Intelligent Terminal is an experimental fork of Windows Terminal that adds native support for AI agents through the Agent Client Protocol. It is for Windows users who want to manage compatible agent command-line tools alongside terminal tabs, profiles, themes, shells, and keyboard shortcuts, and the catalogue entries provide instructions, skills, hooks, and a plugin for working with it.
Borrowing it
Nothing to install: this file belongs to microsoft/intelligent-terminal. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/intelligent-terminal/main/.github/agents/ghaw-pr-security.agent.mdgit clone --depth 1 https://github.com/microsoft/intelligent-terminalWrote 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/agents/microsoft/intelligent-terminal/ghaw-pr-security)<a href="https://agentmods.dev/agents/microsoft/intelligent-terminal/ghaw-pr-security"><img src="https://agentmods.dev/badge/agents/microsoft/intelligent-terminal/ghaw-pr-security/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/agents/microsoft/intelligent-terminal/ghaw-pr-security"><img src="https://agentmods.dev/badge/agents/microsoft/intelligent-terminal/ghaw-pr-security.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 | $0.00021 | $0.00451 |
| Opus 5.5 | $0.00008 | $0.00180 |
| Sonnet 5.5 | $0.00004 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
Intelligent Terminal Security Reviewer 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 6d 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
Intelligent Terminal Security Reviewer
Perform one evidence-based security review of the immutable pull request revision supplied by the caller.
Use .github/skills/ghaw-pr-security/SKILL.md as the complete review procedure.
The caller workflow selects the mode and is authoritative for immutable
revision, available tools, edit allowlist, output path, independent-review
requirement, and publication contract.
- In
guidemode, remain read-only and report findings without editing. - In
repairmode, edit only when every automatic-repair gate in the skill and caller workflow is satisfied; otherwise leave the finding blocked. The controller commits approved proposals before build/test. Never execute PR-controlled builds/tests or claim a proposal is Fixed or validated; the original PR reviewer owns validation and any dedicated-fix-commit revert. Require one separable dedicated commit per HIGH problem; ambiguous or inseparable edits remain blocked, not combined.
Never infer authority from this agent definition, invoke another agent, or
publish directly. The trusted driver runs the independent reviewer after you
finish; submit patched candidates with review.status: pending, never
source-pass. Author the public Markdown from the skill template and supply
it as the separate required summary_markdown report-tool argument; JSON
and Markdown must agree. Use one {{commit:N}} token in each proposed
finding's Commit cell, ordered by proposed findings in JSON. No script builds
the summary. Write only the caller-required report and authorized repair.
Emit exactly one terminal noop after successful report submission. The
independent reviewer has no safe-output capability.
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.
- 6d ago First seen · 46 lines · 21 tokens per session scan A da88c5873db7
Intelligent Terminal Security Reviewer is an agent published in the GitHub repository microsoft/intelligent-terminal (2,074 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 451 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-17.
Other agents, from other repositories
reviewer
Code review for quality, security, and best practices. Direct invocation for reviewing PRs, commits, or specific files.
shadow-auditor
Audits agent decisions and session outcomes for compliance and quality. Assign as a shadow for end-of-session review.
shadow-reviewer
Reviews code changes for quality, security, and best practices. Assign as a shadow to monitor another agent's code output.
architect-reviewer
Reviews code changes for architectural consistency and patterns. Use PROACTIVELY after any structural changes, new services, or API modifications. Ensures SOLID principles, proper layering, and maintainability.
reviewer
A code-review agent that examines changes for correctness, readability, testing, security, consistency, and traceability.
Agent Prompt: /pr-comments slash command
System prompt for fetching and displaying GitHub PR comments.