Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/verivus-oss/sqrynpx agentmods add skills/verivus-oss/sqry/sqry-semantic-searchWrote 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/verivus-oss/sqry/sqry-semantic-search)<a href="https://agentmods.dev/skills/verivus-oss/sqry/sqry-semantic-search"><img src="https://agentmods.dev/badge/skills/verivus-oss/sqry/sqry-semantic-search/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/verivus-oss/sqry/sqry-semantic-search"><img src="https://agentmods.dev/badge/skills/verivus-oss/sqry/sqry-semantic-search.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 | $0.00054 | $0.06277 |
| Opus 5.5 | $0.00022 | $0.02511 |
| Sonnet 5.5 | $0.00011 | $0.01255 |
| Haiku 4.5 | $0.00005 | $0.00628 |
Grade E, and why
sqry-semantic-search scanned grade E with 3 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 10d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/verivus-oss/sqry/main/scripts/install.sh | bash -s -- --component all Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .sqry/graph .sqry/graphs .sqry/analysis Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/verivus-oss/sqry/main/scripts/install.sh | bash -s -- --component all How it starts
The opening of the file, as written. The whole thing — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sqry Semantic Code Search Skill
Routing rule: For structural code search (symbols, callers, callees, impact, dependencies), use sqry MCP tools when connected; otherwise use the sqry CLI from the workspace root. Use rg/grep only for literal text, and native file tools only for reading full files.
Use this skill when users ask to:
- find functions, classes, methods, variables, types, modules, or files by code structure;
- trace callers, callees, references, imports, inheritance, or call paths;
- analyze dependency impact, unused symbols, cycles, duplicates, or semantic diffs;
- understand a codebase through AST-backed graph facts instead of text guessing.
What Makes sqry Different
sqry uses "semantic" in the compiler sense. It parses code into ASTs, builds a graph of symbols and relationships, and answers structural queries from that graph. It is not an embedding search tool.
Current Version Target
This skill targets public verivus-oss/sqry v33.0.1. Its version numbers advance with each release; the figures below are maintained by hand, and the installed runtime is the source of truth (see below):
- 37 languages: 28 full-relation languages and 9 symbol-extraction languages. The released binaries compile 30 of them (29 enabled by default, JSON with
--include-high-cost);pulumi,puppet,salesforce-apex,sap-abap,servicenow-xanadu,servicenow-xmlandterraformare cargo features and a release binary rejects--enable-pluginfor them - 39 MCP tools standalone, 17-tool subset when daemon-hosted (see the tool table below)
- 6 MCP resources and 6 MCP prompts standalone, none when daemon-hosted
- snapshot format 17 (
sqry://meta/manifestsnapshot_format;snapshot.sqrystarts withSQRY_GRAPH_V17; distinct from the on-disk.sqry/graph/manifest.jsonsnapshot_format_version) - default MCP redaction preset:
minimal - default query timeout: 60s (
SQRY_MCP_TIMEOUT_MS=60000) - default index timeout: 600s (
SQRY_MCP_INDEX_TIMEOUT_MS=600000) - MCP protocol 2024-11-05 over stdio
- Rust 1.94+, Edition 2024
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.
- 10d ago First seen · 423 lines · 54 tokens per session scan E 3a4985f3ee14
sqry-semantic-search is a skill published in the GitHub repository verivus-oss/sqry (31 stars, last pushed 10d ago), licensed MIT. It adds 54 tokens to every session and 6,277 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it E with 3 findings (downloads and executes remote code, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-06.
Other skills, from other repositories
tilth
Use the tilth CLI for code reading, outlining, search, callers, blast-radius deps, and structural diffs. Activate when the user asks to explore a repo, find a symbol, trace callers, read a file, view a diff, or analyze impact. Prefer tilth over grep/cat/find/ls — one invocation returns AST-aware outlines, definitions…
cocosearch-debugging
Use when debugging an error, unexpected behavior, or tracing how code flows through a system. Guides root cause analysis using CocoSearch semantic and symbol search.
cocosearch-refactoring
Use when planning a refactoring, extracting code into a new module, renaming across the codebase, or splitting a large file. Guides impact analysis and safe step-by-step execution using CocoSearch.
cocosearch-deps
Use when exploring dependency relationships, tracing file connections, analyzing change impact, or identifying hub files. Guides dependency graph exploration using CocoSearch.
use-ivygrep
Gather focused local repository context with ivygrep before implementing, debugging, reviewing, or explaining code. Use for coding tasks involving unfamiliar paths, branch changes, stack traces, architectural relationships, callers, dependents, tests, configuration, or documentation. Prefer one bounded context pack…
dekko-verify
Sanity-check a suspiciously low or zero call-graph result from dekko (getcallers, getcallees, findusages, impactedtests, unused) before concluding "no callers" or "dead code," or a heritage/throws-provenance result (query supertypes, query subtypes, query throws) that labels something (external) when you expect it to…