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 5.5 | $0.00014 | $0.02347 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 4mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 5,867 once invoked, about $0.0001 per session on Opus 5.5. 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.
add-wshcmd compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| add-wshcmdmits-pl/wove | Skill | 42 | 4mo ago | Apache-2.0 | A | 36 | Claude Code, Codex |
| build-teaql-appteaql/teaql-agent-kit | Skill | 2.8k | 4d ago | MIT | A | 112 | Codex |
| context-exclusionteaql/teaql-agent-kit | Skill | 2.8k | 4d ago | MIT | A | 41 | Claude Code |
| context-lifecycleteaql/teaql-agent-kit | Skill | 2.8k | 4d ago | MIT | A | 51 | Claude Code |
| batch-apiQwenLM/qwen-code | Skill | 29k | today | Apache-2.0 | A | 51 | Claude Code |
| repo-hygieneQwenLM/qwen-code | Skill | 29k | today | Apache-2.0 | A | 48 | Claude Code, Codex |
| test-failure-explorerQwenLM/qwen-code | Skill | 29k | today | Apache-2.0 | A | 32 | Claude Code, Codex |