flow-feature

flow-feature is a skill for Claude Code, Codex from asherzj/ashers-agent-skills. It costs 73 tokens per session (1,101 once invoked), scanned A, original, MIT.

A workflow coordinator for taking a new software request from an initial conversation through research, specification, task breakdown, and implementation. It connects several separate development skills into one process.

In plain words
What is it for?
It is for clarifying feature requests, making prototypes when needed, publishing specifications, creating delivery tickets, and implementing unblocked tickets.
Why use it?
It keeps requirements, decisions, acceptance examples, dependencies, and implementation tasks connected as the work moves forward.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit It is for clarifying feature requests, making prototypes when needed, publishing specifications, creating delivery tickets, and implementing unblocked tickets.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/asherzj/ashers-agent-skills/flow-feature
Install

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.

Any agent
npx skills add asherzj/ashers-agent-skills --skill flow-feature
Clone the repo
git clone --depth 1 https://github.com/asherzj/ashers-agent-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for flow-feature

README.md
[![agentmods](https://agentmods.dev/badge/skills/asherzj/ashers-agent-skills/flow-feature/github.svg)](https://agentmods.dev/skills/asherzj/ashers-agent-skills/flow-feature)
Your own site
<a href="https://agentmods.dev/skills/asherzj/ashers-agent-skills/flow-feature"><img src="https://agentmods.dev/badge/skills/asherzj/ashers-agent-skills/flow-feature/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.

agentmods 80×15 button for flow-feature

Your own site · 80×15
<a href="https://agentmods.dev/skills/asherzj/ashers-agent-skills/flow-feature"><img src="https://agentmods.dev/badge/skills/asherzj/ashers-agent-skills/flow-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,101 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.01101
Opus 5 $0.00036 $0.00550
Sonnet 5 $0.00015 $0.00220
Haiku 4.5 $0.00007 $0.00110

Measured 9d ago against content hash f9d954ef1e4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

flow-feature 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 9d 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.

coding/flow-feature/SKILL.md · 56 lines

What it actually says

新需求交付流程

本 Skill 只负责衔接已有研发模块,不复制它们的内部操作。进入每个阶段时,加载并完整遵循对应 Skill。

依赖

必须能够使用 grill-with-docsprototypeto-specto-ticketsimplement;原始输入是口述或逐字稿时还要能够使用 from-transcript。首次在仓库中运行工程流程前,应先完成 setup-engineering-skills。如果依赖缺失,停在当前边界并明确报告,不要临时发明一套替代流程。

开始前读取仓库的 AGENTS.mdCLAUDE.md,让工单系统、分诊标签、领域术语和 ADR 约定贯穿整个流程。

流程

0. 编译原始口述(按需)

输入是会议逐字稿、连续口述或未经整理的聊天记录时,先调用 from-transcript。只有经用户确认的输入简报进入后续阶段;保留当前会话作为一手来源,不让用户重述已经确认的内容。

1. 澄清需求

调用 grill-with-docs,直到用户价值、范围、领域语言、验收接缝、正常与异常验收例子和难以回退的决策都已明确。功能依赖外部系统时,确认不可用、超时、重复、部分成功和并发冲突中哪些会改变接口承诺。澄清、规格化和拆工单应尽量留在同一个连续上下文中。

如果最终只有一个局部行为且一次实现上下文足够,转用 flow-small-change;如果连通往目标的路线都还说不清,转用 flow-large-effort

2. 只在必须运行或亲眼查看时制作原型

只有当某个问题无法靠对话回答、必须运行状态/业务逻辑或查看 UI 时才调用 prototype。动手前写明原型要回答的唯一问题;结束时记录原型分支或产物、结论,以及它改变了哪项决策,再把结论带回原需求上下文。

原型是规格的证据,不是生产代码,也不能代替规格。只有跨运行环境、目录、仓库或协作者时才需要可携带的 handoff;否则继续使用当前上下文。

3. 发布规格

调用 to-spec,用完整澄清记录和原型结论合成规格。确认验收接缝、带编号的验收用例、故障与一致性决策以及非目标后,把规格发布到已配置的工单系统。这个阶段只做综合,不重新访谈用户。

4. 拆成交付工单

调用 to-tickets。发布前必须让用户确认纵向切片的粒度、验收用例分配、阻塞边,以及所有临时结构的删除工单。这里生成的工单天然是 ready-for-agent,禁止再次送入 triage

5. 推进可执行前沿

只实现所有阻塞项均已关闭的工单。每次调用 implement 只处理一张工单;一张工单对应一个分支/工作树、验证、评审、提交、推送和关闭周期。

完成一张后,下一张从干净上下文开始,重新读取完整工单、评论、相关领域文档和 ADR。如果当前环境无法自动切换干净上下文,就停下来列出下一张可执行工单和准确调用方式,不要把上一张工单的偶然上下文继续带下去。只有用户明确要求并行,且每张工单都有隔离分支和可写工作树时才并行。

6. 功能级收尾

所有范围内工单完成后,检查父规格中的每个验收用例是否都有交付证据、临时结构是否已删除或有明确责任工单、领域与架构上下文是否已同步。执行仓库规定的项目级完成钩子,例如项目管理记录或变更日志更新。

完成条件

规格已发布,所有范围内工单都有交付证据并关闭,全部验收用例有证据,临时结构有明确结局,项目级完成钩子已执行,且没有未解决的阻塞项。除非工单系统规则明确授权,否则不要关闭或改写父规格 Issue。

Files

What ships with it

1 file 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.

Changes

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.

  1. 9d ago First seen · 56 lines · 73 tokens per session scan A f9d954ef1e4f

Subscribe to this mod's changes

flow-feature is a skill published in the GitHub repository asherzj/ashers-agent-skills (2 stars, last pushed 11d ago), licensed MIT. It adds 73 tokens to every session and 1,101 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

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…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

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…

Donchitos/Claude-Code-Game-Studios · 77 tokens

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.

Orkas-AI/Orkas · 5 tokens

projects

List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.

me2resh/apexyard · 24 tokens