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/evaluategit clone --depth 1 https://github.com/WingedGuardian/GENesis-AGIWhat 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 | $0.00041 | $0.01353 |
| Opus 5 | $0.00020 | $0.00677 |
| Sonnet 5 | $0.00008 | $0.00271 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
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 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.
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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technology & Intelligence Evaluation Framework
Purpose
Conduct rigorous, balanced evaluation of external technologies, tools, articles, and competitive developments against Genesis's architecture, design philosophy, and build roadmap. Produce actionable findings — not summaries.
Core Principle
Give the full picture. Do not undersell, do not be sycophantic. Think about how it could help, how it can't, and how maybe it /could/. Every finding gets the four-lens treatment before any conclusions are drawn.
Phase 1: Source Acquisition
Parallel Research
Fetch all sources simultaneously. Never serialize independent lookups.
Obstacle Exhaustion
When a source is inaccessible, exhaust all autonomous options before involving the user:
- Try the primary tool (WebFetch, scrape, direct access)
- Try alternative tools in the toolkit (Firecrawl, other MCP tools)
- Route to a different model/service that CAN access the content type:
- 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?"
Proactive Capability Surfacing
Even when a workaround succeeds, note the faster/better path for later. Example: "Resolved via Gemini, but authorizing Firecrawl would handle this and more."
Phase 2: Four-Lens Evaluation
Evaluate EVERY finding through all four lenses before drawing conclusions. Do not skip lenses or collapse them.
Lens 1: How It Helps
- Direct applicability to Genesis architecture, current phase, or planned phases
- Ready-to-use tools, libraries, or integrations
- Validated patterns that confirm our design decisions
Lens 2: How It Doesn't Help
- Platform incompatibilities (OS, runtime, deployment model)
- Architectural misalignment with Genesis design philosophy
- Scope mismatch (solves a problem we don't have)
- Maturity or reliability concerns
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.
- 3d ago First seen · 160 lines · 41 tokens per session scan A 1e7683fbe96e
evaluate is a command published in the GitHub repository WingedGuardian/GENesis-AGI (93 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,353 once invoked, about $0.0002 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
phase-status
Report progress against the current phase in docs/phases.md.
add-adr
Create a new numbered Architecture Decision Record.
daily-log
Append entry to today's daily log.
review-prs
Check open PRs for human feedback before picking new work.
brief-refresh
Audit docs for staleness and contradictions, propose new features.
new-module
Scaffold a new module that registers with core.