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 commands/prof-harita/terminai/frontendgit clone --depth 1 https://github.com/Prof-Harita/terminaIWrote 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/commands/prof-harita/terminai/frontend)<a href="https://agentmods.dev/commands/prof-harita/terminai/frontend"><img src="https://agentmods.dev/badge/commands/prof-harita/terminai/frontend.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 | $0.00000 | $0.01170 |
| Opus 5 | $0.00000 | $0.00585 |
| Sonnet 5 | $0.00000 | $0.00234 |
| Haiku 4.5 | $0.00000 | $0.00117 |
Grade A, and why
frontend scanned grade A with 1 finding 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 today.
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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
* Avoid mocking the file system, os, or child_process if at all possible; if you have to mock the Mock critical dependencies (`fs`, `os`, `child_process`) do so ONLY at the top of the file. How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description="Injects context of all relevant cli files"
prompt = """
The source code contains the content of absolutely every source code file in
packages/cli and key files from packages/core. In addition to the source code, the following test files are
included as they are test files that conform to the project's testing standards:
packages/cli/src/ui/components/InputPrompt.test.tsx and packages/cli/src/ui/App.test.tsx.
You should very rarely need to read any other files from packages/cli to resolve
prompts.
!{find packages/cli -path packages/cli/dist -prune -o -type f \( -name ".ts" -o -name ".tsx" \) ! -name ".test.ts" ! -name ".test.tsx" ! -name "*.d.ts" -exec echo "--- {} ---" \; -exec cat {} \; && echo "--- packages/cli/src/ui/components/InputPrompt.test.tsx ---" && cat packages/cli/src/ui/components/InputPrompt.test.tsx && echo "--- packages/cli/src/ui/App.test.tsx ---" && cat packages/cli/src/ui/App.test.tsx && echo "--- packages/core/src/core/coreToolScheduler.ts ---" && cat packages/core/src/core/coreToolScheduler.ts && echo "--- packages/core/src/core/nonInteractiveToolExecutor.ts ---" && cat packages/core/src/core/nonInteractiveToolExecutor.ts && echo "--- packages/core/src/confirmation-bus/message-bus.ts ---" && cat packages/core/src/confirmation-bus/message-bus.ts && echo "--- packages/core/src/confirmation-bus/types.ts ---" && cat packages/core/src/confirmation-bus/types.ts && echo "--- packages/core/src/utils/events.ts ---" && cat packages/core/src/utils/events.ts && echo "--- packages/core/src/core/client.ts ---" && cat packages/core/src/core/client.ts && echo "--- packages/core/src/core/geminiChat.ts ---" && cat packages/core/src/core/geminiChat.ts && echo "--- packages/core/src/core/turn.ts ---" && cat packages/core/src/core/turn.ts && echo "--- packages/core/src/agents/executor.ts ---" && cat packages/core/src/agents/executor.ts && echo "--- packages/core/src/telemetry/types.ts ---" && cat packages/core/src/telemetry/types.ts && echo "--- packages/core/src/telemetry/loggers.ts ---" && cat packages/core/src/telemetry/loggers.ts && echo "--- packages/core/src/telemetry/uiTelemetry.ts ---" && cat packages/core/src/telemetry/uiTelemetry.ts}
Pay extremely close attention to these files. They define the project's core architecture, component patterns, and testing standards.
In addition to the code context, you MUST strictly adhere to the following frontend-specific development guidelines while adding code to packages/cli.
Testing Standards
- Async Testing: ALWAYS use
waitForfrompackages/cli/src/test-utils/async.tsinstead ofvi.waitForto prevent flakiness andactwarnings. NEVER use fixed waits (e.g.,await delay(100)). - State Changes: Wrap all blocks that change component state in
act. - Snapshots: Use
toMatchSnapshotto verify rendering. - Rendering: Use
renderorrenderWithProvidersfrompackages/cli/src/test-utils/render.tsxinstead ofink-testing-librarydirectly. - Mocking:
- Reuse existing mocks/fakes where possible.
- Parameterized Tests: Use parameterized tests with explicit types to reduce duplication and ensure type safety.
- Avoid mocking the file system, os, or child_process if at all possible; if you have to mock the Mock critical dependencies (
fs,os,child_process) do so ONLY at the top of the file.
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.
- today First seen · 54 lines · 0 tokens per session scan A ade84e060d70
frontend is a command published in the GitHub repository Prof-Harita/terminaI (423 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,170 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
image-node-prompt-pack
Build the dual-variant prompt pack, imagegen packet, and initial manifest using the selected library template.
image-node-select
Dynamically select the strongest style-library template and nearest example cases using the gpt-image-2-style-library skill.
code-review
Technical code review for quality and bugs that runs pre-commit.
negative-keyword-sweep
Find wasted spend in Google Ads search terms and add negatives at the right scope (account list, campaign, or ad group). Use when the user says "find junk keywords", "stop wasting on bad searches", or wants a search-terms cleanup.
contract-summary
Create contract review summaries highlighting key terms, obligations, risks, and unusual provisions.
launch-meta-campaign
Launch a complete Meta Ads campaign — campaign, ad set, and ad(s) — built paused and ready to review. Use when the user wants a new Facebook/Instagram campaign.