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 agentmods add instructions/21pounder/terminalagent/gemini-mdgit clone --depth 1 https://github.com/21pounder/terminalAgentWrote 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/instructions/21pounder/terminalagent/gemini-md)<a href="https://agentmods.dev/instructions/21pounder/terminalagent/gemini-md"><img src="https://agentmods.dev/badge/instructions/21pounder/terminalagent/gemini-md.svg" alt="Measured on agentmods" 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 | $0.00768 | $0.00768 |
| Opus 5 | $0.00384 | $0.00384 |
| Sonnet 5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
terminalAgent GEMINI.md 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 4d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terminal Coding Agent (Gemini Context)
This document provides context for the Gemini AI agent to understand and interact with the Terminal Coding Agent project.
Project Overview
Name: Terminal Coding Agent Version: 5.0.0 Purpose: A terminal coding assistant powered directly by the official Claude Agent SDK. It enables natural language coding tasks and supports custom "Skills" defined via Markdown. Core Technology:
- Runtime: Node.js (TypeScript).
- Engine:
@anthropic-ai/claude-agent-sdk. - Skill System: Doc-based skills (Markdown definitions in
.claude/skills/).
Architecture & Design
This version (v5) moves away from custom tool loops and raw API calls, fully embracing the official SDK.
Key Components
src/index.ts: The CLI entry point.- Initializes the SDK
query()function. - Handles "Smart Input" (files references with
@, command completion). - Dynamically loads skills from
.claude/skillsdirectories.
- Initializes the SDK
- Skills System (
.claude/skills/):- Skills are defined as directories containing a
SKILL.mdfile. - The SDK reads these definitions and injects them as capabilities into the agent context.
- This allows for "Low-Code" skill creation (Prompt Engineering vs. Coding).
- Skills are defined as directories containing a
- UI (
src/ui/):- Custom TUI components for input, banners, and message formatting.
Usage
Interaction Modes
-
Natural Language:
- "Refactor src/index.ts to use a class."
- "Explain the authentication logic."
-
Skill Invocation:
- Slash commands (e.g.,
/deep-research,/code-migrate) are routed to the specific skill defined in.claude/skills/. - The agent uses the prompt instructions in
SKILL.mdto execute the task.
- Slash commands (e.g.,
-
File Context:
- Use
@filenameto explicitly attach files to the context (e.g., "Fix the bug in src/utils.ts").
- Use
Directory Structure
deepresearch/.claude/skills/: (User-defined) Collection of skill directories (e.g.,code-migrate/SKILL.md).src/index.ts: Main logic and SDK integration.ui/: UI components.
bin/: Executable entry points.
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.
- 4d ago First seen · 75 lines · 768 tokens per session scan A 9aa1782b90a2
terminalAgent GEMINI.md is an instructions file published in the GitHub repository 21pounder/terminalAgent (120 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 768 tokens to every session, about $0.0038 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.