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 | $0.00041 | $0.00530 |
| Opus 5.5 | $0.00016 | $0.00212 |
| Sonnet 5.5 | $0.00008 | $0.00106 |
| Haiku 4.5 | $0.00004 | $0.00053 |
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 1mo 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:先定模式,再定角色
本项目默认单会话模式;多角色接力(制作人 / 实现者 / 验收员)是可选能力。
- 读
process/docs/HANDOFF.md开头的「当前模式」一行(模板预置单会话); 读不到、或与process/docs/handoff/下的实际内容不符,用提问卡片请用户定一次。 - 单会话:本会话不需要角色,直接按下面的单会话顺序读档。
- 多角色:再确定你的角色——由角色预设启动的,角色已由 persona 给定; 否则先用提问卡片请用户指定角色。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.
- 1mo ago Changed · +3 lines · +2 tokens per session 78ebcc9718f3
- 1mo 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 (11 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 530 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.
project-flow compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| project-flowfore-thought/deepseek-harness-project-collection-starter | Skill | 11 | 1mo ago | MIT | A | 41 | Claude Code, Codex |
| event-reviewreatcat/l123-harness | Skill | 3 | 2mo ago | MIT | A | 92 | Claude Code |
| tddreatcat/l123-harness | Skill | 3 | 2mo ago | MIT | A | 45 | Claude Code |
| write-a-skillreatcat/l123-harness | Skill | 3 | 2mo ago | MIT | A | 35 | Claude Code |
| agent-crdt-synchronizerruvnet/ruflo | Skill | 82k | today | MIT | A | 25 | Claude Code |
| agent-topology-optimizerruvnet/ruflo | Skill | 82k | today | MIT | A | 21 | Claude Code |
| flow-nexus-platformruvnet/ruflo | Skill | 82k | today | MIT | A | 24 | Claude Code |