spec-direction-gate

spec-direction-gate is a skill for Claude Code from chenweil/skillcaddy. It costs 99 tokens per session (1,704 once invoked), scanned A, original, MIT.

A human approval checkpoint for a technical plan before coding begins. It requires separate approval of the plan's overall direction and its detailed contents, then records both decisions in TECH.md.

In plain words
What is it for?
Use it after a TECH.md draft is written and before implementation of a substantial change. It is not intended for small fixes or changes that do not need a technical plan.
Why use it?
It prevents implementation from starting on an unapproved approach. If nobody is available to approve it, the process stops instead of approving the plan automatically.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use it after a TECH.md draft is written and before implementation of a substantial change. It is not intended for small fixes or changes that do not need a technical plan.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chenweil/skillcaddy/spec-direction-gate
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 chenweil/skillcaddy --skill spec-direction-gate
Clone the repo
git clone --depth 1 https://github.com/chenweil/skillcaddy

Made for: Claude Code.

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 spec-direction-gate

README.md
[![agentmods](https://agentmods.dev/badge/skills/chenweil/skillcaddy/spec-direction-gate/github.svg)](https://agentmods.dev/skills/chenweil/skillcaddy/spec-direction-gate)
Your own site
<a href="https://agentmods.dev/skills/chenweil/skillcaddy/spec-direction-gate"><img src="https://agentmods.dev/badge/skills/chenweil/skillcaddy/spec-direction-gate/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 spec-direction-gate

Your own site · 80×15
<a href="https://agentmods.dev/skills/chenweil/skillcaddy/spec-direction-gate"><img src="https://agentmods.dev/badge/skills/chenweil/skillcaddy/spec-direction-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,704 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 $0.00099 $0.01704
Opus 5.5 $0.00040 $0.00682
Sonnet 5.5 $0.00020 $0.00341
Haiku 4.5 $0.00010 $0.00170

Measured 28d ago against content hash eaa7cf2333d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spec-direction-gate 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 28d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (check-approval.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/spec-pipeline/spec-direction-gate/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

方向确认关卡(B)

一条流程只有在"方向"这一格真的会挡住它的时候才算成立。这个技能就是那一格。

输入是 specs/<id>/TECH.md 的草稿,输出是写回 TECH.md 的批准状态记录。中间没有任何自动放行的路径。

何时使用

  • TECH.md 草稿已写完,尚未开始实施
  • 需要在实施前留下"谁在什么时候批准了方向"的可核验记录
  • 复盘时需要确认某个实施是否真的经过方向批准,而不是默认通过

何时不使用

  • 纯 UI 改动、单文件修复等低复杂度变更,TECH.md 本身就不必产出
  • 方向已经单独确认过、这次只是修订若干小节时,改用下面的"增量修订"路径

硬性约束

  1. 两次确认,不合并。 先确认方向,确认通过之后才确认内容。合并这一步会破坏关卡:把大纲和方向放在同一次确认里,人会锚定在已经看到的具体大纲上,而不再重新考虑它上位的那个问题。
  2. 拒绝语义。 没有人在场就停止并报告这个技能需要人,不要"先按草稿往下走,回头再确认"。
  3. 批准要落盘。 两次确认的结论写进 TECH.md,不只留在对话里。实施阶段的验收要能读到"批准后文档仍存活"的证据。
  4. 批准的是方向,不是逐字内容。 方向确认通过后,作者仍可改实现细节;实施者不得改方向。

流程

第 0 步:确认在场

先确认当前是有人可以回答的交互会话。

不是交互式会话时:停下并报告"这个关卡需要人在场确认方向",然后结束。不要用默认值代替确认,也不要因为草稿看起来已经足够好就跳过。

第 1 步:确认方向

读 TECH.md,然后只向人提出方向层面的问题,不要展示具体大纲或章节结构:

  • 这份文档要解决的问题,和仓库当前状态对得上吗
  • 选定的方案,是这几个候选里最合适的那个吗
  • 哪些明确不在这次范围内
  • 还有什么上位问题,是这份文档答不了的

