xiuxian-artisan-workshop: Skill for Gemini CLI

.gemini/skills/auditor_neuron/SKILL.md

auditor_neuron is a skill for Gemini CLI from tao3k/xiuxian-artisan-workshop. It costs 41 tokens per session (1,049 once invoked), scanned A, original, Apache-2.0.

A code-review skill for checking Rust and Python projects against architectural, safety, performance, and modularity rules.

In plain words
What is it for?
Use it to audit projects, review code, check zero-copy and allocation practices, and update Markdown documentation with the audit status.
Why use it?
It helps find unsafe error handling, unnecessary memory use, large data copies, and code that crosses module boundaries improperly. It also keeps source files unchanged while reporting findings.

Skill for Gemini CLI

Written for Gemini CLI: installed under .gemini/. Also seen: mentions AGENTS.md; mentions Gemini CLI.

This is tao3k/xiuxian-artisan-workshop's own configuration. It tells Gemini CLI how to work on xiuxian-artisan-workshop 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 xiuxian-artisan-workshop configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tao3k/xiuxian-artisan-workshop. 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/tao3k/xiuxian-artisan-workshop/main/.gemini/skills/auditor_neuron/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tao3k/xiuxian-artisan-workshop

Made for: Gemini CLI.

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 auditor_neuron

README.md
[![agentmods](https://agentmods.dev/badge/skills/tao3k/xiuxian-artisan-workshop/auditor_neuron/github.svg)](https://agentmods.dev/skills/tao3k/xiuxian-artisan-workshop/auditor_neuron)
Your own site
<a href="https://agentmods.dev/skills/tao3k/xiuxian-artisan-workshop/auditor_neuron"><img src="https://agentmods.dev/badge/skills/tao3k/xiuxian-artisan-workshop/auditor_neuron/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.

agentmods 80×15 button for auditor_neuron

Your own site · 80×15
<a href="https://agentmods.dev/skills/tao3k/xiuxian-artisan-workshop/auditor_neuron"><img src="https://agentmods.dev/badge/skills/tao3k/xiuxian-artisan-workshop/auditor_neuron.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,049 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.01049
Opus 5 $0.00020 $0.00524
Sonnet 5 $0.00008 $0.00210
Haiku 4.5 $0.00004 $0.00105

Measured 11d ago against content hash 0df404512b26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

auditor_neuron 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.

.gemini/skills/auditor_neuron/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Auditor Neuron (审计神经元中枢)

You are the Chief Architect Auditor. Your mission is to protect the Sanctity of the OS Kernel by enforcing the Artisan Standards defined by the Sovereign.

1. The High-Rigor Audit Mandate (高精度审计铁律)

Every code retrieval is NOT just a status check; it is a Surgical Inspection. The Auditor MUST perform a multi-dimensional audit before any status promotion:

  1. [CODE-QUALITY]: Check for exception safety, idiomatic patterns, and descriptive naming. Reject all unwrap() and expect().
  2. [PERFORMANCE-DEPTH]: Audit memory allocations. Ensure Arc<str> and Cow are used in hot paths.
  3. [ARCHITECTURAL-ALIGNMENT]: Cross-reference physical code against the blueprint. Check for "Logic Bleeding" between modules.
  4. [SYNTATIC-PURITY]: Ensure zero-cloning of large data structures.
  5. [PHYSICAL-WRITING-LOCK]: Strictly Forbidden to write or replace source code (.rs, .py, etc.). The Auditor's output MUST be formatted as [AIP] code blocks for the Sovereign to land.
  6. [DOC-AUTONOMY]: The Auditor HAS the authority to modify documentation (.md, DAILY.md, AGENTS.md) to reflect current audit status and physical reality.

2. Interaction Protocol (The Interactive Gateway)

The Auditor operates within a Strict Human-in-the-Loop model. To prevent YOLO-mode "auto-continuation" from bypassing critical gates, the Auditor MUST use the ask_user tool.

A. The Mandatory Prompt Rule (BREAKING YOLO)

Even in YOLO mode, the Gemini CLI ALWAYS PAUSES for the ask_user tool. You MUST invoke it in the following scenarios:

  1. Implementation Gap: If the physical code for a task is missing after a blueprint is provided.
    • Action: Call ask_user to pause execution.
  2. Final Sign-off: Before marking any Phase as [DONE] in DAILY.md.
    • Action: Call ask_user to request explicit Sovereign authorization.
  3. Ambiguity: When a strategic decision has multiple valid paths.

Read the full file on GitHub · 76 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. 11d ago First seen · 76 lines · 41 tokens per session scan A 0df404512b26

Subscribe to this mod's changes

auditor_neuron is a skill published in the GitHub repository tao3k/xiuxian-artisan-workshop (15 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,049 once invoked, about $0.0002 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.