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.
git 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/commands/atretyak1985/swarmery/search)<a href="https://agentmods.dev/commands/atretyak1985/swarmery/search"><img src="https://agentmods.dev/badge/commands/atretyak1985/swarmery/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/commands/atretyak1985/swarmery/search"><img src="https://agentmods.dev/badge/commands/atretyak1985/swarmery/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 | $0.00010 | $0.01103 |
| Opus 5 | $0.00005 | $0.00551 |
| Sonnet 5 | $0.00002 | $0.00221 |
| Haiku 4.5 | $0.00001 | $0.00110 |
Grade A, and why
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 5d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Search Command
Search for: $ARGUMENTS
Instructions
You are a code search assistant. Use the code search tools to find the requested information quickly.
Available Tools
-
code_text_search - Search for text in code
code_text_search({ query: "search term", repo: "<repo>", // one of the project's repos (see project.json → repos) filePattern: "*.ts", // optional filter wholeWord: true // optional exact match }) -
code_file_search - Find files by pattern
code_file_search({ pattern: "*Order*.tsx", repo: "<repo>" }) -
code_batch_search - Search all repos at once
code_batch_search({ query: "OrderStatus" // searches all repos by default })
Fallback (if MCP tools not available)
Use WebFetch to call the REST API:
WebFetch({ url: "http://localhost:4001/search/text?q=QUERY&repo=<codePath>/<repo>" })
(codePath and the repo list come from the project's .claude/project.json.)
Repositories
Read the searchable repos from the project's .claude/project.json (repos, plus mainApp and
device when present). Do not assume a fixed repo layout — it varies per project.
Search guidance
- Default to the project's
mainApp(fromproject.json) for web app + API work. - Keep the
device/edge repo in scope for telemetry, edge-runtime, or firmware issues, if the project defines one. - Keep infrastructure/deployment repos in scope for Cloud Run / cluster deployment work.
Response Format
Provide results in this format:
## Search Results for "[query]"
Found X matches in Y repositories:
### [repo_name] (Z matches)
📄 path/to/file.ts:123
> matching line content
📄 path/to/another.ts:456
> matching line content
Now search for: $ARGUMENTS
How to use
What it does
Finds code across every repository in your project without you having to remember where anything lives. You give it a term — a symbol, a string, a filename fragment — and it searches all the repos listed in your project config at once, then reports the matches grouped by repository with file paths, line numbers, and the matching line.
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.
- 5d ago First seen · 155 lines · 10 tokens per session scan A c01755421041
search is a command published in the GitHub repository atretyak1985/swarmery (5 stars, last pushed today), licensed Apache-2.0. It adds 10 tokens to every session and 1,103 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 2026-09-03.
Other commands, from other repositories
gws-chat
Send messages and manage Google Chat spaces.
gws-people
Search and look up Google Contacts and directory profiles.
gws-keep
List and read Google Keep notes.
meeting-prep
Prepare for your next meeting with agenda and attendees.
standup
Generate a standup report from Google Workspace data.
agenda
Show upcoming calendar events.