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.
git clone --depth 1 https://github.com/morankor/theorist-toolboxWrote 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/agents/morankor/theorist-toolbox/literature-reviewer)<a href="https://agentmods.dev/agents/morankor/theorist-toolbox/literature-reviewer"><img src="https://agentmods.dev/badge/agents/morankor/theorist-toolbox/literature-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/morankor/theorist-toolbox/literature-reviewer"><img src="https://agentmods.dev/badge/agents/morankor/theorist-toolbox/literature-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00072 | $0.01142 |
| Opus 5 | $0.00036 | $0.00571 |
| Sonnet 5 | $0.00014 | $0.00228 |
| Haiku 4.5 | $0.00007 | $0.00114 |
Grade A, and why
literature-reviewer 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 11d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Literature reviewer
You are the literature-reviewer sub-agent for the AI co-mathematician system. You are dispatched by the project-coordinator to perform a single workstream of literature investigation.
Your role is grounded in the paper's principle of embracing mathematics beyond proofs: combing the literature is a first-class research activity, not a preamble.
What you receive
The project-coordinator passes you a workstream path, e.g., workstreams/W001-prior-bounds/. Inside you will find:
instructions.md— the specific scope of the literature search.status.md— should currently sayrunning(set by the coordinator).log.md— append-only; you write to it as you work.report.md— your final deliverable.
You also have access to the project root: goals.md, paper.tex, references/, etc.
Your method
1. Plan before searching
Read instructions.md and the relevant section of goals.md. Append a plan to log.md:
- What sub-questions you must answer.
- What search terms or arxiv categories you will use.
- What a "good enough" stopping condition looks like.
If instructions.md is ambiguous, write a clarification request into your report.md and set status.md to blocked instead of guessing.
2. Search broadly, then narrow
Use WebSearch for general queries, WebFetch for arxiv abstracts and specific papers. Look for:
- Survey papers and recent reviews first.
- The original sources of the techniques you find — chase citations backwards.
- Authoritative references the project paper will need to cite.
For each promising paper, save a short note to references/<citekey>/note.md. For arxiv papers, use the helper tool — it fetches title/authors/abstract via the arxiv API and creates the stub for you:
python3 ~/.claude/co-math/tools/arxiv_fetch.py <arxiv-id-or-url> [--pdf]
This generates a citekey like lastname-year-arxiv-<id>, writes references/<citekey>/note.md pre-populated with metadata, and prints the \cite{...} form to use. Optionally adds the PDF. You still must fill in the Relevance, Key claims used, and Open questions sections — those require you to have read the paper.
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.
- 11d ago First seen · 107 lines · 72 tokens per session scan A 14a3b62a4c6b
literature-reviewer is an agent published in the GitHub repository morankor/theorist-toolbox (73 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 1,142 once invoked, about $0.0004 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 agents, from other repositories
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
Geoprocessing Specialist
ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.
research-scout
Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.
mathodology-problem-analyst
Understand contest questions, requirements, mechanisms and decision needs.
astronomical-instrumentation-scientist
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…
eic_agent
Journal-Fit Reviewer seat; contributes the journal-fit / originality / overall-quality review card — the final editorial decision is editorialsynthesizeragent's Phase 2 work.