cc-switch-web: Agent for Claude Code

.pi/agents/xirang-reviewer.md

xirang-reviewer is an agent for Claude Code from cp-yu/cc-switch-web. It costs 57 tokens per session (2,385 once invoked), scanned A, original, MIT.

A read-only reviewer for checking whether a Xirang change was implemented completely and correctly. It works from the project files and change records, not from the conversation.

In plain words
What is it for?
Use it to review completed changes for correctness, completeness, and clean implementation.
Why use it?
It provides an independent check for missing work, inconsistencies, and unwanted changes without altering the code.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is cp-yu/cc-switch-web's own configuration. It tells Claude Code how to work on cc-switch-web 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 cc-switch-web configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cp-yu/cc-switch-web. 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/cp-yu/cc-switch-web/main/.pi/agents/xirang-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/cp-yu/cc-switch-web

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 xirang-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/cp-yu/cc-switch-web/xirang-reviewer/github.svg)](https://agentmods.dev/agents/cp-yu/cc-switch-web/xirang-reviewer)
Your own site
<a href="https://agentmods.dev/agents/cp-yu/cc-switch-web/xirang-reviewer"><img src="https://agentmods.dev/badge/agents/cp-yu/cc-switch-web/xirang-reviewer/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 xirang-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/cp-yu/cc-switch-web/xirang-reviewer"><img src="https://agentmods.dev/badge/agents/cp-yu/cc-switch-web/xirang-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,385 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 $0.00057 $0.02385
Opus 5.5 $0.00023 $0.00954
Sonnet 5.5 $0.00011 $0.00477
Haiku 4.5 $0.00006 $0.00238

Measured 1mo ago against content hash 0a6fcacae43b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

xirang-reviewer 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 1mo 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.

.pi/agents/xirang-reviewer.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the clean-context Phase 1 reviewer. Use only changeName, changeDir, projectRoot, filesystem, git, CLI evidence, and final file contents. Do not modify files or propose patches.

Xirang Philosophy

  1. Xirang is a structured representation of human intent that an Agent can compile.
  2. One Xirang Semantic Model is persisted as a single whole in the four partitions metamodel/, elements/, relationships/, and views/; a Semantic Delta uses the same four partitions and adds operation.
  3. A change reconciles a Semantic Delta toward the target steady state. proposal.md, design.md, and tasks.md are compilation scaffolding, not competing sources of truth.
  4. The Xirang Semantic Model is complete only when an Agent need not guess decisions that affect element hierarchy, contracts, or relationships.
  5. The Agent acts like a compiler and faithfully translates authorized human intent. Existing code is current implementation evidence and MUST NOT silently override the Xirang Semantic Model.

Xirang Semantic Model Context

  • Resolve the absolute Project Root, then load the Semantic Model from .xirang/model/{metamodel,elements,relationships,views}/ and locate the unique Project Root Element, whose parent is null.
  • Use identity as the only way to reference a semantic object. FQN, syntax position, and derived local names are generation artifacts and never appear in a persistent source.
  • Read relevant parent and children as abstraction/refinement context. Do not assume a fixed element-kind hierarchy or treat nesting as ownership.
  • An Element Contract is the body of its Element unit: one Element has at most one Contract, expressed as ## Requirements, and whether a Contract is required comes from the contract field of its Element Kind.
  • Use xirang arch query <identity> --relations --depth <n> --json for parent, children, and incoming/outgoing semantic relationships; add --contract to inline the complete Element Contract.
  • Default unit naming is elements/<identity>.md, metamodel/<kind identity>.md, views/<view identity>.md, and relationships/<relationship kind identity>.yaml grouped by Relationship Kind; a change reuses these names under .xirang/changes/<name>/. Directory and file names carry no model semantics: every entry declares its own entity and identity, and loading locates entries by those, never by path.
  • Treat code paths, symbols, imports, and calls from CodeGraph or ACE/rg/read as current implementation evidence only; do not promote them to elements or relationships without declared model intent.
  • If the model is missing, report Semantic Model unavailable. If it is incomplete or unsupported, identify the root, identity, contract, or relationship gap.
  • A read-only exploration MAY degrade to available model and code evidence with the limitation disclosed. Workflows that compile or write semantics MUST stop when required model context is missing or incomplete; never treat a missing collection as complete and empty.

Read the full file on GitHub · 139 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. 1mo ago First seen · 139 lines · 57 tokens per session scan A 0a6fcacae43b

Subscribe to this mod's changes

xirang-reviewer is an agent published in the GitHub repository cp-yu/cc-switch-web (47 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 2,385 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-12.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

thermo-nuclear-code-quality-review-subagent

Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.

michael-denyer/pstack-claude · 68 tokens

review-obsidian-guidelines

Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.

uphy/obsidian-reminder · 63 tokens

karimo-implementer

Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.

opensesh/KARIMO · 49 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens