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.
npx skills add agentproto/ts --skill ap-terminalgit clone --depth 1 https://github.com/agentproto/tsWrote 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/agentproto/ts/ap-terminal)<a href="https://agentmods.dev/skills/agentproto/ts/ap-terminal"><img src="https://agentmods.dev/badge/skills/agentproto/ts/ap-terminal/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/agentproto/ts/ap-terminal"><img src="https://agentmods.dev/badge/skills/agentproto/ts/ap-terminal.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 | $0.00083 | $0.00993 |
| Opus 5.5 | $0.00033 | $0.00397 |
| Sonnet 5.5 | $0.00017 | $0.00199 |
| Haiku 4.5 | $0.00008 | $0.00099 |
Grade A, and why
ap-terminal 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 12d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Real PTY Terminals
When to use
Use ap-terminal when a task needs a genuine interactive terminal — a TUI
that repaints in place, a CLI that prompts step by step, or anything
expecting a real tty (raw mode, cursor control, paste detection). Batch,
non-interactive work belongs in command_execute (see ap-run-command), not
here.
MCP tool: terminal_start
Spawn a PTY running argv (e.g. ['bash'], or an interactive CLI directly).
Set cwd, a name/label for the session list, and cols/rows if the
TUI is picky about terminal size.
{
"tool": "terminal_start",
"args": {
"argv": ["claude"],
"cwd": "/Volumes/SSDExternalMacStudio/Code/products/agentik/agentik-studio/apps/simone",
"name": "simone-claude-tui",
"cols": 120,
"rows": 40
}
}
MCP tool: terminal_output
Read the current screen/buffer. clean: true strips ANSI escape codes for
readable text; lastBytes caps how much of the tail you pull back. The
buffer is a ring of roughly 64KiB — older output is gone once it rolls off.
{ "tool": "terminal_output", "args": { "sessionId": "term_4b91", "clean": true, "lastBytes": 4000 } }
MCP tool: terminal_input
Send keystrokes. text is sent verbatim (no implicit newline). Set
enter: true to additionally send an isolated carriage return AFTER the
text — required for paste-detecting TUIs that ignore a newline embedded in
pasted content.
{ "tool": "terminal_input", "args": { "sessionId": "term_4b91", "text": "/status", "enter": true } }
MCP tool: terminal_kill
Tear down the PTY when done or wedged.
{ "tool": "terminal_kill", "args": { "sessionId": "term_4b91" } }
MCP tool: terminal_sessions_list
List live terminal sessions. Without limit at most 50 rows come back; when
there are more, the reply carries total, truncated: true and a nextCursor
(pass it as cursor, with a limit, for the next page), or narrow with
onlyAlive / status.
{ "tool": "terminal_sessions_list", "args": {} }
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.
- 12d ago Changed · +3 lines f1f35760fbe8
- 1mo ago First seen · 107 lines · 83 tokens per session scan A 6627caa9e4df
ap-terminal is a skill published in the GitHub repository agentproto/ts (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 83 tokens to every session and 993 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
markedit-tools
Provides tools for managing MarkEdit, a macOS markdown editor.
deferred-task-execution
Delays execution of a task until a specified time or after a duration. Use when the user asks to run something later, in X minutes/hours, at a specific time, schedule a command, or defer work to a future point.
herdr
Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly asks to you use or configure Herdr.
glyph
Render an answer as ASCII art plus semantic emojis inline with no setup questions: one render per reply, verdict first. Use for any answer with shape: status, inventories, audits, budgets, comparisons, rankings, pipelines, 'what is using X', or any ad-hoc 'show me X visually' ask. Not for definitions, conceptual…
cocoplus-off
Deactivate Full Assist Mode — removes all CocoPlus feature flags. Data files (memory, meter history, grove patterns) are preserved. Idempotent.
wisdom-forget
Remove a must-keep CocoWisdom entry with rationale. Usage: $wisdom forget --id --rationale " ".