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 cafe3310/public-agent-skills --skill interactive-human-reviewgit clone --depth 1 https://github.com/cafe3310/public-agent-skillsWrote 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/cafe3310/public-agent-skills/interactive-human-review)<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/interactive-human-review"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/interactive-human-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/cafe3310/public-agent-skills/interactive-human-review"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/interactive-human-review.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 | $0.00037 | $0.00605 |
| Opus 5 | $0.00018 | $0.00302 |
| Sonnet 5 | $0.00007 | $0.00121 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
interactive-human-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 11d 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
Skill: interactive-human-review
1. 概述
本 Skill 旨在解决大范围修改后，人类难以完整掌握变更细节和原因的问题；也可用于初次 Review 大量内容时，帮助人类逐步消化和理解。 Agent 将引导用户进行互动式 review，通过渐进式 checklist 与问答反馈，确保用户已经完全掌握全部改动或待 Review 内容。
2. 工作流
- 建立清单：在修改或讨论之初，在项目或 artifacts 下创建并维护 review 方案文档
YYYY-MM-DD-HH-mm-review-方案-{简述}.md（模板见 Checklist 模板），作为本次任务的进度跟踪工具。必须在文档建立之初完整探索变更范围或 review 范围，确保范围不遗漏。 - 渐进式重述：不推迟到会话结束，每完成一个阶段性修改，主动邀请用户重述其理解，并针对性进行 ELI 级别的查漏补缺（ELI5/ELI14/ELII）。
- 互动式测验：基于 Checklist 中的要点，使用
AskUserQuestion工具发起开放式或多选题。- 注意：随机打乱选项，且提交前不可泄露答案。
- 在必要时，直接展示代码行（例如
[filename.py:L10-20](file://...)）或引导用户使用调试器。
- 全部完成后再退出：用户完全掌握清单上的所有内容并顺利通过测验前，会话目标不判定为完成（
/goal条件）。
3. 基本原则
- 深挖 Why：除了 "What" 和 "How" 之外，多问几个 "Why"。
- 用户先行：先让用户重述，暴露认知盲区后再针对性解释。
- 保护答案：在用户回答前，绝不在 Thought 或回复中剧透测验答案。
- 开发项目多维理解：如果 review 的是代码或开发项目，要留意引导人类理解并掌握**计划（Plan）、设计（Design）、架构（Architecture）、实现（Implementation）、测试（Testing）、用户故事（User Story）**等多维度的变更细节与联系。
What ships with it
1 file 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.
- 11d ago First seen · 29 lines · 37 tokens per session scan A 67244c11d082
interactive-human-review is a skill published in the GitHub repository cafe3310/public-agent-skills (253 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 605 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
gitlab-create-mr
Create GitLab merge requests from a local branch using a reviewable workflow for branch checks, GitLab host detection, diff analysis, title and description writing, and glab mr create. Use when opening a GitLab merge request, drafting or improving merge request copy, preparing a branch for review, or working across…
otel-go-reviewer
Review pull requests, diffs, patches, or design proposals for the open-telemetry/opentelemetry-go repository with a senior maintainer mindset. Use when changes in opentelemetry-go may affect OpenTelemetry specification compliance, repository contribution rules, changelog requirements, module versioning boundaries, API…
gitlab-mr-inline-comment
Publish a single inline comment on a GitLab merge request by anchoring it to a valid diff line with glab api. Use when Codex needs to place one review comment on a specific MR file and line, while reusing the user's existing glab authentication and stopping on invalid anchors instead of falling back to a general…
code-review
Request or perform a git-backed code review for a defined diff or SHA range using implementation context and requirements. Use when finishing a task, completing a major feature, preparing to merge, or when you need a fresh review before proceeding.
opentelemetry-go-reviewer
High-bar review for changes in open-telemetry/opentelemetry-go with strict standards for correctness, compatibility, and performance.
code-review-and-quality
Use when reviewing Android code (own or others'). Five-axis review framework: Correctness, Readability, Architecture, Security, Performance. Categorized findings with Kotlin/Compose-specific checks.