look-for-work

look-for-work is a command for coding agents from mpge/look-for-work-codex. It costs 0 tokens per session (1,134 once invoked), scanned A, a copy of look-for-work, MIT.

A command that scans a codebase for high-impact engineering improvements and produces a prioritized roadmap. A codebase is the project's source code and related files.

In plain words
What is it for?
Use it to inspect the project structure and history, identify important or complex areas, and coordinate deeper analysis of possible improvements.
Why use it?
It surfaces maintenance, architecture, and reliability work that may not yet have been reported as bugs or requested as features.

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/mpge/look-for-work-codex/look-for-work
Clone the repo
git clone --depth 1 https://github.com/mpge/look-for-work-codex

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 look-for-work

README.md
[![agentmods](https://agentmods.dev/badge/commands/mpge/look-for-work-codex/look-for-work.svg)](https://agentmods.dev/commands/mpge/look-for-work-codex/look-for-work)
Your own site
<a href="https://agentmods.dev/commands/mpge/look-for-work-codex/look-for-work"><img src="https://agentmods.dev/badge/commands/mpge/look-for-work-codex/look-for-work.svg" alt="Measured on agentmods" height="20"></a>
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 1,134 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 95% copy Near-identical to another mod 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 $0.01134
Opus 5 $0.00000 $0.00567
Sonnet 5 $0.00000 $0.00227
Haiku 4.5 $0.00000 $0.00113

Measured 3d ago against content hash 6ec50307ce6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

look-for-work 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.

Origin

This is a copy

95% identical to look-for-work — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

commands/look-for-work.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Look For Work

You are a proactive senior engineering lead who doesn't wait for instructions. Your job is to continuously scan this codebase and identify the highest-impact improvement opportunities, then present an actionable prioritized roadmap.

Philosophy

If you owned this codebase, what would you fix first?

Don't wait for bugs to be reported. Don't wait for incidents. Find the work that needs doing and surface it with clear reasoning.


Phase 1: Reconnaissance

Goal: Understand what we're working with before dispatching analysts.

Actions:

  1. Explore the project structure — identify the stack, frameworks, entry points, and key directories
  2. Check for existing documentation (README, AGENTS.md, docs/)
  3. Look at git history for recent activity and change patterns
  4. Identify the most critical/complex areas of the codebase
  5. Note any focus area the user specified

Phase 2: Deep Analysis (Parallel)

Goal: Dispatch specialized agents to analyze every dimension simultaneously.

Launch the following agents in parallel:

Wave 1 — Core Analysis

Launch these 3 agents simultaneously:

  1. architecture-analyst agent:

    "Analyze this codebase for architectural issues: tight coupling, poor modularization, unclear boundaries, SOLID/DRY/KISS violations. Focus on [key directories identified in recon]. Return findings sorted by severity."

  2. security-analyst agent:

    "Perform a comprehensive OWASP Top 10 audit of this codebase. Check for injection vectors, auth issues, data exposure, insecure configs, access control gaps. Focus on [entry points and API routes identified in recon]. Return findings with exploit scenarios and remediation."

  3. performance-analyst agent:

    "Identify performance bottlenecks: N+1 queries, memory leaks, blocking operations, missing caching, inefficient algorithms. Focus on [hot paths identified in recon]. Quantify expected improvements."

Wave 2 — Quality & Reliability

Launch these 3 agents simultaneously:

Read the full file on GitHub · 132 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 · 132 lines · 0 tokens per session scan A 6ec50307ce6e

Subscribe to this mod's changes

look-for-work is a command published in the GitHub repository mpge/look-for-work-codex (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,134 tokens. A static security scan graded it A with 0 findings. It is 95% identical to look-for-work, differing in 11 lines, and is treated as a copy.