arc-gate

arc-gate is a command for Claude Code from rana/skills. It costs 0 tokens per session (801 once invoked), scanned A, original, MIT.

A command that checks whether a project is ready for its current development phase, such as before coding, during implementation, before launch, or at a project boundary.

In plain words
What is it for?
Use it to run the quality checks appropriate to a project's phase and connect the results across the selected review steps.
Why use it?
It exposes missing documentation, gaps, hidden dependencies, and design or implementation drift before they cause larger problems.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the y plugin — 64 skills, 14 commands, 8 agents shipped together

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 commands/rana/skills/arc-gate
Clone the repo
git clone --depth 1 https://github.com/rana/skills

Made for: Claude Code.

Or install y, the plugin that ships this one along with the rest of its 64 skills, 14 commands, 8 agents.

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 arc-gate

README.md
[![agentmods](https://agentmods.dev/badge/commands/rana/skills/arc-gate.svg)](https://agentmods.dev/commands/rana/skills/arc-gate)
Your own site
<a href="https://agentmods.dev/commands/rana/skills/arc-gate"><img src="https://agentmods.dev/badge/commands/rana/skills/arc-gate.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 801 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 5.1 $0.00000 $0.00801
Opus 5 $0.00000 $0.00400
Sonnet 5 $0.00000 $0.00160
Haiku 4.5 $0.00000 $0.00080

Measured 5d ago against content hash ef240a0c1af3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

arc-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 5d 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.

commands/arc-gate.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase-appropriate quality gate. Selects the right skill chain for the current project phase.

$ARGUMENTS

Gate Selection

Parse the argument to determine which gate to run. Accept: pre-implementation, during-implementation, pre-launch, boundary, or a stage/arc number.

Gate: pre-implementation (default if no argument)

The project has a design but no code (or code is about to begin). Focus: are the documents ready to implement from?

Run these skills in sequence, threading findings:

  1. /doc-health — Identifier audit + omission search + consistency check
  2. /gaps — Intent alignment: check the design against the project's stated purpose, principles, and constraints. Focus on the top 3 gaps between intent and design.
  3. /ghost — Hidden dependencies and assumptions that would block implementation
  4. /crystallize — Simplify before building

Gate: during-implementation

Code exists and is evolving. Focus: is the code drifting from the design?

Run these skills in sequence, threading findings:

  1. /drift-detect — Compare stated architecture against actual code patterns
  2. /ghost — Hidden dependencies surfaced by real implementation
  3. /deep-review — Cross-document consistency and gap detection (focused on implemented sections)
  4. /crystallize — Simplify what's accumulated during implementation

Gate: pre-launch

A stage or arc is about to ship. Focus: is it production-ready?

Run these skills in sequence, threading findings:

  1. /launch-gate — Go/no-go across SLAs, monitoring, backups, rollback
  2. /ops-review — Deployment, costs, monitoring, incident response
  3. /hardening-audit — HTTP headers, secrets, input validation, dependencies
  4. /threat-model — STRIDE-based threat identification from actual architecture

Gate: boundary or boundary [N]

An arc or stage boundary. Focus: is everything consistent and complete before moving on?

Run these skills in sequence, threading findings:

  1. /deep-review — Comprehensive multi-dimensional quality gate
  2. /gaps — Intent alignment: full check against all stated goals, principles, and success criteria. Focus on gaps between what was intended and what was built.
  3. /workflow-trace — Trace the editorial pipeline end-to-end for friction
  4. /crystallize — Simplify before the next phase adds complexity

Read the full file on GitHub · 76 lines

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. 5d ago First seen · 76 lines · 0 tokens per session scan A ef240a0c1af3

Subscribe to this mod's changes

arc-gate is a command published in the GitHub repository rana/skills (1 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 801 tokens. 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.