A required verification checklist for changes to RustBrowser, a Rust-based browser project. It combines formatting checks, linting, tests, a release build when needed, and real smoke tests against a site or tool interface.

Use it before reporting RustBrowser work as finished, especially after changing fetching, rendering, or the MCP interface, to run the required checks and capture their results.

It prevents declaring a change complete without evidence that the code passes automated checks and still works in a realistic run.

How JoshuaWangTW/RustBrowser configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to JoshuaWangTW/RustBrowser. 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/JoshuaWangTW/RustBrowser/master/.claude/skills/verify-rb/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/JoshuaWangTW/RustBrowser

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/joshuawangtw/rustbrowser/verify-rb.svg)](https://agentmods.dev/skills/joshuawangtw/rustbrowser/verify-rb)

Your own site

<a href="https://agentmods.dev/skills/joshuawangtw/rustbrowser/verify-rb"><img src="https://agentmods.dev/badge/skills/joshuawangtw/rustbrowser/verify-rb.svg" alt="Measured on agentmods" height="20"></a>

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 388 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00055	$0.00388
Opus 5	$0.00028	$0.00194
Sonnet 5	$0.00011	$0.00078
Haiku 4.5	$0.00006	$0.00039

Measured 8d ago against content hash 6dd4a2da67c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

verify-rb 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 8d 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.

.claude/skills/verify-rb/SKILL.md · 45 lines

What it actually says

Verify RB

宣告完成的唯一途徑。全部通過才算過；任一步失敗就回去修，不降級標準。

1. 環境（每個 shell 都要先設）

$env:Path = "$env:USERPROFILE\.cargo\bin;D:\aiproject\RustBrowser\.tools\nasm-2.16.03;$env:Path"
$env:CARGO_HTTP_CHECK_REVOKE = "false"

2. 靜態檢查（= CI 同款）

cargo fmt --all -- --check
cargo clippy --all-targets -- -D warnings

3. 測試

cargo test

全部 suite（unit / integration / session / eval / schema_freeze / benchmark）0 failed 才算綠。

4. 真實煙測（動過 fetch / render / MCP surface 時）

cargo build --release
# CLI 真站煙測
target\release\rustbrowser.exe https://example.com --stats
# MCP 煙測（動過 MCP surface 時）：以 stdio 打 initialize + fetch_url

5. 證據

回報必附：測試 summary 行（test result: ok. N passed）+ 煙測輸出片段。「應該可以了」不是證據；「實測 X → 得到 Y」才是。

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.

8d ago First seen · 45 lines · 55 tokens per session scan A 6dd4a2da67c0

Subscribe to this mod's changes

verify-rb is a skill published in the GitHub repository JoshuaWangTW/RustBrowser (10 stars, last pushed 17d ago), licensed MIT. It adds 55 tokens to every session and 388 once invoked, about $0.0003 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

RustBrowser: Skill for Claude Code