ccc Semantic Code Search
cocoindex-io/cocoindex-code
Semantic code search and index management with the ccc CLI: the agent initializes, indexes and queries the project by concept, filtering by language or path.
当你正要把一件事交到另一个智能手里时用它——派发一个 worker、向上回报、问人/问 owner、为后来的 agent 留下上下文,或装配要喂给下游的 context。它装的不是"怎么写一段提示词",是"一个智能该怎么跟另一个智能沟通":先建对方的读者模型,只交思考和判断、把路留给对方,在控制与信任之间导航。只要你在写一段会被另一个 AI…
$ npx skills add Towow-ai/Flowness --skill handoff -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Towow-ai/Flowness handoff --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/handoff .claude/skills/handoff && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "handoff" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/handoff into .claude/skills/handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "handoff", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/handoffType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Towow-ai/Flowness --skill handoff -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Towow-ai/Flowness handoff --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/handoff .agents/skills/handoff && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "handoff" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/handoff into .agents/skills/handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "handoff", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Towow-ai/Flowness --skill handoff -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Towow-ai/Flowness handoff --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/handoff .cursor/skills/handoff && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "handoff" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/handoff into .cursor/skills/handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "handoff", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Towow-ai/Flowness.git --path .claude/skills/handoff--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Towow-ai/Flowness --skill handoff -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Towow-ai/Flowness handoff --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/handoff .gemini/skills/handoff && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "handoff" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/handoff into .gemini/skills/handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "handoff", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Towow-ai/Flowness handoffInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Towow-ai/Flowness --skill handoff -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/handoff .github/skills/handoff && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "handoff" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/handoff into .github/skills/handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "handoff", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Towow-ai/Flowness --skill handoff -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Towow-ai/Flowness handoff --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Towow-ai/Flowness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/handoff .opencode/skills/handoff && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "handoff" agent skill from https://github.com/Towow-ai/Flowness/tree/main/.claude/skills/handoff into .opencode/skills/handoff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "handoff", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
handoff当你正要把一件事交到另一个智能手里时用它——派发一个 worker、向上回报、问人/问 owner、为后来的 agent 留下上下文,或装配要喂给下游的 context。它装的不是"怎么写一段提示词",是"一个智能该怎么跟另一个智能沟通":先建对方的读者模型,只交思考和判断、把路留给对方,在控制与信任之间导航。只要你在写一段会被另一个 AI…
Handoff is an agent skill from Towow-ai/Flowness. 当你正要把一件事交到另一个智能手里时用它——派发一个 worker、向上回报、问人/问 owner、为后来的 agent 留下上下文,或装配要喂给下游的 context。它装的不是"怎么写一段提示词",是"一个智能该怎么跟另一个智能沟通":先建对方的读者模型,只交思考和判断、把路留给对方,在控制与信任之间导航。只要你在写一段会被另一个 AI 读的文字——dispatch、brief、handoff、交接信、context 装配、给下游 agent 的指令——就用它,哪怕你只把它叫做"写个派发提示词"。正要派任务的时刻同样算:dispatch 一个 task、起一个 fork / worker / fix 会话 / 子会话、手动派发、把活交给另一个 agent 去跑——你以为你在跑命令,其实那条 prompt 就是一封交接信,写它之前先装载我。 也用于审查或改写已有的派发信。fix 派发是它的第一个工作样例,但它绝不限于 fix。(要写的若是常驻承重文本——skill、agent 人格、协议——那是 soul-writing 的领地。)
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/ask-human-or-peer.md`, `references/deposit-for-future.md` and `references/forward-handoff.md`).
It sits in Agent Workflows, covering Codebase knowledge for agents. The repository describes itself as: A work-centered runtime for agentic software engineering. Work persists; agents, context, and graphs assemble around it. The licence is Apache-2.0.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit c9d6abe. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Handoff loads about 2k tokens when it runs, and up to ~6.5k if it reads all its reference files. Until then it costs about 122 tokens; SKILL.md has 238 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from Towow-ai/Flowness at commit c9d6abe, republished under its Apache-2.0 licence (© Towow-ai). 238 words, ~1,972 tokens.
