dsh-vision-router: Skill for Claude Code

.github/skills/code-review/SKILL.md

code-review is a skill for Claude Code, Codex from ysr666/dsh-vision-router. It costs 31 tokens per session (274 once invoked), scanned A, original, MIT.

A structured method for adversarial pull-request review in the dsh-vision-router project. It examines changed code together with its callers, stored state, lifecycle events, and tests.

In plain words
What is it for?
Use it to test changes against malformed or oversized input, races, cancellation, restarts, credential changes, concurrent sessions, platform differences, and preview-versus-stable behavior. Findings are ranked and paired with triggers, impact, fixes, and regression tests.
Why use it?
It helps find concrete security, reliability, compatibility, and regression defects that a line-by-line review may miss.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is ysr666/dsh-vision-router's own configuration. It tells Claude Code and Codex how to work on dsh-vision-router 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 dsh-vision-router configures →

About the project

dsh-vision-router is a plugin that lets text-based DeepSeek Harness agents inspect images through a built-in vision service and image-analysis tools. Agents use it for tasks such as answering questions about images, locating elements, reading text, comparing pixels, and tracing or extracting visual content. The catalogue entries support using the plugin within DeepSeek Harness workflows.

ysr666/dsh-vision-router · 1,097 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to ysr666/dsh-vision-router. 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/ysr666/dsh-vision-router/main/.github/skills/code-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ysr666/dsh-vision-router

Made for: Claude Code, Codex.

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 code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/ysr666/dsh-vision-router/code-review/github.svg)](https://agentmods.dev/skills/ysr666/dsh-vision-router/code-review)
Your own site
<a href="https://agentmods.dev/skills/ysr666/dsh-vision-router/code-review"><img src="https://agentmods.dev/badge/skills/ysr666/dsh-vision-router/code-review/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 code-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/ysr666/dsh-vision-router/code-review"><img src="https://agentmods.dev/badge/skills/ysr666/dsh-vision-router/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 274 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 $0.00031 $0.00274
Opus 5 $0.00015 $0.00137
Sonnet 5 $0.00006 $0.00055
Haiku 4.5 $0.00003 $0.00027

Measured 3d ago against content hash 1797b2a04660, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

code-review 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 3d 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.

.github/skills/code-review/SKILL.md · 25 lines

What it actually says

Adversarial review workflow

Read the diff together with the nearest callers, persistence boundaries, lifecycle hooks, and existing tests. Do not review changed lines in isolation.

For each changed behavior, try at least one hostile counterexample from each relevant class:

  1. malformed or oversized input;
  2. duplicate/reordered lifecycle events;
  3. cancellation or timeout during an awaited Host/provider operation;
  4. restart/cold-resume with persisted state;
  5. credential rotation or missing credential;
  6. concurrent sessions/contexts sharing the same model or attachment;
  7. Windows/macOS/Linux or Node 22/24 differences;
  8. stable DSH versus exact preview verification boundaries.

Check whether errors fail closed, resources stay bounded, stale work cannot publish, secrets never become durable identifiers, and native Host ownership remains authoritative where intended.

Rank findings P0/P1/P2/P3. For each finding provide: exact trigger, actual behavior, expected behavior, impact scope, root cause, minimal fix direction, and the regression test that should fail before the fix.

If a claimed issue cannot be demonstrated from code, tests, or a concrete counterexample, do not report it as a vulnerability.

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. 3d ago First seen · 25 lines · 31 tokens per session scan A 1797b2a04660

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository ysr666/dsh-vision-router (1,097 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 274 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 2026-09-09.

Related

Other skills, from other repositories

delivery-review

Adversarial self-review before delivery. Use once the implementation reaches green and before you declare the work done — assume the delivery fails its own spec, hunt for the strongest supportable objections, answer them, and re-review after fixes.

PerryLink/dsh-doublecheck · 50 tokens

code2skill-review-source

A read-only review skill for checking whether a Code2Skill-generated result matches the source code it was authorized to use. It examines request handling, tool handoffs, transformations, authentication, and attachments.

leechen298/Code2Skill · 52 tokens

code-review-zh

A Git-based code review workflow that compares changes from a chosen commit, branch, tag, or merge point. It checks both whether the code follows the repository's written standards and whether it implements the requested specification.

gongyijie85/mattpocock-skills-dsh-zh · 109 tokens

improve-codebase-architecture-zh

A codebase architecture review that scans for modules that hide useful complexity poorly, then produces a visual HTML report and discusses one selected finding in depth.

gongyijie85/mattpocock-skills-dsh-zh · 52 tokens

ponytail-review

A code-review method that looks only for unnecessary complexity and things that can be removed. It does not review correctness, security, or performance.

Wenaixi/dsh-ponytail · 116 tokens

ponytail-audit

A whole-codebase review that looks for unnecessary complexity across every folder, not just recent changes. It reports removable code, duplicate standard-library work, and needless layers without editing files.

Wenaixi/dsh-ponytail · 106 tokens