dsh-code-review

Review guidance for pull requests in the DeepSeek-Harness repository, covering its project rules, defensive coding patterns, documentation standards, and required quality checks.

In plain words
What is it for?
Use it when reviewing a DeepSeek-Harness pull request to verify its exact base and head, inspect the right files, and prioritize broken behavior, security, and correctness.
Why use it?
It helps reviewers assess repository-specific risks that may not be visible from the diff alone, such as lifecycle, subprocess, asynchronous-state, and testing problems.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/whitelonng/dshcode/dsh-code-review
Any agent
npx skills add whitelonng/dshcode --skill dsh-code-review
Clone the repo
git clone --depth 1 https://github.com/whitelonng/dshcode

Made for: Claude Code, Codex.

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,648 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.00054 $0.01648
Opus 5 $0.00027 $0.00824
Sonnet 5 $0.00011 $0.00330
Haiku 4.5 $0.00005 $0.00165

Measured 2d ago against content hash 59df05ce442f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dsh-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 2d 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.

Origin

This is a copy

86% identical to dsh-code-review — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/dsh-code-review/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviewing a DeepSeek-Harness PR

This skill is guidance, not a complete checklist. Verify and fetch the PR's live base and exact head, then run pnpm --silent run change-scope --base <verified-base-ref> --head <verified-head-ref> before reading the diff and enough surrounding code to understand the design. The report identifies paths and dirty layers but does not replace semantic review. Re-establish the base and rerun it after a retarget or merge. Prioritize correctness, lifecycle, security, and broken required behavior over style; a short review with one substantiated blocker is better than a list of nits.

Sources of truth

Blocking requirements

  1. New prose receives semantic review. Use dsh-prose-standard to critically review every added or changed Markdown passage, JSDoc, comment, prompt, description, diagnostic, and visible string. Verify required coverage, accuracy, placement, and editorial quality against the owning code or behavior; automated checks do not establish those properties.
  2. Docs match the code. Config, defaults, errors, wire fields, events, and public behavior update the package README and JSDoc in the same diff. Comments state non-obvious contracts; flag implementation narration, test walkthroughs, review history, and duplicated rationale for deletion or a link to their one home.
  3. Core type docs match. Changes to spine or seam vocabulary update the appropriate subsystems page and any type-equiv entry. Internal types need no catalog entry.
  4. Registrations clean up. Verify each new registry contribution passes the disposal tests required by packages/AGENTS.md.
  5. Invariant companions are semantic. For every touched ./invariant, require an owner event-stream or mutable-data relationship at the point where that package can observe it; service or method presence, plugin metadata or effects, and fixed pure examples belong in type, load, or unit tests. Accept an empty installer when its package-specific reason establishes that no plausible runtime relationship exists; do not demand an invented check merely to eliminate emptiness (repository rule; package invariant rules).
  6. Required evidence exists. Verify the author ran the relevant local checks for the diff and that CI covers the exhaustive matrix; review the semantic gaps neither can detect.

Read the full file on GitHub · 50 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. 2d ago First seen · 50 lines · 54 tokens per session scan A 59df05ce442f

Subscribe to this mod's changes

dsh-code-review is a skill published in the GitHub repository whitelonng/dshcode (553 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 1,648 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to dsh-code-review, differing in 5 lines, and is treated as a copy.

Related

Other skills, from other repositories

visionary-cli

Analyze images with DeepSeek's vision model via the visionary-server CLI. Use this whenever the user provides an image, photo, screenshot, or document with images - run vision to look at it rather than guessing.

xlight/deepseek-visionary · 46 tokens

deepseek-harness

Use when building AI agent applications with a plugin-based architecture — Web UI, CLI, Python SDK, Cordis plugin system, multi-model orchestration. DeepSeek Harness (dsh): open-source agent harness by DeepSeek AI where everything is a plugin, powered by Cordis for spatiotemporal composability.

znlgis/opengis-skills · 68 tokens

deepseek-harness

Use this skill whenever the user wants to call DeepSeek V4-Pro / V4-Flash (or its legacy aliases deepseek-chat / deepseek-reasoner), or you see code that imports from openai import OpenAI with baseurl="https://api.deepseek.com". This skill teaches you the 10 protocol contract rules required to avoid the 16 documented…

HenryZ838978/deepseek-harness · 144 tokens

web-ui-motion

Build polished front-end UI together with a signature motion effect in a single self-contained HTML file, combining SVG.js / SVG filters and the Canvas 2D API. Use when the user asks to build a web page, landing page, dashboard, or component that has a special visual effect, animation, particle system, fluid/water…

creativedswork/dscode · 152 tokens

openspec-propose

Create a complete OpenSpec proposal with design, specs, prototype, and tasks. Use when the user wants a change ready for implementation.

creativedswork/dscode · 32 tokens

prototype-workflow

Generate and lifecycle-manage HTML prototypes for UI exploration and OpenSpec changes. Use when creating, validating, completing, or archiving a UI prototype.

creativedswork/dscode · 34 tokens