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.
npx agentmods add skills/znlgis/my-opencode-deepseek-config/code-reviewnpx skills add znlgis/my-opencode-deepseek-config --skill code-reviewgit clone --depth 1 https://github.com/znlgis/my-opencode-deepseek-configWrote 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.
[](https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/code-review)<a href="https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/code-review"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/code-review.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00075 | $0.01765 |
| Opus 5 | $0.00037 | $0.00882 |
| Sonnet 5 | $0.00015 | $0.00353 |
| Haiku 4.5 | $0.00007 | $0.00177 |
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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Overview
A single-pass review: one pass covers all dimensions, depth scales to effective
size. Pair with security-review only when the diff touches a trust boundary.
Scope by effective size, not raw lines
Establish the change set before reading code:
- Branch vs base:
git diff --stat main...HEAD(or the stated base) - PR: use the
gh-cliskill (gh pr diff <n> --patch,gh pr view <n>) - Explicit files: just those paths
Weight each changed file by category — a 2000-line lockfile diff is not a 2000-line review. Sum the effective logic lines:
| File category | Weight | Examples |
|---|---|---|
| generated / mechanical | 0× | lockfiles, *.pb.go, snapshots, @generated, import-only reshuffles |
| data / config | 0.25× | .json, .yaml, .toml, .tf, fixtures |
| tests | 0.5× | *_test.*, *.spec.*, __tests__/ |
| logic | 1× | everything else (source code) |
Pick the path from effective size and stakes:
| Condition | Path | Behavior |
|---|---|---|
| ≤ 8 logic files and ≤ 300 effective lines | Abbreviated (default) | Single focused pass over the diff and its immediate callers. Report inline. |
| larger | Full | Walk each dimension deliberately. |
High-stakes override — route Full regardless of size when any changed
logic/config file matches: auth|authz|migration|schema|lock|concurr|public api| wire contract|serializ. A hit upgrades the depth; no hit keeps the default.
Abbreviated is the default — it costs ~an order of magnitude fewer tokens. State which path you took, the effective size, and any stakes trigger in one line.
Scope constraint: report only findings attributable to this diff. Nothing outside the blast radius — not pre-existing unchanged code, not unrelated files. ADRs and other historical decision documents are records, not living specs: do not flag them stale.
Large-diff two-axis split
Default is the single pass above. Only when the effective diff is large (>~500 effective lines), split into two parallel axes and merge into one report — never a consensus loop:
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.
- yesterday Changed · -1 lines ce3b1f9ebeb7
- 5d ago First seen · 169 lines · 75 tokens per session scan A 508b07f806d0
code-review is a skill published in the GitHub repository znlgis/my-opencode-deepseek-config (57 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 1,765 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
image-generator
Generate or edit images from text and local files, image URLs, or data URLs through image API. Use when the user asks to create an image, generate from one or more reference images, combine styles or elements across references, or edit a marked region while blending the result into the original scene.
weibo-poster
微博内容创作 - 140字优化、话题热搜、@提及策略、配图描述、发布时机.
excel-helper
Excel 表格助手 - 公式编写、数据透视表、图表可视化、宏自动化、数据清洗.
code-mate-antigravity
Runs Antigravity CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Antigravity CLI or compare its result with another coding agent.
dsh-doc-site-sync
Use when publishing, updating, moving, or removing DeepSeek Harness documentation website pages; editing website/docs.ts mappings or navigation; diagnosing a page missing from the VitePress site; fixing projected documentation links; or running the docs:dev, docs:check, and doc-sync workflow after website-content…
code-mate-openclaw
Runs a local OpenClaw agent non-interactively and returns its structured response. Use when the user asks to delegate a bounded task to the OpenClaw main agent.