input-capture

A skill for temporarily taking control of keyboard input in a terminal. While active, the human's keystrokes are intercepted instead of reaching the shell.

In plain words
What is it for?
It is for approval prompts, terminal menus, and workflows that need to capture and process typed input.
Why use it?
It lets an agent request approval or guide a selection step without commands being entered accidentally.

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

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,338 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00047 $0.02338
Opus 5 $0.00023 $0.01169
Sonnet 5 $0.00009 $0.00468
Haiku 4.5 $0.00005 $0.00234

Measured 2d ago against content hash 25607462b227, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

input-capture scanned grade B with 2 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

Bad: capture → build UI → show prompt → wait

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/input-capture/SKILL.md · 315 lines

How it starts

The opening of the file, as written. The whole thing — 315 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:input-capture — Intercepting Keyboard Input

Input capture lets you temporarily take over the keyboard. While active, keystrokes from the human go to you instead of the shell. The terminal is frozen — nothing the human types reaches the PTY. You decide what to do with each keystroke.

The Mechanism

capture input       # grab the keyboard
# Keystrokes now go to subscribers, not the PTY
# Do your thing — build a menu, ask a question, etc.
release input       # give it back

The human can press Ctrl+\ at any time to toggle input capture. If input is in passthrough mode, Ctrl+\ enters capture. If input is already captured, Ctrl+\ releases it. This is a physical toggle — never disable it, never tell the human to avoid it. It's their escape hatch.

When the human presses Ctrl+\ to enter capture mode manually, this is a signal that they want to interact with you. If you don't already have overlays or panels visible, this is your cue to create UI elements and engage. Subscribe to mode change events to detect this.

Read the full file on GitHub · 315 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. 2d ago First seen · 315 lines · 47 tokens per session scan B 25607462b227

Subscribe to this mod's changes

input-capture is a skill published in the GitHub repository deepgram/wsh (5 stars, last pushed 3mo ago), licensed ISC. It adds 47 tokens to every session and 2,338 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (asks the agent to reveal its instructions, 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens