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/mits-pl/wovenpx agentmods add skills/mits-pl/wove/add-wshcmdWrote 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/mits-pl/wove/add-wshcmd)<a href="https://agentmods.dev/skills/mits-pl/wove/add-wshcmd"><img src="https://agentmods.dev/badge/skills/mits-pl/wove/add-wshcmd/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/mits-pl/wove/add-wshcmd"><img src="https://agentmods.dev/badge/skills/mits-pl/wove/add-wshcmd.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 | $0.00036 | $0.05867 |
| Opus 5 | $0.00018 | $0.02933 |
| Sonnet 5 | $0.00007 | $0.01173 |
| Haiku 4.5 | $0.00004 | $0.00587 |
Grade A, and why
add-wshcmd 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 9d 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 — 922 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a New wsh Command to Wave Terminal
This guide explains how to add a new command to the wsh CLI tool.
wsh Command System Overview
Wave Terminal's wsh command provides CLI access to Wave Terminal features. The system uses:
- Cobra Framework - CLI command structure and parsing
- Command Files - Individual command implementations in
cmd/wsh/cmd/wshcmd-*.go - RPC Client - Communication with Wave Terminal backend via
RpcClient - Activity Tracking - Telemetry for command usage analytics
- Documentation - User-facing docs in
docs/docs/wsh-reference.mdx
Commands are registered in their init() functions and execute through the Cobra framework.
Step-by-Step Guide
Step 1: Create Command File
Create a new file in cmd/wsh/cmd/ named wshcmd-[commandname].go:
// Copyright 2025, Command Line Inc.
// SPDX-License-Identifier: Apache-2.0
package cmd
import (
"fmt"
"github.com/spf13/cobra"
"github.com/wavetermdev/waveterm/pkg/wshrpc"
"github.com/wavetermdev/waveterm/pkg/wshrpc/wshclient"
)
var myCommandCmd = &cobra.Command{
Use: "mycommand [args]",
Short: "Brief description of what this command does",
Long: `Detailed description of the command.
Can include multiple lines and examples of usage.`,
RunE: myCommandRun,
PreRunE: preRunSetupRpcClient, // Include if command needs RPC
DisableFlagsInUseLine: true,
}
// Flag variables
var (
myCommandFlagExample string
myCommandFlagVerbose bool
)
func init() {
// Add command to root
rootCmd.AddCommand(myCommandCmd)
// Define flags
myCommandCmd.Flags().StringVarP(&myCommandFlagExample, "example", "e", "", "example flag description")
myCommandCmd.Flags().BoolVarP(&myCommandFlagVerbose, "verbose", "v", false, "enable verbose output")
}
func myCommandRun(cmd *cobra.Command, args []string) (rtnErr error) {
// Always track activity for telemetry
defer func() {
sendActivity("mycommand", rtnErr == nil)
}()
// Validate arguments
if len(args) == 0 {
OutputHelpMessage(cmd)
return fmt.Errorf("requires at least one argument")
}
// Command implementation
fmt.Printf("Command executed successfully\n")
return nil
}
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.
- 9d ago First seen · 922 lines · 36 tokens per session scan A 37bb6b38b1e4
add-wshcmd is a skill published in the GitHub repository mits-pl/wove (42 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 5,867 once invoked, about $0.0002 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
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
repo-hygiene
Use when the scheduled repo-hygiene workflow runs from GitHub Actions (or an operator dry-run) to scan the repository for small, certain docs/test/code hygiene issues and fix them as one batched branch.
coordinate
Coordinate a small team of Qwen Code teammates with enforced read-only workers, an optional worktree-pinned writer, shared tasks, peer messages, and existing Agent View tabs. Invoke explicitly with /coordinate.
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
telegram
Owner-only Telegram text bridge and Mini App gateway for the existing Ouroboros interface.