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 commands/rana/skills/arc-gategit clone --depth 1 https://github.com/rana/skillsWrote 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.
[](https://agentmods.dev/commands/rana/skills/arc-gate)<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>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.
| Model | Per session | Once 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 |
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.
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:
/doc-health— Identifier audit + omission search + consistency check/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./ghost— Hidden dependencies and assumptions that would block implementation/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:
/drift-detect— Compare stated architecture against actual code patterns/ghost— Hidden dependencies surfaced by real implementation/deep-review— Cross-document consistency and gap detection (focused on implemented sections)/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:
/launch-gate— Go/no-go across SLAs, monitoring, backups, rollback/ops-review— Deployment, costs, monitoring, incident response/hardening-audit— HTTP headers, secrets, input validation, dependencies/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:
/deep-review— Comprehensive multi-dimensional quality gate/gaps— Intent alignment: full check against all stated goals, principles, and success criteria. Focus on gaps between what was intended and what was built./workflow-trace— Trace the editorial pipeline end-to-end for friction/crystallize— Simplify before the next phase adds complexity
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.
- 5d ago First seen · 76 lines · 0 tokens per session scan A ef240a0c1af3
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.
Other commands, from other repositories
init
Install the formatters this repository needs, with every command visible before it runs.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
check-dev
Type-check a Z specification with fuzz.
adr-supersede
Create a new ADR that supersedes an existing one.
audit-plugin
Audit plugin skills, commands, and agents for structure, size, and naming issues.