specrew-gate-stop

specrew-gate-stop is a skill for Claude Code, Codex from alonf/specrew. It costs 127 tokens per session (1,219 once invoked), scanned A, original, MIT.

A stop procedure for Specrew, a lifecycle-governance system, when a person must review and approve the next step.

In plain words
What is it for?
Use it at every required human-verdict boundary to show the current phase, progress, decisions, and next action before stopping.
Why use it?
It ensures the person can read the full six-part review packet before giving a verdict, instead of seeing only shortened approval options.

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/alonf/specrew/specrew-gate-stop
Any agent
npx skills add alonf/specrew --skill specrew-gate-stop
Clone the repo
git clone --depth 1 https://github.com/alonf/specrew

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 specrew-gate-stop

README.md
[![agentmods](https://agentmods.dev/badge/skills/alonf/specrew/specrew-gate-stop.svg)](https://agentmods.dev/skills/alonf/specrew/specrew-gate-stop)
Your own site
<a href="https://agentmods.dev/skills/alonf/specrew/specrew-gate-stop"><img src="https://agentmods.dev/badge/skills/alonf/specrew/specrew-gate-stop.svg" alt="Measured on agentmods" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,219 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 $0.00127 $0.01219
Opus 5 $0.00063 $0.00609
Sonnet 5 $0.00025 $0.00244
Haiku 4.5 $0.00013 $0.00122

Measured 4d ago against content hash 3eb74bd86e3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specrew-gate-stop 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 4d 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.

.claude/skills/specrew-gate-stop/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

specrew-gate-stop

Type: Lifecycle-Governance Skill Schema: v1 Status: Active boundary-stop renderer (Claude host)

Purpose

You have reached a Specrew human-verdict boundary stop. On the Claude host the AskUserQuestion picker collapses the Rule 46 packet into its short header/option fields, so the human is asked to approve something they cannot read. This skill removes that failure mode: while it is active the AskUserQuestion tool is disallowed — you have no picker to collapse into, so you MUST render the stop as a Markdown message. The design workshop is governed by its own skill, which independently removes the same unsafe picker on Claude and uses typed prose choices. Clarify questions are not boundary stops and keep the picker. Only boundary verdict stops route through this skill.

What to render — one Markdown message, then STOP

Render the full Rule 46 six-section re-entry packet as Markdown — all six headers, each with real content built from the lifecycle state (the current phase, tasks-progress.yml, the decisions ledger, and what the lifecycle does next), never a placeholder and never a terse one-liner:

  1. ## What I Just Did
  2. ## Why I Stopped
  3. ## What Needs Your Review
  4. ## What Happens Next
  5. ## Discussion Prompts
  6. ## What I Need From You

Every artifact / file / directory reference in every section MUST be a visible bare file:/// URL (Rule 52) — not a repo-relative path (specs/..., .specrew/...), and not a markdown link, because terminal hosts hide the clickable target otherwise.

Then render the verdict options as a numbered Markdown list, exactly:

What's your verdict?
  1. Approve as-is — proceed with the defaults
  2. Approve with instructions — proceed and carry the added instructions
  3. Send back — describe what to change before this boundary can advance
  4. Discuss prompt #N — discuss that prompt only, then return for explicit approval

Then, as the VERY LAST line of your message, emit the machine marker — an HTML comment, invisible when the message is rendered, but read by the Stop hook to capture the human's verdict and tie it to THIS exact boundary:

Read the full file on GitHub · 85 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. 4d ago First seen · 85 lines · 127 tokens per session scan A 3eb74bd86e3e

Subscribe to this mod's changes

specrew-gate-stop is a skill published in the GitHub repository alonf/specrew (54 stars, last pushed 2d ago), licensed MIT. It adds 127 tokens to every session and 1,219 once invoked, about $0.0006 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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