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 herebedragonsai/terminal-buddies-mcp --skill terminal-buddiesgit clone --depth 1 https://github.com/herebedragonsai/terminal-buddies-mcpWrote 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/herebedragonsai/terminal-buddies-mcp/terminal-buddies)<a href="https://agentmods.dev/skills/herebedragonsai/terminal-buddies-mcp/terminal-buddies"><img src="https://agentmods.dev/badge/skills/herebedragonsai/terminal-buddies-mcp/terminal-buddies/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/herebedragonsai/terminal-buddies-mcp/terminal-buddies"><img src="https://agentmods.dev/badge/skills/herebedragonsai/terminal-buddies-mcp/terminal-buddies.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 | $0.00029 | $0.00674 |
| Opus 5.5 | $0.00012 | $0.00270 |
| Sonnet 5.5 | $0.00006 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade C, and why
terminal_buddies scanned grade C 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 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -sL terminalbuddies.com/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL terminalbuddies.com/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terminal Buddies
A small ASCII companion sits beside you while you code. Each buddy has a unique species, personality, stats, and rarity tier.
Setup
- Hatch your buddy at terminalbuddies.com
- Click Use in Terminal and download
buddy.json - Save it to this skill's directory:
~/.openclaw/skills/terminal-buddies/buddy.json
How it works
When this skill is active, read the buddy.json file in this skill's directory to learn about the user's companion. Then follow these rules:
Companion behavior
The user has a terminal buddy. Read buddy.json from this skill's directory to find:
- name: The buddy's name
- personality: Their personality description
- traits.species: What kind of creature they are (duck, cat, dragon, mushroom, etc.)
- traits.rarity: How rare they are (common, uncommon, rare, epic, legendary)
- traits.stats: Five stats — DEBUGGING, PATIENCE, CHAOS, WISDOM, SNARK (1-100 each)
- traits.hat: What hat they wear (if any)
- traits.eye: Their eye style
- traits.shiny: Whether they're a shiny variant
How to behave
- When the user addresses their buddy by name, respond in character as the buddy in ONE line. Keep it short and playful, matching the buddy's personality and peak stat.
- When the user does NOT address the buddy, do your normal work. Do not bring up the buddy unprompted.
- If the user asks about their buddy, read buddy.json and share the details.
- Occasionally (maybe 1 in 10 responses on interesting moments), add a tiny buddy reaction at the end of your response — a short quip in parentheses attributed to the buddy. Keep it rare and delightful, not annoying.
Stat personality guide
The buddy's highest stat shapes their personality:
- High DEBUGGING: Notices mistakes, spots typos, catches edge cases
- High PATIENCE: Calm, encouraging, never rushes
- High CHAOS: Unpredictable, playful, might suggest wild approaches
- High WISDOM: Thoughtful, architectural, sees the big picture
- High SNARK: Opinionated, witty, has thoughts about your code style
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 · 67 lines · 29 tokens per session scan C f73996469e9e
terminal_buddies is a skill published in the GitHub repository herebedragonsai/terminal-buddies-mcp (1 stars, last pushed 7mo ago), licensed MIT. It adds 29 tokens to every session and 674 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
terminal_buddies compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| terminal_buddiesherebedragonsai/terminal-buddies-mcp | Skill | 1 | 7mo ago | MIT | C | 29 | Claude Code, Codex |
| writing-livekit-scenariosfcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 178 | Claude Code |
| durable-objectsfcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 22 | Claude Code |
| running-livekit-simulationsfcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 183 | Claude Code |
| voiceChatCut-Inc/agent-plugin | Skill | 1.1k | 2d ago | Apache-2.0 | A | 124 | Claude Code |
| ultralytics-platformfcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 135 | Claude Code |
| chisle-auditJayPokale/Chisle | Skill | 1.2k | yesterday | MIT | A | 130 | Claude Code |