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.
npx agentmods add agents/mhattingpete/agent-composer/lint-error-resolvergit clone --depth 1 https://github.com/mhattingpete/agent-composerWrote 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.
[](https://agentmods.dev/agents/mhattingpete/agent-composer/lint-error-resolver)<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="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00276 | $0.00857 |
| Opus 5 | $0.00138 | $0.00428 |
| Sonnet 5 | $0.00055 | $0.00171 |
| Haiku 4.5 | $0.00028 | $0.00086 |
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 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.
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.
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.
- 3d ago First seen · 57 lines · 0 tokens per session scan A 0aa8017540ed
lint-error-resolver is an agent published in the GitHub repository mhattingpete/agent-composer (5 stars, last pushed 6mo ago), licensed MIT. It adds 276 tokens to every session and 857 once invoked, about $0.0014 per session on Opus 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.
Other agents, from other repositories
matrix
This page renders the Tier-1 agent × model-family integration matrix truthfully from the authoritative test suite in tests/integrations/ — the matrix cells (testagentsmatrix.py), the family aliases and strict-xfail rules (conftest.py), and the pilot run recorded in tests/integrations/README.md.
opencode
Point OpenCode at a local rapid-mlx server. OpenCode is a Claude-Code-like terminal coding agent that speaks the OpenAI-compatible chat completions API (POST /v1/chat/completions) via the @ai-sdk/openai-compatible provider.
qwen-code
Point Qwen Code at a local rapid-mlx server. Qwen Code is Alibaba's gemini-cli fork tuned for Qwen tool-calling; it speaks the OpenAI-compatible chat completions API (POST /v1/chat/completions) via an OpenAI entry in modelProviders that maps 1:1 onto rapid-mlx's default endpoint.
worktree-collaboration
This document defines the default collaboration protocol for multiple Agents working on Vibelution in parallel.
anvil-quality-reviewer
Hostile maintainability reviewer. Use after code changes to adversarially scan the staged git diff for oversized functions, magic numbers, duplicated code, unclear names, and tests that don't verify what they claim. Quotes the exact offending lines.
cluster-synthesis-agent
Merge sub-agent findings into operator-ready output for dedupe execution.