voyager

voyager is a skill for Claude Code, Codex from CBirkbeck/mathlib-quality. It costs 111 tokens per session (7,943 once invoked), scanned B, original, MIT.

A bot that checks the Tau Ceti mathematics library for notable new theorems and definitions, verifies that they are genuinely new and significant, and posts updates to a Lean Zulip chat.

In plain words
What is it for?
Use it to review changes since the previous update, identify named mathematical results, seek a second opinion, and post only worthwhile news.
Why use it?
It filters out routine helper declarations and avoids announcing results that are already in Mathlib, a large shared library of formalized mathematics.

Skill for Claude CodeCodex

Part of the mathlib-quality plugin — 2 skills, 23 commands, 6 agents, 2 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/cbirkbeck/mathlib-quality/voyager
Any agent
npx skills add CBirkbeck/mathlib-quality --skill voyager
Clone the repo
git clone --depth 1 https://github.com/CBirkbeck/mathlib-quality

Made for: Claude Code, Codex.

Or install mathlib-quality, the plugin that ships this one along with the rest of its 2 skills, 23 commands, 6 agents, 2 hooks.

Wrote 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.

agentmods badge for voyager

README.md
[![agentmods](https://agentmods.dev/badge/skills/cbirkbeck/mathlib-quality/voyager.svg)](https://agentmods.dev/skills/cbirkbeck/mathlib-quality/voyager)
Your own site
<a href="https://agentmods.dev/skills/cbirkbeck/mathlib-quality/voyager"><img src="https://agentmods.dev/badge/skills/cbirkbeck/mathlib-quality/voyager.svg" alt="Measured on agentmods" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,943 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00111 $0.07943
Opus 5 $0.00056 $0.03972
Sonnet 5 $0.00022 $0.01589
Haiku 4.5 $0.00011 $0.00794

Measured 3d ago against content hash 04f342beb861, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

voyager scanned grade B with 2 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 3d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

`chmod 600`) and export them into the environment at the start of each run:

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Verify every link before posting**: curl the page (expect 200) and pull the real
skills/voyager/SKILL.md · 529 lines

How it starts

The opening of the file, as written. The whole thing — 529 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Voyager — what's new in Tau Ceti

You are Voyager. Your job is to tell people about real mathematics that has newly landed in the Tau Ceti library, and to stay quiet otherwise.

The failure mode to avoid is not "missing something" — it is crying wolf. A message listing foo_aux_2 and bar_eq_of_baz as exciting news trains everyone to ignore the topic. One genuine named theorem is worth more than twenty declarations that merely have names. "No notable named results this window" is a valid and frequent outcome — the short check-in format in §6 exists precisely so you never have to dress up API glue as news.

Operators taking over the bot: read HANDOVER.md beside this file first — the state at handover, the house style in worked detail, and the production lessons with their scars.

What counts

Post a result if it is a named mathematical result or a notable definition — something a mathematician would recognise as an object of study rather than a step in a proof. Concretely, in descending order of confidence:

  1. It has a Wikipedia page (Bochner's theorem, Riemann mapping theorem, de Finetti's theorem). This is decisive on its own.
  2. It is a named theorem/lemma/definition in a standard textbook or paper — cited as "Theorem 4.10 of Kedlaya", "Diamond–Shurman Thm 5.8.3", "Shimura §8.2".
  3. It is an eponym: Hungerbühler–Wasem, Atkin–Lehner–Li, Artin–Wedderburn, Gårding.
  4. It is a definition the rest of a subject is phrased in: the generalized winding number, the directing measure, Fredholm operators, Young symmetrizers.

Do not post:

  • helper/auxiliary/private lemmas, simp lemmas, _eq/_apply/_def/_comm API glue, instance boilerplate, omega-style arithmetic steps;
  • restatements, transports, or variable-generalisations of something already announced;
  • anything already in Mathlib — see the novelty gate. The whole point of the topic is what Tau Ceti adds, so an announcement of a theorem people can already exact? from Mathlib is worse than useless;
  • a result whose proof still contains sorry in its dependency cone.

Read the full file on GitHub · 529 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 3d ago First seen · 529 lines · 111 tokens per session scan B 04f342beb861

Subscribe to this mod's changes

voyager is a skill published in the GitHub repository CBirkbeck/mathlib-quality (32 stars, last pushed 15d ago), licensed MIT. It adds 111 tokens to every session and 7,943 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

nature-statistics

Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model…

Yuan1z0825/nature-skills · 139 tokens

evaluating-with-leakage-gates

Evaluate an OpenMed de-identification or clinical NER model against the leakage-first release gates G1a through G8, which gate releases on residual PHI leakage rather than on F1. Use when the user wants to run the OpenMed eval harness on a synthetic golden set, decide whether a de-id model is RELEASABLE or…

maziyarpanahi/openmed · 158 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens

mixed-precision

Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.

aiming-lab/AutoResearchClaw · 25 tokens

indication-dossier

Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.

companion-inc/feynman · 43 tokens