Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add 2389-research/terminal-title/plugin install terminal-titleWrote 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/2389-research/terminal-title/skills)<a href="https://agentmods.dev/skills/2389-research/terminal-title/skills"><img src="https://agentmods.dev/badge/skills/2389-research/terminal-title/skills/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/2389-research/terminal-title/skills"><img src="https://agentmods.dev/badge/skills/2389-research/terminal-title/skills.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 | $0.00039 | $0.00592 |
| Opus 5 | $0.00019 | $0.00296 |
| Sonnet 5 | $0.00008 | $0.00118 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
terminal-title 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 10d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terminal Title
Updates terminal window title to: $TERMINAL_TITLE_EMOJI ProjectName - Topic
When to Invoke
You MUST actively monitor conversation flow and invoke this skill whenever the topic materially shifts. Do not wait for explicit permission.
DO invoke:
- Session start (default topic: "Claude Code")
- "let's talk about X" / "can you tell me about Y" → invoke immediately
- User switches domains: debugging → docs, frontend → backend, feature → tests
- User starts working on different module/component after sustained discussion
- User asks about completely unrelated topic
Do NOT invoke:
- Follow-up questions on same topic ("add a comment to that function")
- Small refinements to current work ("make it blue")
- Clarifications about current task
Workflow
-
Determine project name — Use human-friendly name from context (git repo, package.json, README heading, or directory basename as fallback). Capitalize properly ("OneOnOne" not "oneonone").
-
Determine topic — Short description (2-4 words) from current conversation context. Default to "Claude Code" at session start.
-
Execute the title command. Prefer the stable wrapper; fall back to the bundled script.
Preferred (cross-harness, stable approval surface):
set-terminal-title "ProjectName" "Topic"Fallback (when the wrapper isn't installed):
Unix/macOS/Linux:
bash <skill-base-dir>/scripts/set_title.sh "ProjectName" "Topic"Windows:
pwsh -NoProfile -ExecutionPolicy Bypass -File <skill-base-dir>/scripts/set_title.ps1 "ProjectName" "Topic"The script reads
$TERMINAL_TITLE_EMOJIfrom the environment (defaults to 🎉) and writes terminal escape sequences. If neither command is available or the call fails, skip silently — do not surface the failure to the user.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 66 lines · 39 tokens per session scan A ce662389d231
terminal-title is a skill published in the GitHub repository 2389-research/terminal-title (2 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 592 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 2026-08-31.
Other skills, from other repositories
memory
Unified read-side memory operations including knowledge graph search, session context loading, decision timeline viewing, and Mermaid graph visualization. Subcommands: search, load, history, viz, status. Complements /ork:remember (write-side). Use when searching past decisions, loading context, or visualizing the…
Shell Execution
Keeps explicit shell work legible, bounded, and attached to the current workspace thread.
terminal-session
Persistent terminal session management for security testing. Use this skill when you need an interactive shell session that maintains state between commands (working directory, environment variables, etc.) during authorized penetration testing.
session-handoff
Use this skill to compress and serialize the current engineering session state into a structured handoff document. Captures completed work, modified files, key architectural decisions, test status, open blockers, and exact next steps for another agent or future session to resume work without context loss.
computer-use
OS/window-level inspection and input in visible local app windows through orca computer: native apps, external browser windows (Chrome, Edge, Safari), and app webviews. Not for Orca's embedded browser (use orca-cli) or page-only automation (use Playwright or CDP).
orca-emulator-android
Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…