inspecto: Skill for Claude Code

.claude/skills/vscode-ext-probe/analyze-params/SKILL.md

vscode-ext-analyze-params is a skill for Claude Code from inspecto-dev/inspecto. It costs 133 tokens per session (667 once invoked), scanned A, original, MIT.

A script that inspects a compiled Visual Studio Code extension to determine what arguments one of its commands accepts. A Visual Studio Code extension adds features or commands to the editor.

In plain words
What is it for?
Use it to inspect one or all extension commands, infer argument types, map parameters from URI handlers, and show nearby source code for manual checking.
Why use it?
The original source code may be unavailable or compressed, making command inputs difficult to document or use correctly.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is inspecto-dev/inspecto's own configuration. It tells Claude Code how to work on inspecto 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 inspecto configures →

Reuse

Borrowing it

Nothing to install: this file belongs to inspecto-dev/inspecto. 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/inspecto-dev/inspecto/main/.claude/skills/vscode-ext-probe/analyze-params/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/inspecto-dev/inspecto

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-analyze-params

README.md
[![agentmods](https://agentmods.dev/badge/skills/inspecto-dev/inspecto/analyze-params/github.svg)](https://agentmods.dev/skills/inspecto-dev/inspecto/analyze-params)
Your own site
<a href="https://agentmods.dev/skills/inspecto-dev/inspecto/analyze-params"><img src="https://agentmods.dev/badge/skills/inspecto-dev/inspecto/analyze-params/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-analyze-params

Your own site · 80×15
<a href="https://agentmods.dev/skills/inspecto-dev/inspecto/analyze-params"><img src="https://agentmods.dev/badge/skills/inspecto-dev/inspecto/analyze-params.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 667 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00133 $0.00667
Opus 5.5 $0.00053 $0.00267
Sonnet 5.5 $0.00027 $0.00133
Haiku 4.5 $0.00013 $0.00067

Measured 2mo ago against content hash 16d0b3706717, 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-analyze-params 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/analyze_params.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/vscode-ext-probe/analyze-params/SKILL.md · 65 lines

What it actually says

Analyze VSCode Extension Command Parameters

Deep-dive into a specific command's parameter signature from minified source code.

Usage

# Analyze a single command
python3 scripts/analyze_params.py <extension-id> <command-name> [--context-size 800]

# Analyze all commands at once
python3 scripts/analyze_params.py <extension-id> --all

What It Does

For each target command:

  1. Finds the registerCommand("cmd", callback) in extension.js
  2. Extracts the callback parameter list (e.g. (N, v, U))
  3. Analyzes type-checking patterns in the function body:
    • typeof X === "string" → parameter is string
    • Array.isArray(X) → parameter is array
    • X?.property → parameter is object
    • Ternary guards like typeof X === "string" ? X : undefined → optional typed parameter
  4. Checks URI Handlers (handleUri) for human-readable parameter name mapping
  5. Extracts the surrounding code context for manual inspection

How to Read the Output

┌─ claude-vscode.terminal.open
│  Params: (N, v, U)
│  Types:  N: string, v: string[], U: object (via validator)
│  URI:    /open → params: [session, prompt]
│  Mapped: N=prompt, v=flags, U=options (inferred from URI + position)
└──
  • Params: Raw minified parameter names from the callback
  • Types: Inferred from type guards in the function body
  • URI: If the command is also accessible via URI handler, shows the human-readable parameter names
  • Context: The surrounding code for manual analysis

Key Insights

  1. Parameter position matters — editor.open(session, prompt, viewColumn) puts prompt as arg 2
  2. URI Handlers are the Rosetta Stone — they map minified names to human-readable ones
  3. Type guards reveal optionality — typeof X === "string" ? X : undefined means the param is optional
  4. Validator function calls (e.g., M_6(U)) indicate custom object schemas — check the validator's definition for details
Files

What ships with it

1 file 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.

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 · 65 lines · 133 tokens per session scan A 16d0b3706717

Subscribe to this mod's changes

vscode-ext-analyze-params is a skill published in the GitHub repository inspecto-dev/inspecto (22 stars, last pushed 1mo ago), licensed MIT. It adds 133 tokens to every session and 667 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systemic-issue-triage

Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.

Gentleman-Programming/gentle-ai · 57 tokens

issue-root-resolution

Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.

Gentleman-Programming/gentle-ai · 45 tokens

rdd-defect-workflow

Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.

Gentleman-Programming/gentle-ai · 41 tokens

debug-live

Guides root-cause investigations with debugging capabilities by setting breakpoints, starting a debug session, stepping through execution, inspecting variables, and tracing symptoms back to their origin. Prefer it for runtime bugs, failing tests, exceptions, crashes, hangs, wrong/null values, and unexpected output…

microsoft/DebugMCP · 84 tokens

dex-doctor

Whole-system checkup: verifies every Dex feature honestly (working/off/broken/couldn't-check), self-heals what's provably safe, guides the rest. Use when the user says 'is Dex healthy', 'something's broken', 'check my setup', 'run diagnostics'. Not for discovering unused features; use dex-level-up. Not for applying an…

davekilleen/Dex · 85 tokens

debug-helper

Help debug code by analyzing error messages, identifying root causes, and providing fix suggestions.

JackyST0/awesome-agent-skills · 20 tokens