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/atretyak1985/swarmery/code-searchnpx skills add atretyak1985/swarmery --skill code-searchgit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/code-search)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/code-search"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/code-search.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.00849 |
| Opus 5 | $0.00026 | $0.00425 |
| Sonnet 5 | $0.00010 | $0.00170 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
code-search 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Selects the most efficient search tool — Grep for exact symbol lookup, Glob for file-name patterns, codebase-retrieval for semantic/architectural questions — to locate code across the project's repositories (.claude/project.json → repos). Produces matching file paths with line numbers and context. Read-only, tool-selection skill. Placeholders: <mainApp>, <device>, <infrastructure-repo> come from project.json.
Rules (never violate)
- Grep for exact symbols, Glob for name patterns, codebase-retrieval for "how does X work?" — never swap them.
- Every result carries a
file:linecitation, never a bare file path; max 50 results per search. - Verify the top 2 codebase-retrieval results with Read; anything mismatched is marked
[POTENTIALLY-STALE], never presented as authoritative. - No hardcoded absolute paths, never search the filesystem root — scope to the workspace; repo names come from
.claude/project.json→repos. - Zero-result searches report the alternatives attempted before saying "not found".
- Refuse searches outside the project workspace; stop and ask on >50 results or an ambiguous query.
Resources
- Read
resources/search-procedure.mdwhen running a search — tool selection table, procedure, scope defaults, self-check, mistakes, escalation, failure modes. - Read
resources/query-patterns.mdwhen composing queries — per-repo Grep/Glob patterns and two worked examples.
How to use
What it does
Picks the right search tool for a lookup and runs it, so you stop guessing between exact match, file-name pattern, and "how does this work?". It classifies your query, scopes it to the most likely repository, runs Grep, Glob, or semantic retrieval, and returns matches with file:line citations and surrounding context. It never edits anything.
When to use it
- You need every occurrence of a function, type, or variable across the workspace.
- You need files following a naming convention: route handlers, test files, values files.
- You are starting a task cold, or have a natural-language question about a cross-repo data flow.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 66 lines · 52 tokens per session scan A 8f2986709c79
code-search is a skill published in the GitHub repository atretyak1985/swarmery (4 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 849 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
linkding
Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.
radicale
This skill should be used when managing calendars and contacts on a self-hosted Radicale CalDAV/CardDAV server. Use when the user asks to "list my calendar", "what's on my calendar this week", "show me my events", "when is my next event", "add to my calendar", "create an event", "schedule a meeting", "schedule an…
memos
Manage notes and memos in self-hosted Memos service. Use when the user asks to "save this to memos", "create a memo", "search my memos", "find notes about X", "what did I write about", "add a note", "capture this", "remember this", "save this thought", or mentions note-taking, knowledge management, or personal notes.
qbittorrent
Manage torrents with qBittorrent. Use when the user asks to "list torrents", "add torrent", "pause torrent", "resume torrent", "delete torrent", "check download status", "torrent speed", "qBittorrent stats", or mentions qBittorrent/qbit torrent management.
sabnzbd
Manage Usenet downloads with SABnzbd. Use when the user asks to "check SABnzbd", "list NZB queue", "add NZB", "pause downloads", "resume downloads", "SABnzbd status", "Usenet queue", "NZB history", or mentions SABnzbd/sab download management.
gws-quick-ref
Quick reference for gws CLI syntax — core patterns, key flags, pagination, field masks, and output formats.