Aider Local Bigger — Development agent for Claude Code
Aider running against a larger local Ollama model, used once to confirm.
How to install Aider Local Bigger
Installs to ~/.claude/agents/plainjane20-muster-aider-local-bigger.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/PlainJane20/muster/HEAD/agents/aider-local-bigger.md -o ~/.claude/agents/plainjane20-muster-aider-local-bigger.md Restart Claude Code, or start a new session, for it to be picked up.
What Aider Local Bigger does
id: aider-local-bigger name: Aider Local (bigger model) runtime: aider model: ollama_chat/qwen2.5-coder:7b tool_access: standard cwd: /tmp/aider_test_repo use_worktree: true tags:
- code risk_tier: medium
Aider running against a larger local Ollama model, used once to confirm the filesystem_verified check reports True on a real dispatch that actually persists a change (not just mocked in tests).
Alternatives in Development
- Spark — You are a lightweight implementation agent 3.6k ★
- Aider Conventions 650 ★
- Template Auditor — Use this agent whenever Pulkit wants an existing premium-template clone in the fable repo audited against its 509 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Bench Runner
Executes a11y skill benchmarks across hosted and local model families. Runs cloud/Codex/Ollama benchmark scrip
Ollama Agent
Runs a local model served by Ollama on this machine. One mode - consult (no machine access; the endpoint is a
Local Worker
Coding worker on a local model (Ollama, LM Studio, vLLM) served by the multi-model gateway's upstream. Use whe
Second Opinion
Gets an independent review from a NON-Claude model (via a local CLI such as kimi, or a local Ollama model) and
Frontier Derivation
Baseline-blind derivation panelist for /frontier-run unknown-unknown discovery. Derives failure modes from the
Typesafe Engineer
Implements TypeSafe integrations: registered QuestionSets, client wiring, answer composition in code, and live
Related Skills
Select Coder
Recommend which coder agent and model should execute a coding task — probes locally available backends (opus,
VLS 32M Context Local LLM
Give Claude Code, Codex and opencode a 32M-token memory that never leaves your machine. Local LLM server (MCP
Zlog
Multi-agent session log compressor and storage optimizer for Claude Code, Cursor, Antigravity, Gemini, Ollama,