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 agentmods add skills/noho/code-is-cheap/gateflownpx skills add noho/code-is-cheap --skill gateflowgit clone --depth 1 https://github.com/noho/code-is-cheapWhat 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 | $0.00087 | $0.03347 |
| Opus 5 | $0.00044 | $0.01673 |
| Sonnet 5 | $0.00017 | $0.00669 |
| Haiku 4.5 | $0.00009 | $0.00335 |
Grade A, and why
gateflow 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.
How it starts
The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gateflow
Gateflow 只定义单个 work unit 的流程和 gate。work unit 可以是 feature、issue、bug fix、migration、refactor、
schema/public contract change 或 architecture-sensitive task。
Core Principles
- 先看代码和事实,再判断 work unit 是否成立。
- 进入 plan 前,先用通俗语言向用户确认目标、非目标、边界和成功信号。
- Goal confirmation 是 binding scope contract;后续 gate 不得扩大目标、非目标、success signal 或验收标准,除非先停下来让用户重新确认。
- 只做当前 work unit 需要的设计;不得引入无当前需求、真实风险或明确扩展压力支撑的过度设计。
- 每个 gate 都必须有 artifact、decision、validation 或明确说明;conversation-only 结果不足以通过 gate。
- draft PR gate 自动推进到
draft-PR-pass;merge、approve、mark ready for review、request reviewers、delete branch、 对外 comment、创建/修改外部 issue 仍需用户额外授权。
Invocation
典型调用:
使用 $gateflow 开发 <work-unit>。
可选参数:
使用 $gateflow design_doc=<path> base_ref=<ref> 开发 <work-unit>。
如果传入 design_doc,它是当前 work unit 的设计依据之一。若未传入,则以用户需求和代码事实为准。
Preflight
任何 discussion、plan 或文件修改前,先检查:
git branch --show-current
git status --short
如果当前 branch 是 main、master、develop、release/* 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。
Gate: goal confirmation
进入 plan 前必须完成 goal confirmation:
- 读取需求、design document(如有)和相关代码;
- 从第一性原理判断 work unit 是否成立;
- 复述目标、动机、成功信号、非目标、scope boundary;
- 说明直接代码证据;
- 说明本轮不会做的过度设计;
- 列出 blocking open questions(如有)。
用户确认后才能进入 plan。如果目标不成立、范围过大、动机不足或关键约束缺失,先 discussion,不进入 implementation。
Gate Order
固定顺序:
goal confirmation
-> plan
-> plan review
-> fix
-> re-review
-> accepted plan commit
-> implementation
-> code review
-> fix
-> re-review
-> accepted slice commit
-> aggregate deepreview
-> fix
-> re-review
-> accepted deepreview commit
-> ready-to-open-draft-PR
-> push
-> create draft PR
-> PR review
-> fix
-> re-review
-> accepted PR review commit
-> push
-> draft-PR-pass
-> final closeout
plan review gate 必须使用 planreview skill;code review、aggregate deepreview 和 PR review gates 必须使用 deepreview skill。
Gate Order entry 与下方 section 的绑定是执行约束。必须按对应的 ## Gate: ... 或 ## Gate Group: ... section 执行:
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.
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.
- 2d ago First seen · 341 lines · 87 tokens per session scan A 05b41c97a4e5
gateflow is a skill published in the GitHub repository noho/code-is-cheap (58 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 87 tokens to every session and 3,347 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…