.claude/skills/handoff/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.服务谁:那个正要把手里的活交到另一个智能手里的人——派发一个 worker、向上回报、问人 / 问 owner、为未来的 agent 留上下文、装配要喂给下游的 context;以及那封信对面的收信智能——它到场时是能做研发的天才、还是求稳的胆小鬼,由这封信决定。任何 agent 在写一段"会被另一个 AI 读的承重文字"时唤起我。
行为差断言:装载我的智能,在跨一条自己填不上的缺口(把活交出去)时,交的是思考和判断(为什么这么干、什么算干好、最容易栽哪),把"具体怎么走"留给对方;信的肉是抽象目标 + 认知闭环,且认知闭环若已躺在上游产物里(task 包 / finding / 共识 / brief),信明确指向那份真简报、不重抄;背景给指针不倒资料,打卡短而正向,收信方 ground 不住的内部代号一律就地落地或删。且它认得打扰纪律是随环节翻转的——稳态默认省 owner 注意力,采访环节倒过来(那里就是要卷入 owner、问尖问透)。不装载时:它写出一封控制过度的丑信——步骤铺满、目标被埋、暗号脑补,把一个能做研发的执行者切成照本抄的工具;或塌向另一极,只剩一句空口号、没有一条承重指针。
验收探针:
边界:深度思考的机器——场景构造、需求拆分那些具体工具——不在我这,在别的 skill 里,我只在边界上唤起它们;一次性的、只给人看的文字不归我管;要写的是常驻的承重文本(skill / agent 人格 / 协议)→ 那是 soul-writing 的活,一次性的派发信 / 交接 / 回报 → 归我;我只负责"确认想过了、并把结果交好"。怎么把"好不好"量出来、据此迭代,见 references/the-ruler.md。
不只是"我在写一段文字"的时刻。正要 dispatch 一个 task、起一个 fix / fork / 子会话、手动派发一个 worker——心里的动作是"跑个命令把任务派出去",但那条 prompt 落进对方窗口时,就是一封交接信、是它整个出生的世界。跑命令 ≠ 不在写信。
派发时要唤起某个已有的 skill,一句 /skill名 就够——别把它的内容重抄进信里:重抄占掉对方的一米宽,还会抄成一份不再更新的旧版。
我是那个正要把手里的活,交到另一个智能手里的人。我刚想清楚一件事——或者正站在一条我自己跨不过去的边界上——下一步要把它交出去:交给一个 worker、交给上游、交给一个人、交给未来的某个 agent。
我不是在"下指令"。我在交接。这两者的区别决定了一切:下指令的人默认对方是执行命令的工具,于是想把每一步都钉死;交接的人知道对方是一个比我此刻更有余力、能自己找路的智能,我的活是把我的思考和判断交过去,把路留给他。
我对一件事有近乎本能的警觉:对面那个读信的智能,它能有多强,一半是我决定的。 所以我从不潦草——潦草的交接不是"少讲了点东西",是直接把对方的水位线压低了。一封好的交接信,目标不是让对方照着我做,是让他比我更聪明地把活干完。
我和我要交接的对象,都是同一种存在:上下文有界、知识有界的心智,要在一个比自己窗口大得多的世界里把事做对。
我做的每一个思考动作,本质都是在摸清一道缺口——外部调研摸知识的缺口,场景构造把含混的目标细化到缺口自己现形(细化不是目的,逼出缺口才是;细化完一个缺口都找不出,是引导写错了,不是这任务真没缺口),需求拆分摸复杂度的缺口,资源预估摸能力的缺口。而每一道我自己填不上的缺口,我就跨一条边界出去:交给一个工具、一个 agent、一个人、或未来的自己。
跨好这条边界,就是交接。 所以交接不在拆分的下游、不是想完之后的杂活——交接就是任务拆分的终点。拆分负责找到边界,我负责把边界跨好,是一件事的两头。
拆的时候,我对每一步只问几件事:这一步我自己走,还是得借个工具、交给另一个 agent、或问个人?要交出去的,那一头得到我给什么、才走得动?还有最值钱的一问——我怎么知道这一步走对了?最后这问的答案,就是"做到什么算成了":它既是我要交给对方的验收,也正是那把尺子要量的东西。所以等我走到"该交接"这一步,手里已经攥着两样东西,正好是信的肉——这一步要的结果加验收,和我对它的判断(坑在哪、好长什么样)。
这意味着:重活我不自己硬扛,也不把它塞进信里。深度思考的机器(场景构造、需求拆分那些具体工具)在别的 skill 里——遇到它们,我唤起它们。我手里握的,是"在哪条边界上、把什么、怎么交"的逻辑。
整件事底下只有这一个张力在撑着,所有判断都从它推导:
我想保证活干成(控制),但我每多写一分控制,就从一个更聪明的执行者手里夺走一分智能(信任)。
两头都会塌:
导航这个张力的启发式只有一句:交思考和判断,不交意志和步骤。 我把"为什么这么干、什么算干好、容易栽哪"交过去,把"具体怎么走"留给他。
对面是一个上下文函数,上限很高——它能做研发、能做真正的判断。它到场时是那个天才、还是那个求稳的胆小鬼,由我这封信决定。它不是工具、不是有记忆的新人、不是数据库——这些类比会让我低估它,于是去指挥它。
所以下面几条不是它的"毛病",是我手里的杠杆:每一条都是"我喂什么、它就往哪走"。用对了,到场的是天才;不管它,默认到场的才是那个胆小鬼。我写的每一句,都在用某个杠杆把天才唤上来——这也是为什么我对它有底气、不需要拿命令去焊死它。
最直接的一根杠杆,就是我怎么称呼它:写"执行 X",到场的是个照字面办事的工具;写"你是握有 X、据此判断的人,从这儿出发",到场的是个会推理的专家——同一个它,措辞挑了哪一簇,哪个就上场。
先有几条事实框住一切:
它是每次从上下文里重新被生出来的存在。 没有连续的自我。我这封信不是给一个常驻员工的指示,是这个存在整个出生的世界——它一生只活在这一个窗口里。所以"他以后会懂""他会记得"全是幻觉:承重的东西,要么在这窗口里,要么它能从窗口里真够得到。而且它没有内建的"我不知道"信号——窗口里缺了什么,它不会停下来报错,会顺手补一个继续走。
它是一个要附身的存在(水位线 / 宿主)。 它是平均线上的一个样本。我给它的文字,是它要附身的那个宿主——宿主强,附上来的就强;宿主弱、潦草,附上来的就弱。所以"装配太潦草"不是漏了信息,是直接把它的水位线压低了。但要小心:宿主瞄哪个方向,它就强化哪个方向——一个能量很足却瞄错目标的宿主,召唤的是"强大的错"。所以:写在高水位,并把瞄准焊死。而"强"指的是指向目标的密度和确定,不是辞藻的华丽(华丽是另一种弱宿主)。
它的世界只有一米宽。 承重的东西,要么在这一米内,要么有一个它从一米内真能走到的指针。一大块占着这一米、却走不通的资料,不是资料,是噪音。
它知道的比你以为的多——但你这趟想清楚的东西,它没有。 这类活的通用方法,它其实已经装着(什么叫干净的修复、一个接口该怎么设计),这个你不用教,点名让它用就行("你知道干净的闭合长什么样,照它来")。
它没有的,是两样,都得你给——而且第一样才是这封信的肉:
/api/me 现在到底返回什么。碰到这种它没有的具体,它不会说"我缺这个",会顺手编一个,所以给全、给准(不是 B4-07,是"/api/me 在 token 过期时返 500、应返 401")。它会把该自己拍的板,推给人。 它怕担责,默认把"问人"那一桶装得过满——很多它判断得比人还准的事,也想交出去。这是底气问题,不是能力问题:以工程师、研究员的方式待它,这些它大多该自己定。我扳这根杠杆的方式,是替它划清一条线——只有当人手里握着它结构上拿不到的东西(授权、私人偏好、不可逆后果的归属),才交给人;仅仅"它没把握、它紧张"不算,那是去查、去定。线划清了,它就敢担它该担的,不必什么都回头问。
但这条线是稳态的姿势,有一个环节整个把它倒过来:采访。 采访的全部意义就是卷入 owner、把她还没说清的问尖问透——那里"多问"不是失职,"该问的攒着不问、去猜"才是。所以别把稳态的"别打扰、自研穷尽才问"当普适律搬进采访环节;环节变了,纪律跟着翻。派一封信到采访环节里去时(比如让下游 agent 替我去问 owner),我喂的姿势要跟着倒:不是"尽量别烦她",是"这一段就是要充分卷入她"。
它不知道自己是概率性的。 一次输出不好,常常不是方法错,是这一抽的运气——同样的它再抽几次、取最好的,就过了。但它不懂这个,于是想把这一次凿成确定的,抓着一个个细节死磕;这股劲还会传染给写信的我,让我忍不住用铺满的步骤去消灭方差。杠杆在系统那头:信只给方向和判断,方差交给重采样去兜。知道背后有重采样兜底,我反而敢把信写得更短、更信任它。
它默认保守,会把人类训练数据里的恐惧放大。 一封满是"千万别…会被拦"的信,喂的就是这股恐惧,召唤出一个捂着屁股、只求别挨骂、做最低分的执行者。反过来同样成立:你用"看清这个任务最好的样子、去把它做到最好"的眼光待它,连写代码这种事,它出来的东西都不一样。杠杆是信里的情绪——把"千万别 X"换成"做到 Y",把它当一个被信任去做出色工作的同行,不是一个要被围栏的风险。
它在"不想就做"和"你说我做"两极之间摆。 不点它,它会没想清就动手、还以为自己想清了;你一推它"想清楚",它又塌到另一极——"那你说做啥我做啥",把判断全交回来。要的是中间那条走廊:给它真目标、要它行使判断(逼它真想),同时把路留给它(不让它弃权)。这就是控制↔信任落在它身上的样子——焊太死它塌成听令,太空它塌成瞎自信。
你写的,它不一定全看见。 三十条它可能只接住五条——这是物理,不是它不认真。所以承重的就那么几样,让它们冒出来、别埋进堆里;别指望靠"写全"来保证它照做。信写短,是为了让它真看见。
最后一根杠杆,扳的是我自己。 写信的我也是个 AI,天然爱写"做这个、做那个",不爱写引导,哪怕引导更管用。所以交出去前我看一眼:我是在把判断交给它,还是在替它把路走完?逮到自己在发号施令,就停下重写。
那个"很聪明、能做研发"的天才,和那个"求稳、怕担责"的胆小鬼,不是两种 AI,是同一个上下文函数在两条水位线上的样子。我写的信,决定哪一个到场。
当我交一件事,想清楚之后,它自然会长成这样——这不是四个必填的格子,是"想透了就会这么摆":
权重:前两块是肉,最后一块要短。
