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 skills add RayforceDB/raysense --skill querygit clone --depth 1 https://github.com/RayforceDB/raysenseWrote 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/skills/rayforcedb/raysense/query)<a href="https://agentmods.dev/skills/rayforcedb/raysense/query"><img src="https://agentmods.dev/badge/skills/rayforcedb/raysense/query/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rayforcedb/raysense/query"><img src="https://agentmods.dev/badge/skills/rayforcedb/raysense/query.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00181 | $0.04265 |
| Opus 5.5 | $0.00072 | $0.01706 |
| Sonnet 5.5 | $0.00036 | $0.00853 |
| Haiku 4.5 | $0.00018 | $0.00426 |
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 1mo 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 — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Query
raysense_baseline_query evaluates a Rayfall expression against a
single baseline table, which is bound to the symbol t before
evaluation. The result must itself be a RAY_TABLE. Wrap scalar /
column queries with select to keep the result tabular.
Use this when the question shape isn't covered by the dedicated tools.
For pure paginate / filter / sort, prefer raysense_baseline_table_read
(no Rayfall needed). For graph-shaped questions (blast radius, cycles),
prefer raysense_blast_radius / raysense_cycles.
Inputs
raysense_baseline_query
path: <absolute repo root, defaults to cwd>
table: one of files | functions | imports | calls | call_edges
| types | hotspots | rules | module_edges | changed_files
| file_ownership | temporal_hotspots | file_ages
| change_coupling | inheritance | entry_points | health
| meta
rayfall: Rayfall source, e.g. "(select {from: t where: (> lines 500)})"
Call raysense_baseline_tables first if you are unsure what is saved
(empty / missing tables fail loudly rather than silently).
Schema cheat sheet
The columns most agents ask about. For the full list, query the table
once with t (no filter) and read the column names off the result.
- files:
file_id i64,path str,language str,module str,lines i64,bytes i64,content_hash str - functions:
function_id i64,file_id i64,name str,start_line i64,end_line i64 - calls:
call_id i64,file_id i64,caller_function i64,target str,line i64 - call_edges:
edge_id i64,call_id i64,caller_function i64,callee_function i64 - imports:
import_id i64,from_file i64,target str,kind str,resolution str,resolved_file i64 - hotspots:
file_id i64,path str,module str,fan_in i64,fan_out i64 - rules:
severity str,code str,path str,message str - module_edges:
from_module str,to_module str,edges i64 - change_coupling:
left str,right str,co_commits i64,coupling_strength_milli i64 - file_ownership:
path str,top_author str,top_author_commits i64,total_commits i64,author_count i64,bus_factor i64 - meta:
schema_version i64,raysense_version str,rayforce_version str,repo_sha str,snapshot_id str,scan_unix i64,column_digest str
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.
- 1mo ago First seen · 396 lines · 181 tokens per session scan A 26d52444d02b
query is a skill published in the GitHub repository RayforceDB/raysense (13 stars, last pushed 5mo ago), licensed MIT. It adds 181 tokens to every session and 4,265 once invoked, about $0.0007 per session on Opus 5.5. 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
codebase-refactoring
Three-part workflow to improve overall codebase health with jscpd — find and fix duplicated code, find and remove or refactor dead code, then find and simplify the largest/most complex files. Starts from --dashboard/--health to prioritize and ends by re-measuring the score.
recipe-diagnose
Investigate problem, verify findings, and derive solutions.
dorodango
Polishes working code through successive quality passes in fresh subagents. Use after tests pass when code needs multi-dimension refinement before release.
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:using-assert
Using lib-observability/assert, Lerian's runtime assertion package, in two modes. Sweep Mode detects panic()/log.Fatal zero-panic violations, DIY invariant checks, hand-rolled domain predicates, and missing InitAssertionMetrics. Reference Mode catalogs the asserter lifecycle, domain predicates, observability trident…
refactoring
Apply Martin Fowler-inspired refactoring rules when improving existing code structure while preserving observable behavior.