| *Last synthesized: 2026-10-16 | 52 files | 8 concept pages | offline, zero tokens* |
Raw sources -> readmenator wiki -> links (Karpathy LLM Wiki Pattern, deterministic). Start here, then open one community page. Prefer grep over full reads.
The codebase centres on cJSON.h, aes.h, cJSON.c. Architecturally it is 4 layers, dominant utility (39 files) across 8 import-based communities. Recorded risk surface: 0 security findings and 0 dependency cycles.
Surprising tissue lives between root, include: cJSON, bof/include: 3 extracted cross-community imports and 17 inferred bridges. Follow connections.json sorted by strength before refactoring.
Open work clusters around documentation (44% file coverage), 0 security findings, 5 taint paths, and 5 suggested exploration questions in queries.md.
| Metric | Value |
|---|---|
| Files | 52 |
| Symbols | 1075 |
| Resolved imports | 43 |
| Languages | c, h, py, sh |
| Communities | 8 |
| Doc coverage | 44% (23/52 files) |
| Security findings | 0 |
| Estimated read cost | ~16954 tokens (chars/4, offline so $0) |
queries.md for the next question; log the answer there.grep -rn '<keyword>' index.md community_*.md
readmenator query "<question>" --target blacksandbeacon
| File | Score |
|---|---|
cJSON.h |
27.7 |
aes.h |
22.1 |
include/cJSON.c |
16.5 |
include/beacon_common.h |
15.7 |
beacon.h |
15.3 |
connections.json is machine-readable for GraphRAG pipelines.REPORT.md states what was extracted vs inferred and current limits.readmenator . --rebuild (no network, no tokens).