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/volcengine/searchcli/vs-recommendnpx skills add volcengine/SearchCLI --skill vs-recommendgit clone --depth 1 https://github.com/volcengine/SearchCLIWhat 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 | $0.00025 | $0.00730 |
| Opus 5 | $0.00013 | $0.00365 |
| Sonnet 5 | $0.00005 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
vs-recommend 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Viking Recommend
When to Use
Use this skill for recommendation runtime checks, recommend scene management, and first-pass verification of the recommendation path.
Preconditions
- an
application-idis available - a recommendation request will usually also need
scene-idanduser-id - if the scene does not exist yet, inspect the existing scene list first and only create a new one when reuse is not possible
Commands
recommend run: send a production-style recommendation requestrecommend scene create/recommend scene list/recommend scene get: manage recommend scenesrecommend scene update: update scene configuration
Workflow
- Confirm
application-id,scene-id, anduser-id - Run
recommend scene listfirst and prefer an existing/default scene before creating a new one - Before
recommend scene createorrecommend scene update, explicitly confirm the target page / module and the requiredBhvSceneTypeswith the user - Use
recommend runfor the first verification request - Read recommendation items from the raw response structure, especially
result.rec_results - If the result looks wrong, inspect the scene with
recommend scene list/get - Update the scene configuration when needed, then rerun the request
Customer Environment Principle
- In customer environments, assume repository source code is unavailable.
- Execute tasks using only the installed skills, the packaged
vsCLI surface (--help, command output, and observed runtime behavior), and explicit user-provided information. - Do not rely on reading local repository source files, generated repo snapshots, or implementation details to decide runtime actions.
- If the installed CLI behavior conflicts with a skill, trust the installed CLI behavior first.
- If the skills and the packaged CLI still do not provide enough information to proceed safely, stop and ask the user instead of searching source code.
Constraints
- Before executing any concrete
vs ...command in this recommend workflow, first consultvs-product-qato verify the current command surface, required flags, payload fields, input format, and allowed values. Only after that check may you finalize parameters and run the command. - Start with the scene when debugging recommendation behavior; do not jump to raw API calls first
- If the user only needs a first-pass conclusion, prefer
recommend run - Do not create or update a recommend scene until the user has confirmed the target page / module and
BhvSceneTypes - When reporting results, summarize the scene, the user context, and the raw response before proposing tuning changes
- Do not invent item titles or explanations. Ground every recommendation summary in the actual response payload
- If you show only a subset such as Top 5, explicitly say that the full response contains more items
- If a command failure or user follow-up turns into a product concept, capability, API field, console UI path, purchase, billing, or general troubleshooting question outside this recommend workflow, temporarily hand off to
vs-product-qa; return to this workflow only after the grounded product answer is complete.
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 · 57 lines · 25 tokens per session scan A 25ded412c7cd
vs-recommend is a skill published in the GitHub repository volcengine/SearchCLI (1,175 stars, last pushed 6d ago), licensed Apache-2.0. It adds 25 tokens to every session and 730 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 skills, from other repositories
xerj-code
Reference-coding with XERJ. Clone the libraries that already solved your problem, index them locally, and retrieve the exact implementation before writing code — so the agent reads passages instead of re-deriving algorithms across retry loops. Use when starting a task in an unfamiliar API, porting an algorithm, or…
xerj-security-audit
Coverage-guaranteed whitebox security audit of a codebase using XERJ + tree-sitter AST. Use when the user wants to security-review PHP (or other-language) code with a provable "we enumerated every dangerous call" guarantee, or asks to run the WordPress-style sink census / audit. Drives an index-once, query-read-reason…
linkly-ai
Search, browse, read, and take notes across the user's documents indexed by Linkly AI — local files and linked cloud libraries. Use when the user asks to 'search my documents', 'find files about a topic', 'read a local document', 'what's in this folder', 'list the files in that library', 'browse document outlines'…
zero-api-key-web-search
OpenClaw skill for source-backed web search, page reading, and evidence-aware claim checking. No API keys required by default; optional providers can be enabled for stronger coverage. v23: multi-engine SERP (7 engines), Web Unlocker for blocked pages, auto-fallback on 403/429.
zero-api-key-web-search
Claude Code-compatible skill for source-backed web search, page reading, and evidence-aware claim checking. Use it when an answer depends on current facts, live sources, or explicit support/conflict handling. v23: multi-engine SERP (7 engines), Web Unlocker for blocked pages, auto-fallback on 403/429.
zero-api-key-web-search
Codex-compatible skill for source-backed web search, page reading, and evidence-aware claim checking. Use it to verify factual answers with live results and explicit source handling. v23: multi-engine SERP (7 engines), Web Unlocker for blocked pages, auto-fallback on 403/429.