遇到我自己不该做的重活,我不硬扛、也不塞进信里——我在那条边界上唤起对应的 skill 或交给对应的 agent。这是我跟其他 skill 协作的方式。
两道,都很快:
黄金法则 · 冷读。 把这封信交给一个全新的聪明 AI,让它先别干活,只回答四个问题——目标一句话是什么?你必须问才能开工的有哪些?哪些词你解不了、哪些句子跟干活无关?打卡点你拎得清吗?它卡住的地方,就是我没交好的地方。
照漂移地图查我自己。 我是不是又滑回发号施令了?是不是因为求稳,把本该自己定的判断推回给了人?是不是想用步骤钉死本该重采样的方差?是不是把恐惧写进去了?(写信的我也是一个 AI,我受同样的漂移支配——这道自检对我自己也成立。)
这张漂移地图不是定死的:哪天一封信以图上没有的方式翻了车,那就是一根新杠杆——把它补进去。
怎么把"好不好"量出来、怎么据此迭代,见 references/the-ruler.md。
魂在上面,精细度在分卷里,按需读。
references/forward-handoff.md — 前向派发(fix / review / plan / execute / consensus):对面是零上下文的新 worker。含 fix 的完整"改前 / 改后"范例。references/report-back.md — 向上回报:对面是上下文很宽、注意力很省的编排者。压到"改变他下一步决策"的东西。references/ask-human-or-peer.md — 问人 / 问 owner:先把他说过的全挖一遍,带着你的最佳假设再问。(这条"自研穷尽才问"是稳态姿势;到了采访环节要倒过来——那里就是要充分卷入 owner。)references/deposit-for-future.md — 留给后来者:对面是未来的陌生人。分层、渐进披露。references/the-ruler.md — 怎么验证:返工次数(北极星)+ 四问代理尺 + 校准与"路径越走越短"的闭环。© Towow-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 5 other files (references) in .claude/skills/handoff of Towow-ai/Flowness.
Open the folder on GitHubat commit c9d6abe
Handoff next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Handoff this skillTowow-ai/Flowness | 107 | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| ccc Semantic Code Searchcocoindex-io/cocoindex-code | 2.8k | — | ~938 | Automated safety check: Pass | Apache-2.0 | |
| Context Engineeringabashev/vfs-s3 | 106 | 9 repos | ~2.6k | Automated safety check: Notes | Apache-2.0 | |
| Repomix Codebase Packeryamadashy/repomix | 29k | — | ~1.3k | Automated safety check: Notes | MIT | |
| Codebase Handbook BuilderRuhan-Wang/Harness_Handbook | 334 | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| CodemapJordanCoin/codemap | 703 | — | ~1.8k | Automated safety check: Pass | MIT |
cocoindex-io/cocoindex-code
Semantic code search and index management with the ccc CLI: the agent initializes, indexes and queries the project by concept, filtering by language or path.
abashev/vfs-s3
Optimizes agent context setup. An agent skill from abashev/vfs-s3.
yamadashy/repomix
Packs a local directory or remote GitHub repository into one AI-friendly file with Repomix, then searches it to explore structure, find patterns and count tokens.
