# 11 More Tiny Coding Agent Fixes With A Stupid Amount Of Payoff (Learn These Now)

## Executive summary

This video provides 11 actionable fixes for common frustrations encountered when using AI coding agents. The core thesis is that improving agent performance requires becoming 'engineers of the harness'—meaning the user must actively adjust the agent's underlying 'AI layer' (skills, rules, and hooks). Solutions range from implementing 'devil's advocate' review skills to using programmatic 'hooks' to enforce security and conventions, ensuring the agent's output is reliable, focused, and verifiable.

## Key takeaways

- Use Hooks for Guarantees: For mandatory constraints (e.g., security rules, conventions like 'must never read .env files'), do not rely solely on global rules. Implement these as 'hooks' to provide a programmatic guarantee that the agent cannot bypass, even if it attempts the action.
- Manage Context and Focus: To prevent 'context rot' (performance degradation in long conversations), keep sessions focused on small, individual tasks. For long-running work, create a formal 'handoff document' to transfer context to a fresh session.
- Define the Blast Radius: To prevent agents from over-testing or under-testing, establish the 'blast radius' (the scope of potential impact) upfront, ideally within the planning skill. This determines the appropriate depth of validation for small changes.
- Control Sub-Agent Usage: To manage rate limits and token costs, do not allow coding agents to use sub-agents liberally. Explicitly define in your rules when and how many sub-agents are required, and consider using smaller models for non-reasoning tasks.

## Technical details

- Agent Review and Validation: When an agent claims work is complete, prompt it to 'play devil's advocate' by asking, 'What would make this not actually work?' This helps identify functional gaps. A formal solution is creating a separate 'reviewer skill' to critically assess the implementation.
- Testing Evidence and Validation: Agents must provide concrete testing evidence beyond passing unit tests. This includes real commands and output, or even screenshots of the application working as a user would (e.g., using an agent browser CLI). Validation should test the full stack, not just isolated components.
- Rule Bloat and Context Management: Global rule files (like `claw.md`) tend to become bloated, diluting the agent's focus. It is crucial to use skills (like the `ablate-ai-layer` skill) to identify and remove unnecessary rules, keeping the context lean and reliable.
- Scope Creep Prevention: To prevent small requests from becoming massive changes, enforce conciseness within the AI layer. Rules and skills should guide the agent to be direct and focused, avoiding unnecessary refactors or touching unrelated parts of the codebase.

## Practical implications

- Treat the coding agent as a powerful but fallible junior developer; the user must act as the 'harness engineer' by defining guardrails.
- Prioritize moving critical, non-negotiable constraints from natural language rules into programmatic hooks for guaranteed enforcement.
- Implement a structured planning phase that forces the agent to define the scope (blast radius) and the validation method before writing code.
- Adopt a modular approach to coding tasks, using handoff documents to maintain context integrity across multiple sessions.

## Topics

AI Agents, Large Language Models (LLMs), Build Engineering, Software Architecture, Code Quality, CI/CD, Prompt Engineering, Arcade, Dynamous (Agentic Coding Course 2.0), My first 11 tips, The ablate-ai-layer skill

Source: https://www.youtube.com/watch?v=hMEQ4rdaOLw
