stub-check

A command that scans a software project for unfinished, shallow, skeletal, or otherwise incomplete code. It combines local code inspection with external research and a final review of the findings.

In plain words
What is it for?
Use it to audit an entire codebase or a selected module for placeholders, missing behavior, incomplete implementations, and production-readiness gaps.
Why use it?
It helps reveal work that looks present but is not fully implemented or ready for real use. The audit checks both common code patterns and the broader context of the project.

Command

Install

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.

agentmods
npx agentmods add commands/intellegix/intellegix-code-agent-toolkit/stub-check
Clone the repo
git clone --depth 1 https://github.com/intellegix/intellegix-code-agent-toolkit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,906 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.06906
Opus 5 $0.00000 $0.03453
Sonnet 5 $0.00000 $0.01381
Haiku 4.5 $0.00000 $0.00691

Measured 3d ago against content hash 269ad9682a99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stub-check 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 3d 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.

commands/stub-check.md · 642 lines

How it starts

The opening of the file, as written. The whole thing — 642 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/stub-check — Deep Implementation Completeness Audit

Perform a thorough 3-phase audit of the current project's codebase to find code that is unfinished, shallow, skeletal, or not production-ready. Phase 0.5 runs a Perplexity research reconnaissance using GitHub connectors (runs in parallel with Phase 1). Phase 1 uses local scanning (Grep/Glob/Read) independently. Phase 2 merges both passes through Perplexity for final depth/brevity validation.

Architecture: Research recon (Perplexity + GitHub connectors) runs IN PARALLEL with local pattern scan → merge → research validation last (depth + brevity). ~90s total overhead. $0 cost via Perplexity login session.

CRITICAL: Do NOT ask the user questions before completing all phases. Execute the full audit silently and present results at the end. Only interact if $ARGUMENTS specifies a subset of the codebase to audit.

Input

$ARGUMENTS = Optional path or module to audit (e.g., automated-loop/, src/auth/). If empty, audit the entire project from the working directory.


Step 0: Detect Project Languages — MANDATORY, SILENT

Before scanning, auto-detect which languages and frameworks are present. This determines which pattern sets to use.

  1. Check for language markers (run in parallel):

    • Glob for **/*.py → Python detected
    • Glob for **/*.ts or **/*.tsx → TypeScript detected
    • Glob for **/*.js or **/*.jsx → JavaScript detected
    • Glob for **/*.go → Go detected
    • Glob for **/*.rs → Rust detected
    • Glob for **/*.java or **/*.kt → Java/Kotlin detected
    • Glob for **/*.rb → Ruby detected
    • Glob for **/*.cs → C# detected
    • Glob for **/*.swift → Swift detected
    • Glob for **/*.c or **/*.cpp or **/*.h → C/C++ detected
    • Glob for **/*.php → PHP detected
  2. Check for framework markers (read if they exist):

    • package.json → check dependencies for React, Next.js, Express, Fastify, NestJS, Vue, Angular, Svelte
    • pyproject.toml or setup.py → check for Django, Flask, FastAPI, SQLAlchemy
    • Cargo.toml → Rust crate metadata
    • go.mod → Go module metadata
    • Gemfile → Ruby gems
    • pom.xml or build.gradle → Java/Kotlin build system
    • *.csproj or *.sln → .NET project

Read the full file on GitHub · 642 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. 3d ago First seen · 642 lines · 0 tokens per session scan A 269ad9682a99

Subscribe to this mod's changes

stub-check is a command published in the GitHub repository intellegix/intellegix-code-agent-toolkit (57 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,906 tokens. 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.