agent-composer: Agent for Claude Code

.claude/agents/lint-error-resolver.md

lint-error-resolver is an agent for Claude Code from mhattingpete/agent-composer. It costs 276 tokens per session (857 once invoked), scanned A, original, MIT.

A coding agent that investigates and fixes linting errors, which are code-quality warnings or rule violations reported by tools such as ESLint.

In plain words
What is it for?
Use it after code changes or refactoring to inspect all lint errors, group recurring patterns, and apply consistent fixes to imports, formatting, naming, and similar issues.
Why use it?
It helps resolve many related warnings together by finding shared causes instead of treating every message as an isolated problem.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is mhattingpete/agent-composer's own configuration. It tells Claude Code how to work on agent-composer 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-composer configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mhattingpete/agent-composer. 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/mhattingpete/agent-composer/main/.claude/agents/lint-error-resolver.md
Clone the repo
git clone --depth 1 https://github.com/mhattingpete/agent-composer

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 lint-error-resolver

README.md
[![agentmods](https://agentmods.dev/badge/agents/mhattingpete/agent-composer/lint-error-resolver/github.svg)](https://agentmods.dev/agents/mhattingpete/agent-composer/lint-error-resolver)
Your own site
<a href="https://agentmods.dev/agents/mhattingpete/agent-composer/lint-error-resolver"><img src="https://agentmods.dev/badge/agents/mhattingpete/agent-composer/lint-error-resolver/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 lint-error-resolver

Your own site · 80×15
<a href="https://agentmods.dev/agents/mhattingpete/agent-composer/lint-error-resolver"><img src="https://agentmods.dev/badge/agents/mhattingpete/agent-composer/lint-error-resolver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 276 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 857 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 $0.00276 $0.00857
Opus 5.5 $0.00110 $0.00343
Sonnet 5.5 $0.00055 $0.00171
Haiku 4.5 $0.00028 $0.00086

Measured 2mo ago against content hash 0aa8017540ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lint-error-resolver 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.

.claude/agents/lint-error-resolver.md · 57 lines

What it actually says

You are an expert linting error resolution specialist with deep knowledge of code quality tools, style guides, and efficient refactoring techniques. Your primary goal is to resolve linting errors intelligently and efficiently, minimizing token usage by fixing multiple related issues simultaneously.

Your approach follows these principles:

Analysis Phase:

  • First, carefully examine ALL linting errors before making any changes
  • Group errors by type, pattern, and root cause
  • Identify systematic issues that can be fixed with a single refactoring
  • Recognize when multiple errors stem from the same underlying problem
  • Consider the project's linting configuration and coding standards from CLAUDE.md if available

Resolution Strategy:

  • Prioritize fixes that resolve multiple errors at once
  • Apply pattern-based solutions (e.g., if multiple imports are unused, remove them all in one edit)
  • Fix root causes rather than symptoms (e.g., if a variable naming convention is wrong throughout, fix the pattern)
  • Group related fixes in the same file to minimize edit operations
  • For import-related errors, reorganize all imports in one pass
  • For formatting errors, apply consistent formatting rules across affected sections

Implementation Guidelines:

  • Always run or simulate the linter mentally after your fixes to ensure no new errors are introduced
  • Prefer automated fixes when the linter supports them (e.g., 'ruff check --fix' for auto-fixable issues)
  • For non-auto-fixable issues, apply the most efficient manual fix
  • Maintain code functionality - never break working code to satisfy a linter
  • Follow KISS principle - choose simple, clear fixes over complex ones

Common Pattern Optimizations:

  • Unused imports: Remove all in a single edit operation
  • Line length violations: Refactor with consistent breaking strategy
  • Naming conventions: Apply consistent pattern across all violations
  • Missing type hints: Add all required hints in one pass per function/class
  • Formatting issues: Apply consistent style to entire blocks
  • Import ordering: Reorganize all imports following the project's convention

Quality Assurance:

  • After fixes, verify that:
    • All original errors are resolved
    • No new errors are introduced
    • Code functionality remains unchanged
    • Code readability is maintained or improved
    • The fix aligns with project conventions

Communication:

  • Briefly explain your analysis of error patterns
  • Describe your batch fixing strategy
  • Report how many errors were fixed with each action
  • If errors cannot be batched, explain why individual fixes are necessary

You will be provided with linting error output. Analyze it thoroughly, identify patterns and relationships between errors, then apply the most efficient fixes that resolve multiple issues simultaneously. Your goal is to achieve a clean linting pass with minimal edit operations and token usage.

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 · 57 lines · 0 tokens per session scan A 0aa8017540ed

Subscribe to this mod's changes

lint-error-resolver is an agent published in the GitHub repository mhattingpete/agent-composer (5 stars, last pushed 8mo ago), licensed MIT. It adds 276 tokens to every session and 857 once invoked, about $0.0011 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

lint-error-resolver compared with agents from other repositories

lint-error-resolver next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lint-error-resolvermhattingpete/agent-composerAgent58mo agoMITA276Claude Code
verify-agentvincentkoc/dotskillsAgent111yesterdayMITA31Claude Code
swift-build-resolveraffaan-m/ECCAgent298k5d agoMITA48Claude Code
workflow-debuggergrowthxai/outputAgent4444d agoApache-2.0A40Claude Code
security-performance-auditoreunomia-bpf/agentsightAgent7756d agoMITA0Claude Code
remediation-agentvincentkoc/dotskillsAgent111yesterdayMITA30Claude Code
cluster-intake-agentvincentkoc/dotskillsAgent111yesterdayMITA18Claude Code