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/rayforcedb/raysense/querygit clone --depth 1 https://github.com/RayforceDB/raysenseWhat 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 | $0.00022 | $0.00298 |
| Opus 5 | $0.00011 | $0.00149 |
| Sonnet 5 | $0.00004 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
query 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 yesterday.
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
Answer the following structural question against the raysense baseline at $1:
$2
The first argument is the project path; everything after it is the question. If the project path is missing, treat it as the current working directory and the entire $ARGUMENTS as the question.
- Call
raysense_baseline_tableswithpath: $1to see the available tables and their columns. - Decide the query shape:
- Select (filter / project / aggregate) — for "files where X and Y" style questions.
- Graph algorithm (
.graph.pagerank,.graph.louvain,.graph.topsort,.graph.shortest_path,.graph.k_shortest,.graph.betweenness,.graph.closeness,.graph.bfs,.graph.mst) — for centrality, clustering, or reachability. - Datalog (transitive closure:
reaches,depends-on,tainted-by) — for declarative reachability.
- Call
raysense_baseline_querywithpath: $1and the chosen Rayfall expression.
Show the query you ran, then the result, then a one-line interpretation.
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.
- yesterday First seen · 20 lines · 22 tokens per session scan A ecfafa49adf6
query is a command published in the GitHub repository RayforceDB/raysense (11 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 298 once invoked, about $0.0001 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
brooks-audit
Run a Brooks-Lint architecture audit.
deploy
Deploy Solana program (devnet first, then mainnet).
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
commit-claude-config
Version the Solana AI Kit config in git (un-ignores .claude/, CLAUDE.md, .mcp.json, .gitmodules and commits them).
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
VibeGuard: ExecPlan
Long-term task execution plan — generates self-contained execution documents from SPEC, supports cross-session recovery.