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/mengrru/spherse/code-reviewnpx skills add mengrru/Spherse --skill code-reviewgit clone --depth 1 https://github.com/mengrru/SpherseWrote 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/mengrru/spherse/code-review)<a href="https://agentmods.dev/skills/mengrru/spherse/code-review"><img src="https://agentmods.dev/badge/skills/mengrru/spherse/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 | $0.00036 | $0.00838 |
| Opus 5 | $0.00018 | $0.00419 |
| Sonnet 5 | $0.00007 | $0.00168 |
| Haiku 4.5 | $0.00004 | $0.00084 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Skill
Positioning
This skill guarantees the floor of a code review — discipline and repo-specific knowledge — and never the ceiling. It exists to make reviews reliable (no unverified claims, no missed repo red lines, consistent output), not to make them mechanical.
The perspectives and red lines below are minimum coverage, not a boundary. Findings outside them must be reported regardless of dimension. Never conclude "checklist complete ⇒ approved".
Dispatch template
The main agent loads this skill, then dispatches a review sub agent (research-only task) with:
- Scope: commit range or file list to review
- Context: design doc path if one exists (dev-flow step 2 output); otherwise the requirement summary
- Discipline + perspectives + red lines + output contract: inline the sections below into the dispatch prompt
- Report language: Chinese
Discipline rules
- Review-only: the sub agent researches and reports; it never modifies files
- Verify before claiming: every finding cites
file:lineevidence from actual code. Check the surrounding reality, not just the diff — most hard errors live outside the changed lines - Hunches are allowed, labeled: suspicions without evidence go to a separate "未验证疑点" section, explicitly marked as unverified
- No rubber-stamping: absence of findings must be stated as "抽查未发现", never as a guarantee
Perspectives (lenses, not steps)
- Design fidelity: implementation vs design doc — missing pieces, silent deviations, undocumented decisions
- Correctness: logic, edge cases, error paths, backward compatibility (esp. persisted-data migrations)
- Boundaries & security: access policy, path safety, contract usage, concurrency (see red lines)
- Test adequacy: contract tests for cross-layer seams (PM facade /
SessionPortmethods — consumer packages each need at least one that doesn't mock the tested method); affected-surface coverage for the change - Doc-sync triggers: surfaces whose docs need updating (report only — doc updates are handled by the doc-sync skill afterwards, not by the reviewer)
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.
- 4d ago First seen · 57 lines · 36 tokens per session scan A be6458e90f2d
code-review is a skill published in the GitHub repository mengrru/Spherse (61 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 838 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 2026-08-30.
Other skills, from other repositories
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
error-recovery
Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.
agentic-workflow-designer
Conversational skill that interviews users to design new agentic workflows.
security-review
How to review PRs for security — credentials, injection, workflow permissions, supply chain, git operation safety.
shogun-screenshot
スクリーンショットの取得・加工を行う。ローカルスクショから最新画像を取得、 PlaywrightでWebページをキャプチャ、画像のトリミング・リサイズ、機微情報を黒塗りマスキング。 記事執筆、レポート作成、UI確認、画像加工時に起動。 「スクショ」「スクリーンショット」「画面キャプチャ」「最新のスクショ」「画像加工」「トリミング」「マスク」「写メ」「写メ撮った」「スクショ撮った」で起動。 Do NOT use for: 画像生成（shogun-imagegenを使え）。.