把问题一次问完,然后等回答。

方向被拒时的处理:记录被拒的方向和原因,停止。不要改写成新的大纲再问第二遍——那等于把第一次确认作废。修改草稿后必须从第 1 步重来。

第 2 步:确认内容

只有在第 1 步通过后才进入这一步。展示文档的实际章节和每节承担的内容,然后等确认。

内容被拒时:按意见修订,同样从第 1 步重新开始(内容修订可能改变方向)。

第 3 步:写回批准状态

两次都通过后,把结论追加到 TECH.md 末尾:

## Approval

- 方向确认:通过 / 拒绝(时间:YYYY-MM-DD HH:MM CST,确认人:__)
- 内容确认:通过 / 拒绝(时间:YYYY-MM-DD HH:MM CST,确认人:__)
- 本次确认的范围:仅方向与结构。实现细节可由作者调整,方向变更须重新过本关卡。

批准状态是显式记录,不是推断依据。没有这段内容,验收阶段必须按"未批准"处理。

写完用同目录的校验脚本自查:

python3 check-approval.py specs/<id>/TECH.md

退出码 0 = 已批准可进入实施;1 = 挡住(缺 ## Approval、结论仍是 通过 / 拒绝 模板、缺时间戳、方向被拒、结论无法判定);2 = 用法错误。

模板里的 通过 / 拒绝 必须二选一写死。两个候选都留着会被判为未批准——这是有意的,模板没填就等于没确认。

实施前的机械检查

上面的约束是文字。文字挡不住无人值守运行,所以本技能附带一个退出码校验:

python3 check-approval.py specs/<id>/TECH.md

进入实施之前跑一次,退出码非 0 就不要开始写代码。脚本只读不写,不会改文档。

被挡住的常见情况:

  • 文件不存在
  • 没有 ## Approval 段
  • 有 ## Approval 段但里面没有方向确认结论(摄入技能产出的就是这个状态)
  • 结论仍是 通过 / 拒绝 模板
  • 通过但没写时间戳(批准必须可核验到"谁在什么时候批准")
  • 方向被明确拒绝
  • 既不是通过也不是拒绝——按未批准处理

## Approval 之后如果还有别的章节,脚本只读到下一个章节标题为止;把"方向确认:通过"藏在后面的章节里不算数。## Source draft 之类段落里出现的"通过"也不会被误读成批准。

增量修订路径

只改了措辞、补充了行级引用、调整了不影响方向的实施顺序时,不必重走两次确认。在现有的 ## Approval 段下面追加一条修订记录,写明改了什么、为什么不需要重新确认方向。

Read the full file on GitHub · 120 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. 28d ago First seen · 120 lines · 99 tokens per session scan A eaa7cf2333d7

Subscribe to this mod's changes

spec-direction-gate is a skill published in the GitHub repository chenweil/skillcaddy (29 stars, last pushed 5d ago), licensed MIT. It adds 99 tokens to every session and 1,704 once invoked, about $0.0004 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 2026-10-01.

Related

Other skills, from other repositories

exploratory-data-analysis

Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

webhook-management

Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.

hoangsonww/Claude-Code-Agent-Monitor · 56 tokens

design-review

Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Not a UX audit (that checks usability) — this checks whether it looks professional and polished. Produces a design findings report with screenshots.…

jezweb/claude-skills · 108 tokens

react-patterns

React 19 performance patterns and composition architecture for Vite + Cloudflare projects. 50+ rules ranked by impact — eliminating waterfalls, bundle optimisation, re-render prevention, composition over boolean props, server/client boundaries, and React 19 APIs. Use when writing, reviewing, or refactoring React…

jezweb/claude-skills · 110 tokens

render-3d-product-showcase

Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…

gooseworks-ai/goose-skills · 159 tokens

render-airdrop-carousel

Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…

gooseworks-ai/goose-skills · 207 tokens