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 skills/wingedguardian/genesis-agi/code-intelligencenpx skills add WingedGuardian/GENesis-AGI --skill code-intelligencegit 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 | $0.00037 | $0.00410 |
| Opus 5 | $0.00018 | $0.00205 |
| Sonnet 5 | $0.00007 | $0.00082 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
code-intelligence 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.
What it actually says
Code Intelligence Tool Selection
| Need | Tool | Example |
|---|---|---|
| Package/module overview | codebase_navigate MCP (L0→L1→L2) |
"What packages exist?" |
| Symbol definition/signature | Serena find_symbol |
"Where is Router defined?" |
| Who calls/references X | Serena find_referencing_symbols |
"Who calls _set_output?" |
| File symbol overview | Serena get_symbols_overview |
"What's in engine.py?" |
| What breaks if I change X | GitNexus impact |
"Blast radius of renaming Router" |
| End-to-end execution flow | GitNexus query |
"How does task submission work?" |
| Architecture/clusters | GitNexus context or clusters resource |
"What's in the memory package?" |
| String pattern / non-Python | Grep | "Find all TODO comments" |
| File by name | Glob | "Find all *_hook.py files" |
Escalation Path
Start cheap, escalate as needed:
codebase_navigatefor orientation (always available, fast)- Serena for precise symbol work (LSP-powered, Python-only)
- GitNexus for relationships and impact (knowledge graph, needs index)
- Grep/Glob for everything else
Availability
- Serena: Always available. 1-2s init per session.
- GitNexus: Requires index. Check freshness:
npx gitnexus status. PostToolUse hook auto-detects staleness after commits. codebase_navigate: Always available (Genesis health MCP).
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 · 37 lines · 37 tokens per session scan A 2bba3d550de1
code-intelligence is a skill published in the GitHub repository WingedGuardian/GENesis-AGI (93 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 410 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 skills, from other repositories
survey-methodology
Plan-time methodology contract for survey/review/report projects. Forces an audit-grade survey instead of a paper-trust summary. Distilled from 240 reviews (2024-2026) across 9 domain clusters — physics/RMP/Living Reviews, chemistry/materials, biology/medicine narrative + Cochrane SRs, CS/ML/AI, math/Acta Numerica…
review
Write domain-authentic review articles that synthesize rather than stack. Covers 10 scientific domains (physics, chemistry, biology, medicine, mathematics, computerscience, earthenvironment, astronomy, economics, materials) with per-domain style guides mined from landmark reviews in RMP / Nat. Rev. X / Annu. Rev. /…
search
Unified academic paper search, citation chains, paper download (arXiv LaTeX/PDF, Sci-Hub), figure extraction from papers, LaTeX source reading, BibTeX fetching, web search, and browser automation for Cloudflare-protected sites (PRL, Science, Nature, Google Scholar).
qec-construct
Verifier-in-the-loop CONSTRUCTION of quantum error-correcting codes with transversal non-Clifford gates (CCZ/T). Applies whenever the project goal is a new or better code/construction — INCLUDING search-phrased goals ("find codes beating X"), where the construct-loop (propose algebraic rule → qverify → debug) is the…
venue-specific
Venue-specific formatting requirements for academic journals and conferences across all disciplines. Covers Nature, Science, Cell, PRL, NEJM, Lancet, JACS, NeurIPS, ICML, and 30+ top venues. Use when writing, formatting, or checking a paper for a specific target venue.
figure
Hybrid figure pipeline (Nano Banana raster + rembg background removal + TikZ vector assembly). Includes a TikZ template library covering quantum circuits (quantikz), Feynman diagrams (tikz-feynman), circuits (circuitikz), molecules (chemfig), 2D/3D plots (pgfplots), energy-level diagrams, phase-space trajectories…