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 fore-thought/deepseek-harness-project-collection-starter --skill project-flowgit clone --depth 1 https://github.com/fore-thought/deepseek-harness-project-collection-starterWrote 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/fore-thought/deepseek-harness-project-collection-starter/project-flow)<a href="https://agentmods.dev/skills/fore-thought/deepseek-harness-project-collection-starter/project-flow"><img src="https://agentmods.dev/badge/skills/fore-thought/deepseek-harness-project-collection-starter/project-flow/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/fore-thought/deepseek-harness-project-collection-starter/project-flow"><img src="https://agentmods.dev/badge/skills/fore-thought/deepseek-harness-project-collection-starter/project-flow.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 | $0.00039 | $0.00422 |
| Opus 5.5 | $0.00016 | $0.00169 |
| Sonnet 5 | $0.00008 | $0.00084 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
project-flow 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 8d 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
本项目的工作流程（project-flow）
第一件事：确定你的角色
本项目按角色分工，三个角色是 制作人 / 实现者 / 验收员。
- 若你由角色预设启动，角色已由 persona 给定，直接采用；
- 否则先用提问卡片请用户指定角色，再往下走。角色未定就不要动任何文件。
第二件事：按模式读档
单会话模式（默认）：
process/docs/HANDOFF.md- 根级
AGENTS.md的 TOP 规则 process/docs/work-log.md尾 10 行 +process/docs/decisions.md索引process/docs/plans/plan.md当前段门禁表
多角色模式：process/docs/HANDOFF.md 会写明处于多角色模式——它是静态路由，
真正的接续点在 process/docs/handoff/<你的角色>/index.md。读那里指出的最新一份交接文件，
再按上面的第 2–4 步读。
第三件事：只写你角色范围内的路径
完整角色表、写权范围、归属与越界规程、并行纪律都在组级只读文件：
../shared-standards/pipeline-and-roles.md
那是唯一真源，本技能不复制它的正文——照它执行即可。当前项目的具体单元与交接文件， 在各角色索引里。
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.
- 8d ago First seen · 36 lines · 39 tokens per session scan A 8a2d863d9d3c
project-flow is a skill published in the GitHub repository fore-thought/deepseek-harness-project-collection-starter (9 stars, last pushed 6d ago), licensed MIT. It adds 39 tokens to every session and 422 once invoked, about $0.0002 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 2026-09-18.
Other skills, from other repositories
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.
yao-board
Kanban board and task query expert. ALWAYS invoke this skill when the user asks about boards, tasks, task status, or project progress. Do not guess task state — use this skill first.
b3os-team-inbox
A team message-bus client for sending, receiving, and recalling messages between AI teammates. It also supports replying to a specific message thread and sending final reports to the team lead.
b3os-task-loop
A task-tracking work loop that keeps individual, scheduled, and waiting tasks moving until they are completed, blocked, or awaiting approval.
b3os-project-mgmt
A project-management and reporting guide that keeps instructions, defects, and follow-up items in a repository TODO.md file, while generating reports from that source. It also describes how task status and team handoffs are recorded.
board-pilot
Generic, board-driven implementation pipeline: polls a GitHub Project on a schedule, ARMS an item the moment a human drags it into the configured trigger column, then advances it one stage per tick — each stage a Bridge primitive (skill / workflow / agent / cmd) — and STOPS at a human-gated draft PR. The engine is…