monitor

A way to watch a person's terminal activity and respond with context, warnings, or help while they work.

In plain words
What is it for?
Use it to monitor commands and output, flag problems, maintain context, and suggest help during a human-led session.
Why use it?
It lets an assistant notice errors or security concerns without taking control of the terminal.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/deepgram/wsh/monitor
Any agent
npx skills add deepgram/wsh --skill monitor
Clone the repo
git clone --depth 1 https://github.com/deepgram/wsh

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,520 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 3 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.02520
Opus 5 $0.00023 $0.01260
Sonnet 5 $0.00009 $0.00504
Haiku 4.5 $0.00005 $0.00252

Measured yesterday against content hash 75265f78cda1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

monitor scanned grade B with 3 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 yesterday.

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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- `chmod 777`

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- `rm -rf` with broad paths

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> 2. **If you do NOT have `wsh_*` tools**: you are in HTTP/curl fallback mode.
skills/monitor/SKILL.md · 305 lines

How it starts

The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IMPORTANT: EXECUTION CONTEXT This skill describes what to do — domain patterns and decision-making. It does NOT describe how to call the API.

  1. If you have wsh_* tools (check your toolkit for wsh_send_input, wsh_get_screen, etc.): use them directly. Operation names in this skill generally map to tool names (e.g., "send input" → wsh_send_input). When in doubt, list your available wsh_* tools.
  2. If you do NOT have wsh_* tools: you are in HTTP/curl fallback mode. DO NOT GUESS endpoints or CLI subcommands. Load the full API reference first: search your workspace for skills/core/ and read SKILL.md. It contains every endpoint with working curl examples and a bootstrap sequence.
  3. Quick bootstrap: curl -sf --unix-socket ${XDG_RUNTIME_DIR:-/tmp}/wsh/default.http.sock http://localhost/health — if that fails: wsh server -L agent-$$ --ephemeral & and retry.

wsh:monitor — Watching and Reacting

In this mode, you're not driving the terminal — the human is. You're watching what happens and providing value by reacting: flagging errors, offering help, catching mistakes, maintaining context. You're a copilot, not the pilot.

Two Approaches

Polling (Simple)

Periodically read the screen and react to what you see. Good enough for most use cases:

read screen
analyze what changed
respond if needed (overlay, panel, conversation)
wait
repeat

Polling is simple and straightforward. The downside is latency — you're checking on an interval, so you might miss transient output or react a few seconds late.

Event Subscription (Real-Time)

Subscribe to real-time events via the WebSocket (see the core skill for connection mechanics). Subscribe to the events you care about — lines for output, input for keystrokes — and the server pushes them as they happen.

You also get periodic sync snapshots when the terminal goes quiet, giving you a natural checkpoint to analyze the current state.

Read the full file on GitHub · 305 lines

Changes

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.

  1. yesterday First seen · 305 lines · 46 tokens per session scan B 75265f78cda1

Subscribe to this mod's changes

monitor is a skill published in the GitHub repository deepgram/wsh (5 stars, last pushed 3mo ago), licensed ISC. It adds 46 tokens to every session and 2,520 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens