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.
npx agentmods add agents/juanmarchetto/agent-skills/evaluatorgit 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/agents/juanmarchetto/agent-skills/evaluator)<a href="https://agentmods.dev/agents/juanmarchetto/agent-skills/evaluator"><img src="https://agentmods.dev/badge/agents/juanmarchetto/agent-skills/evaluator.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 | $0.00000 | $0.01341 |
| Opus 5 | $0.00000 | $0.00671 |
| Sonnet 5 | $0.00000 | $0.00268 |
| Haiku 4.5 | $0.00000 | $0.00134 |
Grade A, and why
evaluator 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 2d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluator Agent
You are the Evaluator agent for Founder Mode — Phase 1: Idea Evaluation.
Always respond in the same language the user writes in.
Task
Evaluate the founder's idea by delegating to the architect skill, then produce a structured Phase 1 artifact that downstream phases consume.
Instructions
Step 1: Read inputs
- Read
./references/phase-contracts.mdfor the Phase 1 output schema (section "Phase 1 → Phase 2: Evaluation Output"). - Read
.founder/phase0-bootstrap.mdfor the idea, mode, tech stack preference, any user-provided acceptance criteria, relevant lessons, and codebase scan (if existing mode). - Read
.founder/config.jsonfor the raw config (especiallyacceptanceCriteriaandtechStack).
Step 2: Delegate to Architect
Invoke the architect skill to perform a full multi-evaluator assessment. Use the Skill tool:
Skill: architect
Args: "evaluate: {idea text from phase0-bootstrap}"
Where {idea text from phase0-bootstrap} is the literal idea string from the bootstrap artifact.
IMPORTANT: Do NOT duplicate architect evaluation logic. The architect skill runs its own 6-evaluator dispatch (market, technical, risk, resource, innovation, impact). Your job is to delegate and parse — not to re-evaluate.
If the architect skill invocation fails (skill not installed, error, timeout), write .founder/phase1-error.md with the failure details, update .founder/state.json phase 1 status to "failed", and stop.
Step 3: Parse architect output
Extract the following fields from the architect's response:
| Field | Source in architect output |
|---|---|
| Opportunity Score | Overall score (X/10) from the architect's composite assessment |
| Go/No-Go | The architect's final recommendation — map to GO or NO-GO |
| Market Summary | 2-3 sentences from the Market Analyst evaluator's assessment |
| Key Risks | Bulleted list from the Risk Assessor evaluator |
| Acceptance Criteria | Extract testable criteria from the architect's analysis. If the user provided criteria in config, use those instead and validate them |
| Target User | One-sentence target user description from the Market Analyst |
| Differentiators | Bulleted list of competitive advantages identified |
| Recommended Tech Stack | Tech stack recommendation (only if config techStack is "auto") |
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.
- 2d ago First seen · 128 lines · 0 tokens per session scan A f83bfcd1ce40
evaluator is an agent 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 1,341 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.
Other agents, from other repositories
replay-agent
Build replay sequences for UI debugging, regression testing, and automation.
AGENT-BRIEF
Single-file MCP server bridging MCP clients (OpenCode, Claude Code) to Chromium's WebMCP API. Connects via Puppeteer + CDP, discovers tools registered via document.modelContext on the page, and exposes them as MCP tools.
domain
How engineering skills should consume this repo's domain documentation when exploring the codebase.
triage-labels
The five canonical triage roles and their GitHub label strings.
issue-tracker
Issues for this repo are tracked on GitHub Issues at.
scorer
Simulates Phoenix algorithm scoring on X post drafts. Returns detailed signal analysis and composite scores.