thurbox: Skill for Claude Code

.agents/skills/thurview/SKILL.md

thurview is a skill for Claude Code from Thurbeen/thurbox. It costs 102 tokens per session (2,160 once invoked), scanned A, original, MIT.

A tool for creating and publishing an evidence-based review of a code branch, pull request, or range of commits. It links claims to exact lines at a fixed version and lets readers inspect, comment on, question, or approve the change in a browser.

In plain words
What is it for?
Use it to prepare a review, validate and publish its file and line references, present diffs and diagrams, answer comments, and record approval or requested changes.
Why use it?
It makes code review easier to verify than a free-form explanation because each statement points to the relevant code. It also keeps questions and requested changes connected to the reviewed lines.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

This is Thurbeen/thurbox's own configuration. It tells Claude Code how to work on thurbox itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything thurbox configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Thurbeen/thurbox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Thurbeen/thurbox/main/.agents/skills/thurview/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Thurbeen/thurbox

Made for: Claude Code.

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 thurview

README.md
[![agentmods](https://agentmods.dev/badge/skills/thurbeen/thurbox/thurview.svg)](https://agentmods.dev/skills/thurbeen/thurbox/thurview)
Your own site
<a href="https://agentmods.dev/skills/thurbeen/thurbox/thurview"><img src="https://agentmods.dev/badge/skills/thurbeen/thurbox/thurview.svg" alt="Measured on agentmods" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,160 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium
  • medium MCP Rug Pull · line 28
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 5.1 $0.00102 $0.02160
Opus 5 $0.00051 $0.01080
Sonnet 5 $0.00020 $0.00432
Haiku 4.5 $0.00010 $0.00216

Measured yesterday against content hash 8431c1b3047c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

thurview 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 yesterday.

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.

.agents/skills/thurview/SKILL.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

thurview

The agent studies the change and writes a short document in which every claim about code is anchored to an exact file and line range at a pinned commit. thurview validates those anchors, seals a revision, and serves it in the browser with live code peeks, diffs, diagrams and a map. The reader asks questions, leaves anchored comments, and approves or requests changes. The agent answers, updates, republishes.

flowchart LR
  A[scaffold: pin base and head] --> B[author review.md, data.yaml, map.yaml]
  B --> C[publish: validate and seal revision]
  C --> D[open: reader reviews in the browser]
  D -->|question| E[threads reply]
  E --> D
  D -->|request changes| B
  D -->|approve| F[done]

Run the CLI as thurview. When it is not on PATH, npx -y thurview runs the published package with the same commands; substitute it everywhere below.

Every command prints TOON on stdout: the result, then help[] with the next commands. Errors are structured on stdout too (error, code, help); exit code 1 is a failure, 2 a usage error such as an unknown flag. Progress goes to stderr; do not scrape it. thurview alone shows the reviews of the current directory; thurview <command> --help shows flags and examples.

Request

$ARGUMENTS

Empty: the current branch against its up-to-date trunk. A PR number or URL: that pull request. --base/--head: that range. Anything else: an architecture review of that topic in the current repository.

Before authoring

Read the guidance files that exist, in this order. The second wins on conflict.

  1. ~/.thurview/THURVIEW.md (or $THURVIEW_HOME/THURVIEW.md), user guidance.
  2. THURVIEW.md at the repository root, repository guidance.

thurview scaffold lists the ones it found under guidance.

Read Document authoring before you write. Read Components before you edit data.yaml or add a fenced component. Read Lifecycle for statuses, storage and thread rules. Read Software map before you author map.yaml. Read Theme before you write theme.yaml.

Read the full file on GitHub · 220 lines

Files

What ships with it

5 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. yesterday First seen · 220 lines · 102 tokens per session scan A 8431c1b3047c

Subscribe to this mod's changes

thurview is a skill published in the GitHub repository Thurbeen/thurbox (60 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 2,160 once invoked, about $0.0005 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 2026-09-06.