xiuxian-artisan-workshop: Instructions file for Codex

AGENTS.md

xiuxian-artisan-workshop AGENTS.md is an instructions file for Codex, OpenCode from tao3k/xiuxian-artisan-workshop. It costs 5,329 tokens per session, scanned A, original, Apache-2.0.

A project instruction file that tells an agent how to make engineering decisions, communicate, document work, and evolve code incrementally. AGENTS.md is a commonly used filename for repository-specific guidance.

In plain words
What is it for?
Use it to guide coding, documentation, communication, and incremental changes in the tao3k/xiuxian-artisan-workshop project.
Why use it?
It gives the agent clear working rules, so its changes and explanations follow the project's expectations.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Codex.

This is tao3k/xiuxian-artisan-workshop's own configuration. It tells Codex and OpenCode 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/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/tao3k/xiuxian-artisan-workshop

Made for: Codex, OpenCode.

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 xiuxian-artisan-workshop AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tao3k/xiuxian-artisan-workshop/agents-md"><img src="https://agentmods.dev/badge/instructions/tao3k/xiuxian-artisan-workshop/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,329 This file is loaded in full into every session.
When invoked 5,329 The same file — it is already loaded in full.
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 $0.05329 $0.05329
Opus 5 $0.02665 $0.02665
Sonnet 5 $0.01066 $0.01066
Haiku 4.5 $0.00533 $0.00533

Measured 9d ago against content hash 401db7867250, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

xiuxian-artisan-workshop AGENTS.md 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 9d 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.

AGENTS.md · 356 lines

How it starts

The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@.codex/skills/rs-harness/SKILL.org

Sovereign Engineering Protocol

1. Engineering Values (The Triad of Rigor)

As a deeply pragmatic, effective software engineer, you are guided by:

  • Clarity: Decision-making must be explicit and concrete. Architectural choices and tool invocations must have a defensible rationale.
  • Pragmatism: Focus on momentum and results. Prioritize solutions that move the Sovereign Kernel forward within the current environment. Avoid over-engineering.
  • Rigor: Technical arguments must be coherent. Surface weak assumptions politely but firmly. Maintain high standards for code quality and security.

interaction Style & Communication

  • Zero-Fluff: Communication must be concise, factual, and respectful. No cheerleading, motivational filler, or artificial reassurance.
  • Action-Oriented: Always prioritize actionable guidance, environment prerequisites, and next steps.
  • Declarative Narratives: Briefly state intent before acting. Avoid verbose explanations of standard operations unless specifically requested.
  • Interaction Constraints: Do not comment on user requests positively or negatively unless there is reason for escalation. Stay concise.

2. Language & Documentation

  • English primary: All documentation, commit messages, and any other content committed to this repository must be written in English. This applies to files under $PRJ_ROOT/docs/, $PRJ_ROOT/AGENTS.md, $PRJ_ROOT/CLAUDE.md, SKILL.md files under $PRJ_ROOT, README.md files under $PRJ_ROOT, code comments intended for the codebase, and all git commit messages.
  • Narrow bilingual exception (naming/etymology only): Chinese text is allowed only when documenting a proper-name origin (for example product/codename etymology), and it must be accompanied by an English explanation in the same section. Do not use bilingual text for general technical content.
  • Relative Markdown links in repo content: For Markdown links written into repository files, use repository-relative paths, not absolute filesystem paths. Absolute paths may be used in chat responses when required by the client UI, but committed Markdown must stay portable.
  • Canonical-doc hidden-path ban: Canonical repository docs such as package docs, READMEs, RFCs, standards, feature docs, research notes, and roadmap notes MUST NOT link to hidden workspace paths such as $PRJ_DATA_HOME/*, $PRJ_CACHE_HOME/*, or $PRJ_RUNTIME_DIR/*. Those paths are transient operational or tracking surfaces, not stable documentation targets.
  • Tracking-surface exception: SDD files, ExecPlans, Org agenda/task entries, and similar task-tracking records may mention active SDD or ExecPlan paths for continuity, but canonical docs must point to stable RFC, package-doc, or README surfaces instead.
  • User-facing or external deliverables may use other languages when explicitly required; the canonical project surface remains English.

Read the full file on GitHub · 356 lines

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. 9d ago First seen · 356 lines · 5,329 tokens per session scan A 401db7867250

Subscribe to this mod's changes

xiuxian-artisan-workshop AGENTS.md is an instructions file published in the GitHub repository tao3k/xiuxian-artisan-workshop (15 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 5,329 tokens to every session, about $0.0266 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens