validate-2

A command for comprehensive end-to-end testing of a remote coding-agent platform. End-to-end testing checks the whole system together, including Docker, databases, tests, and GitHub workflows.

In plain words
What is it for?
Use it to test the platform through a public ngrok URL, including creating a GitHub issue, running Archon commands, and reviewing the resulting pull request.
Why use it?
It brings many separate checks and the full issue-to-pull-request workflow into one validation run.

Command for Claude Code

▶ I Turned Claude Code Into a Complete Video Generation System (with Archon) Cole Medin · about coleam00/Archon · on YouTube →
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/coleam00/archon/validate-2
Clone the repo
git clone --depth 1 https://github.com/coleam00/Archon

Made for: Claude Code.

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 9,807 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.09807
Opus 5 $0.00000 $0.04903
Sonnet 5 $0.00000 $0.01961
Haiku 4.5 $0.00000 $0.00981

Measured 3d ago against content hash 981df53026f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

validate-2 scanned grade C with 2 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "${WORK_DIR}"/remote-coding-test-*

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:3090/health | jq
.claude/commands/validation/validate-2.md · 1,153 lines

How it starts

The opening of the file, as written. The whole thing — 1,153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ultimate Validation Command (Updated January 2026)

Run comprehensive end-to-end validation of the Remote Agentic Coding Platform including Docker, Test Adapter, Database, and full GitHub workflow execution.

The key test (Phase 8): Creates a GitHub issue, then invokes the full workflow via issue comments:

  1. @Archon /command-invoke prime - Analyze codebase
  2. @Archon /command-invoke plan-feature - Create implementation plan
  3. @Archon /command-invoke execute - Implement changes and create PR
  4. (Phase 9) @Archon /command-invoke review-pr - Review the created PR

Usage:

/validation:validate-2 <ngrok-url>

Example:

/validation:validate-2 https://trinity-nonadverbial-enharmonically.ngrok-free.dev

Prerequisites:

  • ngrok running and exposing port 3090 (for GitHub webhooks)
  • .env file configured with all required credentials
  • GitHub CLI (gh) authenticated
  • Docker installed and running

Updated for:

  • Bun runtime (not npm)
  • Archon paths (~/.archon/workspaces/owner/repo)
  • 6 database tables (codebases, conversations, sessions, command_templates, isolation_environments, workflow_runs)
  • Worktree isolation with database tracking
  • Full GitHub workflow: Issue → Prime → Plan → Execute → PR → Review
  • Comprehensive command testing (/help, /clone, /repos, /templates, /status, /getcwd, /setcwd, /init, /reset, /worktree cleanup, /worktree orphans)
  • PR/Issue worktree sharing verification
  • GitHub close event cleanup trigger
  • Database consistency checks (orphaned records)

Phase 1: Foundation Validation

1.1 Type Checking

bun run type-check

Expected: Zero TypeScript errors

1.2 Linting

bun run lint

Expected: Zero ESLint errors (warnings acceptable)

1.3 Code Formatting

bun run format:check

Expected: All files pass Prettier checks

1.4 Unit Tests

bun test

Expected: All critical tests pass

1.5 Build

bun run build

Expected: Clean build to dist/ directory

Read the full file on GitHub · 1,153 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. 3d ago First seen · 1,153 lines · 0 tokens per session scan C 981df53026f5

Subscribe to this mod's changes

validate-2 is a command published in the GitHub repository coleam00/Archon (23,339 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 9,807 tokens. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.