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 EricCodeMonkey/magebyte-power --skill cross-verified-feature-developmentgit clone --depth 1 https://github.com/EricCodeMonkey/magebyte-powerWrote 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/ericcodemonkey/magebyte-power/cross-verified-feature-development)<a href="https://agentmods.dev/skills/ericcodemonkey/magebyte-power/cross-verified-feature-development"><img src="https://agentmods.dev/badge/skills/ericcodemonkey/magebyte-power/cross-verified-feature-development/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/ericcodemonkey/magebyte-power/cross-verified-feature-development"><img src="https://agentmods.dev/badge/skills/ericcodemonkey/magebyte-power/cross-verified-feature-development.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 | $0.00287 | $0.07899 |
| Opus 5.5 | $0.00115 | $0.03160 |
| Sonnet 5.5 | $0.00057 | $0.01580 |
| Haiku 4.5 | $0.00029 | $0.00790 |
Grade A, and why
cross-verified-feature-development 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 2mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cross-verified-feature-development — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Verified Feature Development
A structured workflow for high-stakes backend features. After implementation, it runs 4 independent verification passes to catch bugs that self-review and standard code review miss — particularly concurrency races, idempotency gaps, and cross-service contract breaks.
Prerequisites · 前置条件
本 skill 编排 Superpowers 生态中的子 skill 完成各阶段工作。
Install Superpowers（一次性）：
claude mcp add --transport http superpowers https://superpowers.anthropic.com/mcp
本 skill 依赖的子 skill：
| Phase | Skill | 用途 |
|---|---|---|
| 1 | superpowers:brainstorming |
需求分析 → 结构化 spec |
| 2 | superpowers:writing-plans |
spec → 可执行 task 清单 |
| 3 | superpowers:subagent-driven-development |
每个 task 独立 subagent 实施 |
| 4.1 | superpowers:systematic-debugging |
自查阶段的结构化调试框架 |
| 5 | superpowers:writing-plans + superpowers:subagent-driven-development |
修复迭代 |
没有 Superpowers 也能用（fallback）：
| Phase | Fallback 做法 |
|---|---|
| Phase 1 | 手动撰写 spec 文档，确保包含：问题陈述、技术方案、不变式清单、失败模式分析、风险表格 |
| Phase 2 | 手动拆 task 清单，每个 task 须有文件 + 行号 + 验证命令 |
| Phase 3 | 逐 task 实施，每个 task 完成后做 self-review 再进下一个 |
| Phase 4.1 | 按 references/cross-verification-techniques.md 中的 4.1 checklist 手动自查 |
| Phase 4.2–4.5 | 直接使用 references/cross-verification-techniques.md 里的 agent prompt 模板 dispatch subagent |
Overview · 概览
这是一套多轮交叉验证的严谨特性开发方法论，用于开发关键业务特性时最小化生产事故概率。
Core Insight · 核心洞察
单一视角的 review 有系统性盲点。即使最有经验的开发者也会：
- 被自己的设计思路"带偏"
- 默认某些字段语义是唯一的（实际可能多义）
- 假设"应该幂等"的操作真的幂等（实际不是）
- 看漏并发窗口
- 忘记更新文档导致设计文档与代码失联
独立视角产生的信号彼此独立。用 N 个互不知情的 reviewer 轮询一个特性，发现的 bug 集合接近是并集而不是重复。所以这个工作流的本质是：
设计 → 实施 → 多轮独立交叉验证 → 修复 → 谨慎简化 → 文档同步
Comparison with Standard Workflow · 与普通开发工作流的差异
| 环节 | 普通做法 | 本工作流 |
|---|---|---|
| 需求 | 口头沟通/简单 PRD | brainstorming 形成完整 spec |
| 实施计划 | 开发者脑内规划 | writing-plans 显式化成 task 清单 |
| 实施 | 一人连续写完 | subagent-driven-development，每个 task 独立 review |
| 验证 | 自测 + 一次 code review | 4 轮独立交叉验证（本 skill 的核心） |
| 修复 | 直接改 | 发现问题再走一轮 plan + execute |
| 简化/优化 | 直接删减代码 | 带怀疑的验证，发现陷阱勇敢回滚 |
| 文档 | 实施后遗忘 | 强制回填，记录 evolution log |
What ships with it
4 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.
- 2mo ago First seen · 491 lines · 287 tokens per session scan A 2581d86e29fb
cross-verified-feature-development is a skill published in the GitHub repository EricCodeMonkey/magebyte-power (2 stars, last pushed 6mo ago), licensed MIT. It adds 287 tokens to every session and 7,899 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…