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-workflowgit 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-workflow)<a href="https://agentmods.dev/skills/hujianbest/harness-flow/hf-workflow"><img src="https://agentmods.dev/badge/skills/hujianbest/harness-flow/hf-workflow/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-workflow"><img src="https://agentmods.dev/badge/skills/hujianbest/harness-flow/hf-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 54 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 | $0.00133 | $0.01083 |
| Opus 5 | $0.00067 | $0.00541 |
| Sonnet 5 | $0.00027 | $0.00217 |
| Haiku 4.5 | $0.00013 | $0.00108 |
Grade A, and why
hf-workflow 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 6d 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
HarnessFlow 主工作流
主链内容对齐 Matt Pocock 技能(MIT,已获授权复制),外壳保留进度落盘与 auto;并含产品级架构阶段。
hf-ui-design 内置设计层:先定美学方向(ui-ux-pro-max + frontend-design)→ taste 校准 → DESIGN.md → 截图评审。
主链
hf-workflow
→ hf-grill-with-docs
→ hf-to-product-architecture ── hf-review(产品架构) ──►
→ hf-to-spec ── hf-review(规格) ──►
→ hf-to-architecture ── hf-review(架构) ──►
→ hf-to-tickets
→ hf-implement ── hf-review(含代码门) ──►
→ hf-ship
探索旁路:特性 模式: 探索 → 写 conclusion.md 收尾,不应进入 ship,禁止直接晋升探索产物。
存量热修可只建 product/architecture.md(仅架构地图),不强制完整产品层。规格与任务票默认落在 features/<id>/。
进入规则
- 新会话读各特性/
product的progress.md与相关工件恢复状态,不靠聊天记忆。 - 到达阶段时只读该阶段
SKILL.md;有 UI 时另加载hf-ui-design。不预读全链。 - 有
CONTEXT.md/product/architecture.md/ 特性architecture.md时先读地图再读相关代码,禁止每特性全库扫描。 - 绿地首次落盘见
references/product-layer-templates.md(由hf-grill-with-docs创建)。
progress.md
特性:
# 进度
- 特性: <NNN>-<slug>
- 当前阶段: grill-with-docs | to-spec | to-architecture | to-tickets | implement | code-review | ship | close | done
- 执行模式: interactive | auto
- 已加载: <hf-ui-design 或无>
- 下一步: <一句话>
产品层另用 product/progress.md(阶段含 to-product-architecture | ready)。
执行模式
interactive(默认):规格/架构/代码评审通过后以及演示验收时等待用户确认。auto:用户明确要求自动执行时启用。评审通过即可推进,确认行写auto-approved <日期>。底线:实现与评审使用 subagent;降级评审在auto下硬停;替用户作出的选择写入product/assumptions.md;演示可先记为auto-approved,下次交互必须主动呈上。
硬性规则
- 评审结论为「需修改」时返回作者阶段,只修复发现项。
hf-implement任务/票由 subagent 执行;主会话只编排。- 作者/评审分离见
hf-review(代码门为其中的 Standards + Spec 双轴)。 - 欠定不静默填补 → 假设台账。
- 用户可感知特性进入
ship前,宜将演示验收结果落盘。 - 探索产物禁止直接晋升。
- 用户若要求跳过评审等纪律,在
progress.md记录豁免后再继续。
UI
特性含页面/组件/可视交互时,在 to-spec、implement、代码评审加载 hf-ui-design。
设计层要求:
- 绿地项目缺
DESIGN.md时,由hf-ui-design在 to-spec 阶段创建 - UI 实现与评审必须走真实渲染 + 截图评审闭环(详见
hf-ui-design)
元技能(按需)
hf-grilling、hf-domain-modeling、hf-tdd、hf-codebase-design、hf-ui-design。
What ships with it
2 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.
- 6d ago Changed · +7 lines · +18 tokens per session b2c70502614f
- 10d ago First seen · 71 lines · 115 tokens per session scan A b81f6cc05531
hf-workflow is a skill published in the GitHub repository hujianbest/harness-flow (53 stars, last pushed 9d ago), licensed MIT. It adds 133 tokens to every session and 1,083 once invoked, about $0.0007 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.