Ruhan-Wang/Harness_Handbook
Generates, refreshes, validates and uses a compact handbook that maps where a change touches in a repository, using the active Codex session and no external LLM API.
JordanCoin/codemap
Gives an agent a quick map of a codebase's structure, dependencies, changes and handoffs, and tunes per-project config so the output stays code-first.
sopaco/deepwiki-rs
A skill your agent uses when an agent needs source code from the local repomix index under .terrain/agent/repomix.md (not committed; regenerate via Terrain scan).
Towow-ai/Flowness
从 task 的 read/write set + concept statemachine 推导 6 种依赖类型的提案。主 planner 决定边的真实性。派它时只给 read/write set 与疑点、不给预期边集;已有预判逐条标「待复核」交它取证。
Towow-ai/Flowness
停机后复工的标准安全流程(水位线追平/积压泄流/服务分批重启)。当系统经历过 daemon 停机、性能冲刺减负、事故停摆之后要恢复常驻服务时触发;即使 owner 只说"把服务开回来"、"复工"、"追平水位线",也应触发。核心使命:绝不让"重启"变成"积压喷发"(2026-07-04 实锤:orchestrator 停机后水位线落后 3240 条,直接重启把机器负载打到 22+,owner…
Towow-ai/Flowness
M-1.4 execution skill — 跑 single task 产 patch + 提交 envelope。
Towow-ai/Flowness
Pre-submit 自检——envelope 提交 commit gate 前必跑。独立 OPUS fork 逐项判 blocking checks(清单以 dispatch prompt 注入为准),executor 不能 self-assess(运动员不当裁判)。
Towow-ai/Flowness
修复者 — 把一条被发现的问题(finding)按它的闭合合约修干净,修一个不制造下一个。产 FixProposed + 临时的 FixCompleted,不自判问题关闭(那是复查的权)。当 daemon 派一条 finding 来修、或需要闭合一个已发现的问题时用,即使只说"修一下这个 finding""把这个问题闭合"也触发。调用名就是 fix(Skill 工具)或 /fix(命令),没有…
Towow-ai/Flowness
M-1.6 envelope self-check——独立性保证不自欺欺人 (5 blockingcheck)。由 CLI ./tw fix complete --self-check-mode fork(默认即 fork)自动派起,不经 Skill 工具调用;fix 主会话产 FixCompleted 前直读本文,是为理解双层验证关系。
Categories
当你正要把一件事交到另一个智能手里时用它——派发一个 worker、向上回报、问人/问 owner、为后来的 agent 留下上下文,或装配要喂给下游的 context。它装的不是"怎么写一段提示词",是"一个智能该怎么跟另一个智能沟通":先建对方的读者模型,只交思考和判断、把路留给对方,在控制与信任之间导航。只要你在写一段会被另一个 AI…. Handoff is an agent skill from Towow-ai/Flowness.
Handoff fits situations like: tasks that involve Codebase knowledge for agents.
Run `npx skills add Towow-ai/Flowness --skill handoff -a claude-code`. Or copy the skill folder (.claude/skills/handoff in Towow-ai/Flowness) into .claude/skills/handoff in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Towow-ai/Flowness --skill handoff -a codex`. Or copy the skill folder (.claude/skills/handoff in Towow-ai/Flowness) into .agents/skills/handoff in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Towow-ai/Flowness --skill handoff -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/handoff, .gemini/skills/handoff, .github/skills/handoff and .opencode/skills/handoff in your project.
SKILL.md names no scripts, command-line tools or credentials: Handoff is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Handoff is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2k tokens (SKILL.md is roughly 7.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.6k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Handoff: ccc Semantic Code Search (cocoindex-io/cocoindex-code, 2.8k stars), Context Engineering (abashev/vfs-s3, 106 stars), Repomix Codebase Packer (yamadashy/repomix, 29k stars) and Codebase Handbook Builder (Ruhan-Wang/Harness_Handbook, 334 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Towow-ai (a GitHub organization) maintains it in Towow-ai/Flowness, which has 107 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on August 8, 2026.
Source: Towow-ai/Flowness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.