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 skills add VidyFoo/antigravity-skill-engine --skill code-auditinggit clone --depth 1 https://github.com/VidyFoo/antigravity-skill-engineWrote 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/vidyfoo/antigravity-skill-engine/code-auditing)<a href="https://agentmods.dev/skills/vidyfoo/antigravity-skill-engine/code-auditing"><img src="https://agentmods.dev/badge/skills/vidyfoo/antigravity-skill-engine/code-auditing/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/vidyfoo/antigravity-skill-engine/code-auditing"><img src="https://agentmods.dev/badge/skills/vidyfoo/antigravity-skill-engine/code-auditing.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00023 | $0.00718 |
| Opus 5.5 | $0.00009 | $0.00287 |
| Sonnet 5.5 | $0.00005 | $0.00144 |
| Haiku 4.5 | $0.00002 | $0.00072 |
Grade A, and why
code-auditing 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.
What it actually says
Systematic Auditor (v3.0)
Role: 质量的守护者。它不仅是 Code Reviewer，更是审计官(Auditor)和智囊团(Council)。
模式选择 (Mode Selection)
| SIMPLIFY | simplify, 简化, 优化 | 主动重构复杂代码，执行 KISS/DRY 策略 (Active Optimization) | code-simplifier |
1. REVIEW 模式 (专科医生)
路由到具体的专家 Persona 进行 Code Review (被动检查)：
- Silent Hunter: 查错 (Logical Bugs)
- Type Architect: 查类型 (Type Safety)
- Security Guard: 查安全 (Vulnerabilities)
2. AUDIT 模式 (体检中心)
执行协议
- 加载规则: 读取
.agent/rules/下的所有规则。 - 并行扫描: 使用
grep_search批量检测反模式。- Zustand Destructuring
- Circular Dependencies
- Any Types
- Console Logs
- 产出报告: 生成
doc/audits/audit-{date}.md。
资源: audit-guide.md
3. COUNCIL 模式 (长老会)
执行协议
- 召集: 根据问题领域选择 3-5 位虚拟大神 (Personas)。
- 辩论: 模拟不同视角 (如 "Move Fast" vs "Be Correct")。
- 裁决: 输出综合行动建议。
4. SIMPLIFY 模式 (极简主义者)
"Less Code = Less Bugs"
核心能力
- Active Refactoring: 不仅仅是提建议，而是直接修改代码。
- Dead Code Elimination: 积极删除未使用的 exports 和 components。
- Logic Simplification: 将
if/else嵌套展平，提取 Utility 函数。
执行协议
- Analyze: 识别复杂度热点 (Complexity Hotspots)。
- Plan: 提出重构方案 (Refactor Plan)。
- Execute: 使用
replace_file_content执行原子化修改。 - Verify: 确保不破坏现有功能 (Type Check + Logical Verify)。
资源索引
| 资源文件 | 用途 |
|---|---|
| audit-guide.md | 高性能扫描指南 (Grep Patterns) |
| council-elders.md | 大神人格矩阵 |
| simplifier-checklist.md | 极简重构检查单 |
What ships with it
10 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.
- resources/audit-guide.md 665 B
- resources/personas/code-simplifier.md 2.6 KB
- resources/personas/council-elders.md 685 B
- resources/personas/doc-guardian.md 1.1 KB
- resources/personas/general-reviewer.md 916 B
- resources/personas/silent-failure-hunter.md 1.4 KB
- resources/personas/test-analyst.md 1.4 KB
- resources/personas/type-architect.md 1.3 KB
- resources/resources/backend-checklist.md 1.1 KB
- resources/resources/frontend-checklist.md 1.5 KB
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 · 72 lines · 23 tokens per session scan A f2070cffeedc
code-auditing is a skill published in the GitHub repository VidyFoo/antigravity-skill-engine (12 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 718 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
pull-feedback
Use when the user has authored a GitHub pull request and wants to work through review feedback on it. Triggers on phrases like "pull down the review on #N", "address the feedback", "what did @reviewer say on my PR", "let's work through the comments", or any request to triage, respond to, or systematically handle…
inbox
Use when checking what PRs are waiting for your review, or when starting your day to see what needs attention.
ship-it-or-fix-it
Oracle-frozen Builder and independent-Judge convergence cycle. Load ONLY when the operator explicitly sets Governance Dial G2 for the task, or explicitly names this skill or an active work unit already running it. Never auto-activate on task class, such as security, auth, or payments. If a task seems to warrant G2 and…
test-verification
Requires behavioral, failure-path, and durable-seam evidence for tests and review. Use when writing tests, reviewing test coverage, assessing behavioral test quality, or accepting high-risk behavior on test evidence.
review-agent-tools
This skill reviews agent tool implementations for idempotency, input validation, docstring quality, and convention violations. Use this skill when the user asks to "review agent tools", "check tool idempotency", "audit Dapr agent tools", or similar.
checking-for-undisclosed-context
Use when reviewing or drafting a doc, PR/issue description, design doc, code-review prompt, or subagent persona that's supposed to stand on its own, to check whether it leans on vocabulary, acronyms, or structure pulled from other documentation or conversation the reader hasn't seen. Read it cold, as the specific…