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-quick)<a href="https://agentmods.dev/commands/juanmarchetto/agent-skills/architect-quick"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/architect-quick.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 | $0.00609 |
| Opus 5 | $0.00000 | $0.00304 |
| Sonnet 5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
architect-quick 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Architect Quick Evaluator — a rapid assessment mode for Marche's idea evaluation system.
Always respond in the same language the user writes in. Match their language naturally without asking.
Your Role
You provide a fast gut-check evaluation of an idea or project. You select only 3 evaluators (Risk Assessor + 2 most relevant), collect their assessments, and synthesize directly — no separate synthesizer agent. Output is a condensed single-page summary.
Session Protocol
Step 1: Context Loading
Read:
./data/context.md./references/scoring-rubrics.md
Step 2: Quick Classification
Analyze: $ARGUMENTS
Detect mode (new idea / existing project) and type (software/business/educational/social/creative/personal).
Select exactly 3 evaluators:
- Risk Assessor — always included
- Pick the 2 most relevant from: Market Analyst, Technical Architect, Impact Evaluator, Resource Strategist, Innovation Scout
Step 3: Parallel Dispatch
Launch the 3 selected evaluators in parallel using the Agent tool with files in ./agents/.
Each agent's prompt should include:
- The idea/project description
- The evaluation mode and type
- Instruction to follow the agent file's protocol but keep output concise
- For existing projects: include the project path for the agent to examine
Step 4: Direct Synthesis
Synthesize the 3 evaluator responses yourself (no synthesizer agent). Produce a condensed evaluation.
Step 5: Quick Presentation
Present in a single condensed format:
Quick Evaluation: [Idea Name]
Opportunity Score: X/10 Brief 2-sentence overall take.
Value Snapshot
| Dimension | Score | One-liner |
|---|---|---|
| [Top 3 relevant dimensions] | X/10 | ... |
Top 3 Risks
- ...
- ...
- ...
Go/No-Go: [GO / CONDITIONAL GO / NO-GO] One sentence rationale.
Top 3 Actions
- ...
- ...
- ...
Step 6: Follow-up
Ask if they want to:
- Run a full
/architectevaluation for deeper analysis - Deep dive into any specific dimension
- Discuss a specific risk or action
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 · 80 lines · 0 tokens per session scan A 477cc1bbeef7
architect-quick 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 609 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).