Borrowing it
Nothing to install: this file belongs to mengrru/Spherse. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mengrru/Spherse/main/.agents/skills/code-review/SKILL.mdgit 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/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.
<a href="https://agentmods.dev/skills/mengrru/spherse/code-review"><img src="https://agentmods.dev/badge/skills/mengrru/spherse/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00036 | $0.00838 |
| Opus 5.5 | $0.00014 | $0.00335 |
| Sonnet 5.5 | $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 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.
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.
- 1mo ago First seen · 57 lines · 36 tokens per session scan A be6458e90f2d
code-review is a skill published in the GitHub repository mengrru/Spherse (92 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 838 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
open-code-review-delegate
Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for deterministic engineering: file selection and rule resolution. Use when the host agent should drive the review with its own LLM capabilities.
md-audit
Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…
review
Comprehensive security and correctness audit. Use for review, deep review, thermo nuclear, or thermonuclear requests and branch or PR diff audits.
skill-creator
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory.
aster-config
Reference for aster.yaml, covering review models, analyzers, focus areas, include/exclude globs, minconfidence, and the permissions block that gates edits. Use when creating or editing aster.yaml, choosing hypothesis/verify models, enabling semgrep or ast-grep, or configuring edit permissions.