274 |
| Opus 5 | $0.00008 | $0.01137 |
| Sonnet 5 | $0.00003 | $0.00455 |
| Haiku 4.5 | $0.00002 | $0.00227 |
Grade A, and why
onboard 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard a Math Paper
Convert an existing markdown math paper into a fully validated .model.md document with working python:validate blocks. This is an interactive, section-by-section process — you will approve each validation block before moving on.
Step 1: Locate the file
Use the provided path argument. If no path is given, search with Glob for **/*.md (excluding *.model.md files). If multiple results are found:
- Show at most 20 matches and ask the user which one to onboard.
- If more than 20 matches exist, ask the user to provide a path directly.
Step 2: Guard rails
Before proceeding, check two conditions:
-
Already a
.model.mdfile? If the file ends in.model.md, tell the user: "This file is already a.model.mddocument. Use/math-paper-creator:checkto validate it or/math-paper-creator:statusto see its current state." Stop here. -
No math blocks? Read the file and check for
$$...$$display math blocks. If none are found, tell the user: "No display math blocks ($$...$$) were found in this file. There is nothing to onboard." Stop here.
Step 3: Read and analyze
Read the entire document. Identify:
- All sections (by heading level:
#,##,###, etc.) - All
$$...$$display math blocks and which section each belongs to - The mathematical model being described: sets, parameters, variables, expressions, constraints, objectives
Build a mental model of the paper's structure and mathematical content.
Step 4: Present overview
Show the user a summary:
- Number of sections containing math blocks
- Total number of display math blocks
- A high-level interpretation of the model, e.g.: "This paper describes a linear program for workforce scheduling with 3 sets, 5 parameters, 2 variables, and 4 constraints."
Ask the user to confirm or correct this interpretation. The user may respond with free-form corrections. If they do, re-interpret and re-present until the user confirms.
Do not proceed until the user explicitly confirms.
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 · 191 lines · 16 tokens per session scan A 5e1fe1a5c8f3
onboard is a command published in the GitHub repository reggiechan74/cc-plugins (6 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 2,274 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
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…
flow-nexus-neural
Train and deploy neural networks in distributed sandboxes.
check-dev
Type-check a Z specification with fuzz.
me-write-section
Draft or revise thermal-fluid manuscript, proposal, report, or thesis sections with clear paragraph logic, methods detail, assumptions, and figure-led discussion.
diff
Quantitative volume comparison between a CadQuery model and a reference STEP file.