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/vectorpeak/vectorpeak-agent-skills/code-comments-vpnpx skills add VectorPeak/vectorpeak-agent-skills --skill code-comments-vpgit clone --depth 1 https://github.com/VectorPeak/vectorpeak-agent-skillsWhat 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 | $0.00115 | $0.01302 |
| Opus 5 | $0.00057 | $0.00651 |
| Sonnet 5 | $0.00023 | $0.00260 |
| Haiku 4.5 | $0.00012 | $0.00130 |
Grade A, and why
code-comments-vp 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.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Comments VP
Goal
Write maintainable comments that explain responsibility, execution flow, boundaries, side effects, fallback behavior, and design reasons.
Golden rule:
优先解释“为什么这样写”和“这段代码在链路中承担什么责任”,少解释“这行代码语法上做了什么”。
Mode Selection
Choose one mode before editing:
- coarse: Add or improve comments for a file, module, class, or function. This is the default.
- fine: Add detailed block comments because the user asks for细粒度/逐段/逐行 comments, or the code contains complex branching, async/concurrency, cache, fallback, state mutation, external calls, security checks, performance-sensitive logic, or business rule priority.
- review: Review whether comments are sufficient. Lead with findings and suggestions before changing anything.
- rewrite: Existing comments are inaccurate, noisy, inconsistent, or too shallow. Preserve correct meaning and rewrite in this style.
- style-transfer: The user points to an example file. First extract the comment style, then apply it to the target code.
Default Style
Default to coarse-grained comments. Prefer module docstrings, class docstrings, and function docstrings before inline comments.
Use Chinese comments by default when the user uses Chinese or the surrounding project comments are Chinese.
Use these section labels when useful:
执行流程:参数:返回:Yields:异常:说明:字段说明:规则说明:兜底策略:
Read references/comment-patterns.md when adding or rewriting more than one docstring, when the user asks for a reusable style, or when fallback/import-level comments are involved.
Coarse-Grained Template
Use this module docstring for most Python files:
"""模块职责一句话。
说明这个文件处在哪一层、接收什么输入、调用哪些下游能力、产出什么结果。
如果是 API / service / pipeline / adapter / config 文件,说明它的边界职责。
"""
Use this function docstring for important functions:
def some_function(...):
"""一句话说明这个函数在业务链路中的作用。
执行流程:
1. ...
2. ...
3. ...
参数:
xxx: 来源、含义、影响范围。
返回:
xxx: 返回内容和关键字段含义。
异常:
xxx: 什么时候抛出,调用方应如何理解。
"""
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 167 lines · 115 tokens per session scan A b113a39bbf9c
code-comments-vp is a skill published in the GitHub repository VectorPeak/vectorpeak-agent-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 115 tokens to every session and 1,302 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
obsidian-markdown
Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.
wiki-lint
Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…
mermaid-visualizer
Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.
research-mode
Anti-hallucination research mode. Toggle on to enforce citation requirements, source grounding, and "I don't know" behavior. Toggle off for creative work.
council
Multi-persona debate for founder decisions. 4 personas argue a topic across structured rounds.
mstar-conventions
Morning Star (启明星) harness 计划目录约定 —— {HARNESSDIR} / {PLANDIR} / {SDDDIR} / {ITERATIONDIR} / {KNOWLEDGEDIR} / {SPECSDIR} / {WORKFLOWDIR} / {PROJECTDIR} 发现与初始化(默认 .mstar/,兼容 .agents/)、docs 与 harness 子树边界、review bundle、未启用 plan 时的工作方式、Spec 集成分支与多 Plan 实现分支(显式 base / merge 靶 / PR target)、Morning Star plan-writing path…