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 hujianbest/harness-flow --skill hf-reviewgit clone --depth 1 https://github.com/hujianbest/harness-flowWrote 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/hujianbest/harness-flow/hf-review)<a href="https://agentmods.dev/skills/hujianbest/harness-flow/hf-review"><img src="https://agentmods.dev/badge/skills/hujianbest/harness-flow/hf-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/hujianbest/harness-flow/hf-review"><img src="https://agentmods.dev/badge/skills/hujianbest/harness-flow/hf-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 17 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 47 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00092 | $0.00952 |
| Opus 5 | $0.00046 | $0.00476 |
| Sonnet 5 | $0.00018 | $0.00190 |
| Haiku 4.5 | $0.00009 | $0.00095 |
Grade A, and why
hf-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 12d 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
hf-review（独立评审）
评审产出是落盘结论,对抗作者自我偏好。独立性是硬约束。
独立性
| 方式 | 效力 |
|---|---|
| subagent / 全新会话 | 完整 |
| 主会话冷读 | 降级:结论只能「待独立复核」或「需修改」,不得「通过」 |
auto 模式下降级评审是硬停点；确认行禁止写入 auto-approved。
评审对象
| 对象 | 检查清单 | 记录 |
|---|---|---|
product/architecture.md |
references/product-architecture-checklist.md |
product/reviews/product-architecture-review.md |
spec.md |
references/requirements-checklist.md |
reviews/spec-review.md |
特性 architecture.md |
references/design-checklist.md |
reviews/architecture-review.md |
| 实现代码 | references/code-checklist.md（Standards + Spec 双轴） |
reviews/code-review.md |
有 UI 时加载 hf-ui-design，把其检查项并入本轮。
流程
- 冷读被评工件与上游（评产品架构时读 CONTEXT/ADR；评特性架构时读规格与
product/architecture.md；评代码时读取规格/架构/任务票）。 - 代码门见下节。评审者自己运行测试、自己读取
git diff，不采信作者叙述。 - 发现项格式：
- [严重|一般|建议] <位置>: <问题> → <建议>。存在严重/一般问题 →需修改；仅有建议时可判定为通过；降级评审不得判定为通过。 - 落盘:
# <对象> 评审 (第 N 轮)
- 日期: YYYY-MM-DD
- 评审方式: subagent | 独立会话 | 主会话降级
- 结论: 通过 | 需修改 | 待独立复核
## 发现项
代码评审额外保留 ## Standards 与 ## Spec 两节，发现项分轴列出，不要合并重排。
需修改→ 返回作者阶段，只修复发现项后再复审。通过→interactive等待用户确认后写- 用户确认: <日期>；auto下非降级评审写auto-approved <日期>。确认必须位于结论行之后。
代码门（Standards + Spec）
对固定点与 HEAD 的差异做双轴评审（宜并行 subagent，避免互相污染）：
- Standards——是否符合本仓库已记录的编码标准，外加
references/code-smells.md异味基线（仓库规则优先；异味均为判断项）。 - Spec——是否忠实实现
features/<id>/spec.md/ 架构 / 任务票；缺失规格则跳过 Spec 轴并注明no spec available。
固定点由用户指定（提交、分支、标签、main 等）；未指定则询问。先确认 git rev-parse 有效且 git diff <fixed-point>...HEAD 非空。
一项变更可通过一轴而未通过另一轴（代码规范但做错需求，或需求对但违反约定）。分别报告，防止一轴掩盖另一轴。
红线
- 评审者顺手改被评对象;用作者记忆开脱;无具体位置的空泛结论;混合「通过但是…」。
What ships with it
5 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.
- 12d ago First seen · 63 lines · 92 tokens per session scan A 53e45d2ddddb
hf-review is a skill published in the GitHub repository hujianbest/harness-flow (53 stars, last pushed 11d ago), licensed MIT. It adds 92 tokens to every session and 952 once invoked, about $0.0005 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
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…