agent-code-tracker: Skill for Claude Code

.github/skills/vscode-ext-dev/SKILL.md

vscode-ext-dev is a skill for Claude Code from arijeetganguli/agent-code-tracker. It costs 46 tokens per session (1,081 once invoked), scanned A, original, MIT.

A development guide for the Agent Code Tracker extension for Visual Studio Code, a code editor. It covers the extension's features, tests, debugging, and packaging.

In plain words
What is it for?
Use it when adding features, fixing bugs, running tests, debugging in the extension host, packaging releases, or changing package.json settings.
Why use it?
It provides a known workflow for changing the extension while keeping its commands, tracking logic, interface, and tests connected.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is arijeetganguli/agent-code-tracker's own configuration. It tells Claude Code how to work on agent-code-tracker itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-code-tracker configures →

Reuse

Borrowing it

Nothing to install: this file belongs to arijeetganguli/agent-code-tracker. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/arijeetganguli/agent-code-tracker/main/.github/skills/vscode-ext-dev/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/arijeetganguli/agent-code-tracker

Made for: Claude Code.

Wrote 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.

agentmods badge for vscode-ext-dev

README.md
[![agentmods](https://agentmods.dev/badge/skills/arijeetganguli/agent-code-tracker/vscode-ext-dev/github.svg)](https://agentmods.dev/skills/arijeetganguli/agent-code-tracker/vscode-ext-dev)
Your own site
<a href="https://agentmods.dev/skills/arijeetganguli/agent-code-tracker/vscode-ext-dev"><img src="https://agentmods.dev/badge/skills/arijeetganguli/agent-code-tracker/vscode-ext-dev/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.

agentmods 80×15 button for vscode-ext-dev

Your own site · 80×15
<a href="https://agentmods.dev/skills/arijeetganguli/agent-code-tracker/vscode-ext-dev"><img src="https://agentmods.dev/badge/skills/arijeetganguli/agent-code-tracker/vscode-ext-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,081 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.01081
Opus 5.5 $0.00018 $0.00432
Sonnet 5.5 $0.00009 $0.00216
Haiku 4.5 $0.00005 $0.00108

Measured 2mo ago against content hash 982f9123df28, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vscode-ext-dev 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 2mo 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.

.github/skills/vscode-ext-dev/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VS Code Extension Development Workflow

When to Use

  • Adding a new feature or command to the extension
  • Fixing a bug in tracking, UI, or detection logic
  • Running or writing tests
  • Debugging the extension in the Extension Development Host
  • Packaging the extension for distribution
  • Modifying package.json contributions (commands, configuration, activation)

Project Architecture

Module Responsibility
src/extension.ts Activation, command registration, event wiring, disposal
src/codeTracker.ts AI vs manual detection heuristics, stats persistence via workspaceState
src/statusBar.ts Status bar item with 2-second polling updates
src/statsView.ts Webview panel with per-file and workspace-wide statistics
src/test/extension.test.ts Mocha test suite (run via @vscode/test-cli)

Key Interfaces

// in codeTracker.ts
interface CodeStats { totalChars: number; agentChars: number; manualChars: number; percentage: number; }
interface FileStats { [filePath: string]: CodeStats; }

Dependency Flow

extension.ts → creates CodeTracker
             → passes CodeTracker to StatusBarManager
             → passes CodeTracker to StatsViewProvider

All disposables are pushed to context.subscriptions for cleanup.

Procedure

1. Understand the Change

  • Identify which module(s) the change touches (see Architecture table)
  • If adding a command: update both src/extension.ts (registration) and package.json (contributes.commands)
  • If adding a config setting: update package.json (contributes.configuration) and consume it via vscode.workspace.getConfiguration('agentCodeTracker')

2. Implement

  • Follow existing patterns:
    • Classes: PascalCase with descriptive suffixes (Manager, Provider)
    • Methods: camelCase
    • Interfaces: PascalCase, exported
    • Strict mode: All type annotations explicit
    • Semicolons: Required (enforced by ESLint)
  • Webview HTML must use VS Code CSS variables (--vscode-foreground, --vscode-editor-background, etc.)
  • Webview communication uses panel.webview.postMessage() and panel.webview.onDidReceiveMessage()
  • All resources (intervals, event listeners, status bar items) must implement disposal

Read the full file on GitHub · 130 lines

Changes

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.

  1. 2mo ago First seen · 130 lines · 46 tokens per session scan A 982f9123df28

Subscribe to this mod's changes

vscode-ext-dev is a skill published in the GitHub repository arijeetganguli/agent-code-tracker (2 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 1,081 once invoked, about $0.0002 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 2026-08-31.

Related

vscode-ext-dev compared with skills from other repositories

vscode-ext-dev next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
vscode-ext-devarijeetganguli/agent-code-trackerSkill22mo agoMITA46Claude Code
systematic-debuggingopen-metadata/OpenMetadataSkill16kyesterdayApache-2.0A37Claude Code
log-error-digestzebbern/claude-code-guideSkill4.7k3d agoMITA71Claude Code, Codex
cwv-optimizeradobe/skillsSkill319yesterdayApache-2.0A112Claude Code
ci-fixersipyourdrink-ltd/bernsteinSkill1.2kyesterdayApache-2.0A15Claude Code, Codex
incident-response-incident-responsermyndharis/antigravity-skillsSkill1.9k23d agoMITA36Claude Code
triaging-web-analytics-supportPostHog/posthogSkill41kyesterdaynoneA151Claude Code, Codex