Skip to content
Agentmart
Submit a tool

local-llm

Local-LLM fallback for cheap-operation routing — Ollama, llama.cpp, LM Studio.

Skill by drumfiend21

IndexedApache-2.0
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/drumfiend21-local-llm

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Local-LLM fallback for cheap-operation routing — Ollama, llama.cpp, LM Studio. Targets 30–50% baseline daily token-cost reduction by routing triage, affiliation parsing, and issue-label filtering to a local backend.

Use cases: backend, ml

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Shell scripts

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/local-llm

What's inside

Skill name
local-llm
Description
Local-LLM fallback for cheap-operation routing — Ollama, llama.cpp, LM Studio. Targets 30–50% baseline daily token-cost reduction by routing triage, affiliation parsing, and issue-label filtering to a local backend.
License
Apache-2.0
Instructions
30 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (4)

  • SKILL.md
  • cost-report.sh
  • list-backends.sh
  • route.sh

SKILL.md (first lines)

# Local-LLM Skill

Per architecture §16 X-4: routes "cheap" operations — L-3 triage,
L-6 affiliation parsing, L-16 issue-label filtering — to a local
inference backend (Ollama / llama.cpp / LM Studio) when available,
falling back to the remote API when not. Reports a daily token-cost
reduction estimate.

## Supported backends

- `ollama` — http://localhost:11434
- `llama.cpp` — llama-server on a configurable port
- `lm-studio` — local OpenAI-compatible server

## Routed operations

- `triage` (L-3) — coarse pattern filter on PR title/body
- `affiliation-parsing` (L-6) — extract org from reviewer email/handle
- `issue-label-filtering` (L-16) — drop issues missing security label

Everything else continues to use the remote API.

## Cost report

`cost-report.sh` reads `.claude-tdd-pro/local-llm/stats.json` and
emits `reduction_pct=<n> target_band=30-50 tokens_avoided=<n>`. The
target band is the architecture-defined 30–50% reduction goal for
the routed operations.

From drumfiend21/claude-tdd-pro, Apache-2.0.

More from drumfiend21/claude-tdd-pro

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
May 20, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
Repository
github.com/drumfiend21/claude-tdd-pro
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from drumfiend21

Cite this page

local-llm skill. Agent Mart. https://agentmart.dev/skills/drumfiend21-local-llm (last updated 2026-10-24)