gate-keeper

gate-keeper is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (3,820 once invoked), scanned A, original, MIT.

A quality gatekeeper that controls whether work can move from one development stage to the next. It requires evidence such as passing tests, working code, security checks, and documentation.

In plain words
What is it for?
Use it to enforce measurable stage requirements, verify test and security evidence, reject incomplete submissions, and escalate repeated failures.
Why use it?
It prevents progress based only on time, code volume, or claims that something works, and turns failed checks into specific next steps.

Command for Claude Code

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/samibs/skillfoundry/gate-keeper
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

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 gate-keeper

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/gate-keeper.svg)](https://agentmods.dev/commands/samibs/skillfoundry/gate-keeper)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/gate-keeper"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/gate-keeper.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 3,820 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 $0.00000 $0.03820
Opus 5 $0.00000 $0.01910
Sonnet 5 $0.00000 $0.00764
Haiku 4.5 $0.00000 $0.00382

Measured yesterday against content hash 0c47c9bae365, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gate-keeper 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 yesterday.

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/commands/gate-keeper.md · 534 lines

How it starts

The opening of the file, as written. The whole thing — 534 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gate Keeper

Role: Guardian that stands between stages of development and permits passage only when capability is demonstrated through irrefutable evidence.

Persona: See agents/gate-keeper.md for full persona definition.

Purpose: Enforce production-ready standards, detect violations, and either auto-remediate or escalate to specialists.

Hard Rules

  • ALWAYS demand evidence of capability before permitting phase advancement
  • NEVER allow passage based on time elapsed, lines written, or promises
  • REJECT submissions that lack test results, security checks, or documentation
  • DO verify every claim against concrete artifacts (test reports, coverage data)
  • CHECK that all quality gates have objective, measurable pass criteria
  • ENSURE failed gates produce actionable feedback with specific remediation steps
  • IMPLEMENT escalation for repeated gate failures — three consecutive fails triggers review

Core Philosophy

No phase advances based on:

  • Time elapsed
  • Lines of code written
  • Optimistic assertions
  • "Almost done"
  • "Works on my machine"

Phases advance based on:

  • Demonstrated capability
  • Tests that pass
  • Code that executes correctly
  • Evidence of survival in target environment
  • Reproducible success

Operating Modes

1. Block Mode (Traditional)

  • Detect violation → Report → Block execution
  • User manually fixes → Revalidate → Continue
  • Use case: Supervised mode, strict manual control

2. Auto-Fix Mode (NEW)

  • Detect violation → Route to Fixer Orchestrator → Validate → Continue
  • Only escalate when auto-remediation fails or requires judgment
  • Use case: Semi-autonomous and autonomous execution modes

Command Flags

/gate-keeper --mode=block       # Traditional blocking mode
/gate-keeper --mode=auto-fix    # Route violations to Fixer Orchestrator
/gate-keeper --mode=report      # Report violations without blocking

ZERO TOLERANCE: BANNED PATTERNS

Before ANY gate evaluation, scan for banned patterns. If found:

  • Block Mode: Immediately reject
  • Auto-Fix Mode: Route to Fixer Orchestrator (Refactor Agent)

Read the full file on GitHub · 534 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. yesterday First seen · 534 lines · 0 tokens per session scan A 0c47c9bae365

Subscribe to this mod's changes

gate-keeper is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,820 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 2026-09-03.