Visual Studio Code is a code editor that supports editing, navigating, understanding, debugging, and extending software projects. Developers use it for the edit-build-debug cycle, and the catalogue add-ons provide skills, instructions, and agents for working within the editor.
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 skills add microsoft/vscode --skill mergegit clone --depth 1 https://github.com/microsoft/vscodeWrote 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/vscode/merge)<a href="https://agentmods.dev/skills/microsoft/vscode/merge"><img src="https://agentmods.dev/badge/skills/microsoft/vscode/merge/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/vscode/merge"><img src="https://agentmods.dev/badge/skills/microsoft/vscode/merge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- medium Excessive Agency · line 15 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00031 | $0.00566 |
| Opus 5.5 | $0.00012 | $0.00226 |
| Sonnet 5.5 | $0.00006 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
merge 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge Changes
Merge the topic branch (checked out in the current worktree) into the merge base branch (checked out in the main worktree). The context block appended to the prompt contains the source branch, target branch, and main worktree path.
Guidelines
- Never force-push (
--force,--force-with-lease) without explicit user approval. - Never skip pre-push hooks (do not use
--no-verify). - Never rewrite or drop commits without asking the user.
- When in doubt about conflict resolution — ask the user.
Workflow
1. Commit uncommitted changes in the current worktree
Check for uncommitted changes in the current worktree:
git status --porcelain
If there are uncommitted changes, use the /commit skill to commit them before continuing.
2. Merge the topic branch into the base branch
Use git -C <main-worktree-path> to run commands against the main worktree without leaving the current worktree.
git -C <main-worktree-path> merge <topic-branch>
3. Handle merge conflicts
If the merge reports conflicts:
3.1. List conflicted files:
git -C <main-worktree-path> diff --name-only --diff-filter=U
3.2. For each conflicted file, read the file content, resolve the conflict by preserving the intent of both sides, and stage the resolved file:
git -C <main-worktree-path> add <resolved-file>
3.3. When in doubt on how to resolve a merge conflict, ask the user for guidance. If the user wants to abort, run:
git -C <main-worktree-path> merge --abort
3.4. Once all conflicts are resolved and staged, commit the merge:
git -C <main-worktree-path> commit --no-edit
Validation
After the merge completes, verify the result:
- Confirm the main worktree is clean:
git -C <main-worktree-path> status --porcelain
- Confirm the topic branch is an ancestor of the base branch (i.e. all commits are merged):
git -C <main-worktree-path> merge-base --is-ancestor <topic-branch> HEAD
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 · 73 lines · 31 tokens per session scan A b2a83acd902d
merge is a skill published in the GitHub repository microsoft/vscode (194,254 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 566 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 2026-09-03.
Other skills, from other repositories
open-code-review
Use Alibaba Open Code Review (ocr) to review git diffs, staged changes, branches, or scan a workspace, then summarize findings and optionally fix high-confidence issues.
Release Readiness
Review a change against release gates, rollback safety, validation evidence, and operational risk.
publish-npm-version
Cuts the next release of Prisma 8: bumps the root package.json version (on the v8 RC line: 8.0.0-rc.N → rc.N+1), propagates it to every workspace package, and opens a PR titled "chore(release): bump to ". When the maintainer merges the PR, the Publish to npm workflow runs automatically and ships the new version to npm…
contrib-pr
Open a high-quality external contributor PR against prisma/orm. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encodes the contribution flow from CONTRIBUTING.md so the resulting PR passes review on the first round.
merge-seed
Merge upstream React Starter Kit updates (the seed remote) into main, preserving this project's identity, scope, and behavior. Use when asked to sync, pull, or merge the seed / starter kit / upstream template.
competitor-product-monitor
Monitor competitor product releases and new feature announcements. Use this skill when the user wants to track what competitors are shipping, find the latest product launches in their industry, or generate a competitor release report. Triggers include phrases like "track competitor releases", "what are my competitors…