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/untra/operator/build-vscode-extensiongit clone --depth 1 https://github.com/untra/operatorWrote 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/untra/operator/build-vscode-extension)<a href="https://agentmods.dev/commands/untra/operator/build-vscode-extension"><img src="https://agentmods.dev/badge/commands/untra/operator/build-vscode-extension.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 | $0.00015 | $0.00382 |
| Opus 5 | $0.00008 | $0.00191 |
| Sonnet 5 | $0.00003 | $0.00076 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
build-vscode-extension 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 3d 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.
What it actually says
Build VS Code Extension
Build, validate, package, and install the vscode-extension subproject for local inspection. Stop immediately on any failure and report the error.
Workflow
Run each step sequentially from the vscode-extension/ directory. If any step fails, stop and report the failure clearly.
- Install dependencies:
cd vscode-extension && npm install - Lint:
cd vscode-extension && npm run lint - Compile:
cd vscode-extension && npm run compile - Test:
cd vscode-extension && npm test(note: requires a display environment for @vscode/test-electron; if tests fail due to missing display, report it and continue) - Package:
cd vscode-extension && npm run package(creates a.vsixfile via vsce) - Detect version:
cd vscode-extension && node -p "require('./package.json').version" - Install extension:
cd vscode-extension && code --install-extension ./operator-terminals-VERSION.vsix(substitute the detected version) - Report: Confirm the extension was installed successfully. Remind the user they must reload their VS Code window (
Developer: Reload Windowfrom the command palette) for changes to take effect.
Notes
- The
npm run compilestep runscopy-typesthentsc. - The
.vsixfilename follows the patternoperator-terminals-VERSION.vsix. - If
codeCLI is not on PATH, suggest the user install it via VS Code command palette: "Shell Command: Install 'code' command in PATH".
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.
- 3d ago First seen · 29 lines · 15 tokens per session scan A 8981644d5ea4
build-vscode-extension is a command published in the GitHub repository untra/operator (37 stars, last pushed 6d ago), licensed MIT. It adds 15 tokens to every session and 382 once invoked, about $0.0001 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 commands, from other repositories
spec-design
Create comprehensive technical design for a specification.
pm-auto-design2dev
設計レビューから実装完了まで完全自動化(設計レビュー→作業計画→TDD実装).
card
Open one self-contained OverClick card.
bug-fix
不具合の調査・対策案提示・修正実施を完全自動化.
wtfp:new-paper
Interview the researcher and initialize a portable WTF-P project.
setup_research_plan
Set up or start a research project.