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/skills/upstream-sync/SKILL.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/skills/microsoft/intelligent-terminal/upstream-sync)<a href="https://agentmods.dev/skills/microsoft/intelligent-terminal/upstream-sync"><img src="https://agentmods.dev/badge/skills/microsoft/intelligent-terminal/upstream-sync/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/microsoft/intelligent-terminal/upstream-sync"><img src="https://agentmods.dev/badge/skills/microsoft/intelligent-terminal/upstream-sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00139 | $0.02969 |
| Opus 5.5 | $0.00056 | $0.01188 |
| Sonnet 5.5 | $0.00028 | $0.00594 |
| Haiku 4.5 | $0.00014 | $0.00297 |
Grade A, and why
upstream-sync 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 1mo 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upstream Sync (microsoft/terminal → intelligent-terminal)
Cherry-pick commit-by-commit from https://github.com/microsoft/terminal
into this fork, preserving per-commit attribution, auto-skipping picks
that cancel each other out, and stopping cleanly the moment a
human-judgment conflict appears.
You — the agent reading this file — are the orchestrator. Each step
in the run is a single atomic call into one of the scripts/*.ps1 files.
There is intentionally no PowerShell driver, because every interesting
decision (build-fix vs. open stuck issue, retry vs. bail, finalize vs.
dry-run) wants LLM judgment the operator can audit in your transcript.
When to Use This Skill
- User asks to "sync upstream", "pull from microsoft/terminal", "catch up to upstream", or "run upstream sync".
- A scheduler invokes the agent on a weekly/daily cadence.
- The previous run left an
upstream-sync-stucklabeled issue open and the human has finished resolving the conflict — close the issue (that IS the lock-clear signal) and re-run.
When NOT to Use This Skill
- User wants a one-shot rebase of a single feature branch onto upstream — that's a normal
git rebase, not this skill. - An
upstream-sync-stucklabeled issue is open onmicrosoft/intelligent-terminal— do not re-run; resolve the conflict on the stuck branch first, then close the issue.
Prerequisites
git2.38+ (forcherry-pick --keep-redundant-commits),ghCLI authenticated againstmicrosoft/intelligent-terminal(needs push toupstream-sync/*topic branches + issue/label create), PowerShell 7+ (pwsh) on PATH.originMUST point atmicrosoft/intelligent-terminal. All scripts push tooriginand pass-R microsoft/intelligent-terminalexplicitly. Verify withgit remote -vbefore running.- Full git history on
origin/main(no shallow clone). Watermark discovery walks up to 5000 commits scanning forcherry picked from commit <sha>trailers. In CI, useactions/checkout@v4withfetch-depth: 0. - Windows build host with Visual Studio 2022, Windows SDK,
vswhere, andtools\razzle.cmd/bz. Build is a hard gate before finalize. - No
state.jsonto bootstrap. Watermark = newest(cherry picked from commit <sha>)trailer onorigin/main. If the fork has never usedcherry-pick -x, run the one-time First-time sync.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/03-conflict-triage.md 7.7 KB
- references/03-known-conflicts.md 2.0 KB
- references/follow-up-pr.md 6.5 KB
- references/recovery-procedures.md 2.9 KB
- references/run-a-sync.md 15 KB
- scripts/02-compute-pending.ps1 8.7 KB runs code
- scripts/03-cherry-pick-one.ps1 12 KB runs code
- scripts/04-try-build.ps1 7.7 KB runs code
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.
- 1mo ago First seen · 164 lines · 139 tokens per session scan A a17151f49602
upstream-sync is a skill published in the GitHub repository microsoft/intelligent-terminal (2,074 stars, last pushed today), licensed MIT. It adds 139 tokens to every session and 2,969 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
Multitrack
Automatic multi-track ruler orchestration per §11.4.187 — one conductor session spawning, driving, resuming, monitoring and controlling per-track headless workers with per-subscription auth, rate-limit rebind and crash-resilient supervision. Use when working with parallel development tracks, per-track headless…
conventional-commit
Draft a Conventional Commits message from a short summary of the change.
apply-patch
Apply multi-file or tricky edits atomically with git apply instead of many fragile editfile calls. Use when changing several files at once or when editfile fails to match.
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.
csv
CSV data processing — view, filter, convert, merge tabular data. Zero barrier — use with x-cmd, Python, or awk. Use for "csv", "data", "table", "spreadsheet", "conversion".
git
Git and code hosting platform management — GitHub, GitLab, Codeberg, Forgejo. Zero barrier — install x-cmd and manage repos from the terminal. Use for "git", "github", "gitlab", "repo", "pull request", "code hosting".