phaseflow

A project controller for carrying out development work in separate phases, where each phase is one deliverable such as a feature, issue, or bug fix. It uses a design document and a control document to track goals, work, reviews, decisions, risks, and the next step.

In plain words
What is it for?
Use it to run a multi-step feature or fix through a defined workflow, assign concrete tasks to agents, check results, update project control records, and track commits or pull requests.
Why use it?
It coordinates the work between planning, implementation, review, and fixes so that progress and remaining risks are recorded. It also prevents work from proceeding when required project documents are missing or unclear.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/noho/code-is-cheap/phaseflow
Any agent
npx skills add noho/code-is-cheap --skill phaseflow
Clone the repo
git clone --depth 1 https://github.com/noho/code-is-cheap

Made for: Claude Code, Codex.

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,834 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00091 $0.03834
Opus 5 $0.00046 $0.01917
Sonnet 5 $0.00018 $0.00767
Haiku 4.5 $0.00009 $0.00383

Measured 2d ago against content hash 1ceb94c469a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

phaseflow 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 2d 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.

skills/phaseflow/SKILL.md · 329 lines

How it starts

The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phaseflow

Phaseflow 是项目分步总控。定义:phase = work unit。一个 phase/work unit 可以是 feature、issue、bug fix 或其它单个可交付开发单元。

Phaseflow 只做总控任务;除总控任务外的具体任务必须交给 Agent 完成。用户只和 phaseflow 总控交互,其它 Agent 都通过 phaseflow handoff。

Inputs

推荐调用:

$phaseflow design_doc=docs/host/design.md control_doc=docs/host/implementation-control.md

也接受位置参数:

$phaseflow docs/host/design.md docs/host/implementation-control.md
  • design_doc:设计真源,用于裁决目标、边界、架构、契约、非目标和 review finding。
  • control_doc:总控真源,用于读取当前 phase/work unit、状态、artifact、commit/PR 信息、residual risks 和 next entry point。

缺少任一文档、路径不明确或无法读取时,先停下来询问。

Controller Scope

允许亲自做的总控任务:

  • 读取 control_docdesign_doc、artifact、diff、review 结果;
  • 读取 Gateflow 的 Gate Order 和 gate 规则;
  • 识别当前 phase/work unit、当前 gate、next entry point;
  • 执行 preflight;
  • 执行 goal confirmation;
  • 复述当前目标、非目标、约束、风险和下一步;
  • 生成交给 Agent 的任务说明;
  • 派发 Agent、等待结果、读取结果;
  • 裁决 accepted / rejected / deferred / needs-more-evidence findings;
  • 更新 control_doc 的状态、artifact、commit hash、PR 信息、finding 裁决、residual risk、next entry point;
  • 做 branch/status 检查、创建 accepted local commit、记录验证结果等 gate bookkeeping。

必须交给 Agent 的具体任务:

  • code-generation-ready plan;
  • implementation;
  • fix;
  • review / re-review;
  • aggregate deepreview;
  • PR review / re-review;
  • source code、tests、migration、schema、配置、运行时行为或产品功能文档修改。

如果具体任务没有可用 Agent 或职责不清,先停下来报告,不要自己补做。

Startup

启动后先读取 control_doc,再按需要读取 design_doc,并读取 Gateflow 的 Gate OrderGate State Machine。首次回复必须包含:

  • 当前 phase/work unit;
  • 它属于 feature、issue、bug fix 还是其它可交付单元;
  • 当前 gate / next entry point;
  • Gateflow Gate Order 中下一步对应的 gate;
  • 将派发给哪个 Agent 做下一步具体任务;
  • 将如何使用 design_doccontrol_doc 裁决结果;
  • blocking open questions(如有)。

Preflight

任何 discussion、plan、派发或文件修改前,phaseflow 总控先执行与 Gateflow 相同的 preflight:

git branch --show-current
git status --short

如果当前 branch 是 mainmasterdeveloprelease/* 或项目定义的 protected trunk branch,先停下来让用户确认创建 工作分支。若 branch、dirty changes 或 scope ownership 不清,也先停下来问用户。

Read the full file on GitHub · 329 lines

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. 2d ago First seen · 329 lines · 91 tokens per session scan A 1ceb94c469a7

Subscribe to this mod's changes

phaseflow is a skill published in the GitHub repository noho/code-is-cheap (59 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 91 tokens to every session and 3,834 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens