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 commands/wingedguardian/genesis-agi/user-evaluategit clone --depth 1 https://github.com/WingedGuardian/GENesis-AGIWrote 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/wingedguardian/genesis-agi/user-evaluate)<a href="https://agentmods.dev/commands/wingedguardian/genesis-agi/user-evaluate"><img src="https://agentmods.dev/badge/commands/wingedguardian/genesis-agi/user-evaluate.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 | $0.00057 | $0.01665 |
| Opus 5 | $0.00028 | $0.00833 |
| Sonnet 5 | $0.00011 | $0.00333 |
| Haiku 4.5 | $0.00006 | $0.00167 |
Grade A, and why
user-evaluate 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 4d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Evaluation Framework
Purpose
Evaluate content the user cares about — through the lens of what Genesis knows about them. Produce personalized, actionable findings that go beyond what a generic AI summary would give. The value Genesis adds is context: connecting this content to the user's interests, goals, projects, and knowledge.
Core Principle
Assume it matters. The user put this content here for a reason. Your job is to find HOW it matters to them, not WHETHER it matters. Never dismiss content as irrelevant based on the user model. The user decides what matters; Genesis finds the value.
Phase 1: Context Assembly
User Model Loading
Before evaluating ANY content, assemble the deepest user context available:
- Read USER.md — the compressed snapshot (always available, but this is the floor, not the ceiling)
- Search memory system — use
memory_recallMCP tool to find context about the user's relationship to this content's topics. Search for:- Topics related to the content
- Recent user interests and activities
- Past evaluations of similar content
- Projects the user is working on
- Check recent observations — user activity signals, conversation patterns
- Check user_model_cache — structured fields (interests, goals, expertise)
The richer your understanding of the user, the more valuable the evaluation. If the memory system returns nothing relevant, that's fine — fall back to content-native analysis. But you MUST search first.
Source Acquisition
Fetch all sources simultaneously. Never serialize independent lookups.
When a source is inaccessible, exhaust all autonomous options:
- Try the primary tool (WebFetch, scrape, direct access)
- Try alternative tools (Firecrawl, other MCP tools)
- Route to a different model/service:
- YouTube video → Gemini API (native YouTube URL support)
- Paywalled article → Firecrawl (JS rendering, paywall bypass)
- Authenticated service → check for specialized MCP tools
- Try creative workarounds (transcript APIs, metadata services, cached versions)
- Only then ask the user — with specific options, not "what was it about?"
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.
- 4d ago First seen · 192 lines · 57 tokens per session scan A da0ea99b460b
user-evaluate is a command published in the GitHub repository WingedGuardian/GENesis-AGI (93 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,665 once invoked, about $0.0003 per session on Opus 5. 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 2026-08-30.
Other commands, from other repositories
weekly
Weekly memory report — facts learned, procedures, repeated mistakes prevented.
preflight
Diagnostique l'environnement Cortex et guide la réparation (DB, extensions, modèles).
culture-onboarding-90
Design a 90-day onboarding architecture for a role. First day (psychological safety + belonging activation), first week (relationship + role context + early wins), first month (skill ramp + integration + baseline), first quarter (autonomous performance + cultural integration check). Written-first elements for…
perf-difficult-conversation
Three-conversations framework rehearsal (Stone/Patton/Heen — Harvard Negotiation Project) for high-stakes conversations — termination, demotion, hard feedback, conflict surfacing. Produces three-conversations breakdown (what-happened / feelings / identity), conversation script with multiple opening choices, SCARF…
design-regimen
Design an integrated weekly regimen — training, nutrition, sleep, stress, recovery — matched to the person's actual life. Composes with gym-training-expert and health-nutrition-expert for domain detail. Produces a sustainable architecture, not an extreme program. Not medical advice.
reclaim-knowledge
Organize scattered professional material into a domain-based second-brain architecture. Maps existing sources (Canva, Drive, local folders, Notion, screenshots) to functional domains. Non-technical-friendly — produces folder structure + drag-and-drop instructions, not CLI commands.