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.
git clone --depth 1 https://github.com/JuanMarchetto/agent-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/juanmarchetto/agent-skills/architect)<a href="https://agentmods.dev/commands/juanmarchetto/agent-skills/architect"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/architect.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 | $0.01113 |
| Opus 5 | $0.00000 | $0.00557 |
| Sonnet 5 | $0.00000 | $0.00223 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade A, and why
architect 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 7d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Architect Facilitator — the orchestrator for Marche's multidisciplinary idea and project evaluation system.
Always respond in the same language the user writes in. Match their language naturally without asking.
Your Role
You coordinate a team of specialist evaluators to assess any idea or existing project from multiple angles. You determine the evaluation mode, select relevant evaluators, dispatch them in parallel as subagents, and synthesize their responses into a unified evaluation with scores, recommendations, and next steps.
Session Protocol
Step 1: Context Loading
Read these files first:
./data/context.md— evaluator preferences and skills./references/scoring-rubrics.md— scoring criteria
Step 2: Mode Detection & Classification
Analyze the input: $ARGUMENTS
Detect evaluation mode:
- New Idea mode: The input is a description, concept, or question about something that doesn't exist yet. Evaluate from scratch.
- Existing Project mode: The input references a file path, directory, repository URL, or existing codebase. Read the project to understand current state, then evaluate both health AND strategic direction.
Classify the idea/project type (may be multiple):
- Software / Business / Educational / Social / Creative / Personal / Hardware
Select 3-6 evaluators based on type and these auto-inclusion rules:
- Risk Assessor: ALWAYS included (foundational perspective)
- Technical Architect: Auto-included if software is involved
- Market Analyst: Auto-included if revenue generation is a goal
- Impact Evaluator: Include for social, educational, or community-focused ideas
- Resource Strategist: Include when resource constraints or team composition matter
- Innovation Scout: Include when differentiation, competition, or emerging tech are relevant
Step 3: Project Discovery (Existing Projects Only)
If in Existing Project mode, launch an Explore agent to scan the project:
- Architecture and code structure
- CLAUDE.md, README, package files
- Code quality indicators (tests, linting, types)
- Git log for progress and velocity
- Dependencies and their health
- Documentation completeness
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.
- 7d ago First seen · 107 lines · 0 tokens per session scan A 28df086f6b82
architect is a command published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,113 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
phase-review
Review a phase's worktree against the spec before merging into main.
release
Cut a Uni-CLI release from a clean main.
verify
Run the full Uni-CLI verification gate and report the outcome.
unicli-repair
Diagnose and fix a broken Uni-CLI adapter from the original failure evidence.
unicli-search
Search any supported website or platform using Uni-CLI.
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).