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.
Borrowing it
Nothing to install: this file belongs to microsoft/vscode. 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/vscode/main/.github/skills/customizations-in-the-agent-host/SKILL.mdgit 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/customizations-in-the-agent-host)<a href="https://agentmods.dev/skills/microsoft/vscode/customizations-in-the-agent-host"><img src="https://agentmods.dev/badge/skills/microsoft/vscode/customizations-in-the-agent-host/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/customizations-in-the-agent-host"><img src="https://agentmods.dev/badge/skills/microsoft/vscode/customizations-in-the-agent-host.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 Tool Misuse · line 168 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Rogue Agent · line 128 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00083 | $0.02190 |
| Opus 5.5 | $0.00033 | $0.00876 |
| Sonnet 5.5 | $0.00017 | $0.00438 |
| Haiku 4.5 | $0.00008 | $0.00219 |
Grade C, and why
customizations-in-the-agent-host scanned grade C 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 15d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Electron runner setup aborts (`EEXIST`/`EPERM`/`ENOENT`/ReactiveObjC) are environmental. Recover with `rm -rf .build/electron && npm run electron`. How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customizations in the Agent Host
Customizations are the plugins, MCP servers, agents, skills and instructions that an agent-host session exposes to a model. This skill covers enablement: how a customization's on/off state is decided, stored, published and enforced.
Read this before changing anything in:
src/vs/platform/agentHost/node/agentHostCustomizationEnablementService.tssrc/vs/platform/agentHost/node/shared/customizationEnablementGate.tssrc/vs/platform/agentHost/common/customizationEnablement.ts- the per-provider customization paths under
node/copilot/,node/claude/,node/codex/
The mental model
Enablement is a list of scoped decisions, not a boolean
A plugin or MCP server carries enablement?: CustomizationEnablement[] — an ordered list of decisions, most specific first:
| Kind | Owner | Meaning |
|---|---|---|
Session |
agent host | this session only |
Workspace |
agent host | this working directory (carries uri) |
Global |
client, unless the host discovered it | everywhere |
isCustomizationEnabled() picks the first entry; absent entries inherit from the next scope out, and an absent list means enabled. Never re-add a parallel enabled boolean to plugins or MCP servers — a second source of truth is what this design exists to remove. (DirectoryCustomization legitimately keeps a plain enabled; consumers derive its state through isCustomizationEnabled() all the same.)
Who owns Global
The host owns Global for anything it discovered, even when that thing lives inside a plugin the client forwarded. The client owns Global only for what it actually bundled. The discriminator is childEnablement — not clientId. A plugin whose childEnablement record has a key for a child MCP server means "the client bundled this child and owns its global decision"; anything else the host discovered by parsing the plugin directory.
The overlay model
This is the single most important invariant, and getting it wrong caused a self-defeating write that silently erased user decisions:
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.
- 15d ago Changed · +3 lines 70ba80f8d9d1
- 1mo ago Changed · -59 lines 9192020d19c3
- 1mo ago First seen · 183 lines · 83 tokens per session scan C fe6018c92e86
customizations-in-the-agent-host is a skill published in the GitHub repository microsoft/vscode (194,219 stars, last pushed today), licensed MIT. It adds 83 tokens to every session and 2,190 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cyrene-exam-paper
A method for creating formal exams from a learning plan, then keeping the questions, answers, grading, and review separate. It maps learned topics to skills and suitable question types.
cyrene-diagram
A design guide for making static SVG learning cards: small diagrams or reference cards rendered as images. It explains when to use a card instead of Mermaid, a text-based diagram format, and sets layout, color, size, and safety rules.
javascript-sandbox
Best practices for using the clodex built-in JavaScript sandbox for browser debugging, fetched-data processing, attachments, and mini-app orchestration within its bundled capability boundary.
docs-writing
Write, restructure, or review documentation — tutorials, how-to guides, reference pages, concept/explanation docs, API references, READMEs, changelogs, release notes, and troubleshooting guides. Distills documentation craft from Mintlify's guides (compiled from technical writers at Stripe, GitHub, Amplitude, and…
Debug
Use logging calls for in-depth debugging via local log files.
spec-harness-learn
The learning loop — turn feedback, a correction, or a verifier-FAIL root cause into one enforced rule injected into the ratchet (AGENTS.md/airules), dated. Use when Malik says 'learn this', 'remember not to do X', 'capture this lesson', 'don't do that again', or right after he corrects you. Closes the loop the…