gate

A read-only release verification command that checks a project in six stages, including building, tests, linting, dependency safety, a manual user-facing review, and a simplicity check. It stops at the first failed stage and does not fix issues.

In plain words
What is it for?
Use it before releasing software to verify the build, test suite, static analysis, dependencies, user-facing details, and whether the implementation contains unnecessary complexity.
Why use it?
It provides a consistent go/no-go check before release and shows the earliest reason a project is not ready. This prevents later checks from hiding an earlier failure.

Command

Part of the project-scaffolder plugin — 7 skills, 19 commands, 2 hooks 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/valsecchi75/project-scaffolder/gate
Clone the repo
git clone --depth 1 https://github.com/valsecchi75/project-scaffolder

Or install project-scaffolder, the plugin that ships this one along with the rest of its 7 skills, 19 commands, 2 hooks.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 391 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 $0.00026 $0.00391
Opus 5 $0.00013 $0.00196
Sonnet 5 $0.00005 $0.00078
Haiku 4.5 $0.00003 $0.00039

Measured 3d ago against content hash 71937478bcf4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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/gate.md · 48 lines

What it actually says

/gate

Run the pre-release verification gate. Read-only (reports, does not fix).

Usage

/gate

Steps

  1. Locate the [name]-release-gate skill in skills/.
  2. Execute each stage sequentially:
    • Stage 1: Build verification
    • Stage 2: Test suite
    • Stage 3: Lint / static analysis
    • Stage 4: Dependency audit
    • Stage 5: Manual checklist (user-facing concerns)
    • Stage 6: Simplicity Check (Karpathy — scope creep, over-engineering, dead code, speculative features)
  3. On the first FAIL: stop, report which stage failed and why.
  4. On all PASS: report green light for release.

Output format

## Release Gate — YYYY-MM-DD HH:MM
- Stage 1 (Build):     ✅ PASS
- Stage 2 (Tests):     ✅ PASS
- Stage 3 (Lint):      ❌ FAIL — 3 warnings in lib/ui/
- Stage 4 (Deps):      ⏭ SKIPPED (previous stage failed)
- Stage 5 (Manual):    ⏭ SKIPPED
- Stage 6 (Simplicity):⏭ SKIPPED
**Verdict:** NOT READY — fix Stage 3 and re-run

Rules

  • Stages are ordered cheapest → most expensive.
  • Fail-fast: never run stage N if stage N-1 failed.
  • Do not auto-fix issues — /gate only reports.
  • If the release-gate skill is missing: stop and suggest /scaffold to generate it.
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. 3d ago First seen · 48 lines · 26 tokens per session scan A 71937478bcf4

Subscribe to this mod's changes

gate is a command published in the GitHub repository valsecchi75/project-scaffolder (9 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 391 once invoked, about $0.0001 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 2026-08-31.