Borrowing it
Nothing to install: this file belongs to kelvincushman/local-fusion. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kelvincushman/local-fusion/main/AGENTS.mdgit clone --depth 1 https://github.com/kelvincushman/local-fusionWrote 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/instructions/kelvincushman/local-fusion/agents-md)<a href="https://agentmods.dev/instructions/kelvincushman/local-fusion/agents-md"><img src="https://agentmods.dev/badge/instructions/kelvincushman/local-fusion/agents-md/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.
<a href="https://agentmods.dev/instructions/kelvincushman/local-fusion/agents-md"><img src="https://agentmods.dev/badge/instructions/kelvincushman/local-fusion/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00918 | $0.00918 |
| Opus 5 | $0.00459 | $0.00459 |
| Sonnet 5 | $0.00184 | $0.00184 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
local-fusion AGENTS.md 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
local-fusion
A small, dependency-free runner that reproduces an OpenRouter Fusion-style model council
against local OpenAI-compatible servers or Pi-authenticated model subscriptions: a panel
of models answer the same prompt, a judge compares them as structured JSON, and a synthesizer
writes the final answer. Two parity implementations exist for the core council — Node
(src/) and Python (local_fusion/). The MCP connector is Node-only.
You can consult the council as a tool
A local-fusion skill is installed under .pi/skills/. When a decision in this repo is
ambiguous or high-stakes and a second opinion would help, get a deliberated multi-model
answer with node src/cli.mjs ask --json "<question>". Pi loads that skill on demand —
see it for the exact commands and how to read the trace. Your own model still drives the
session; local-fusion is only a tool you call.
Project map
src/— Node implementation (cli.mjs,fusion.mjs,openai-compatible.mjs,config.mjs,pi-transport.mjs,looped.mjs,mcp.mjs,mcp-connector.mjs). No dependencies; needs Node 20+.local_fusion/— Python implementation (core.py,cli.py,pi_transport.py,looped.py). Stdlib only; needs Python 3.10+.test/fusion.test.mjs+test/looped.test.mjs+test/mcp-connector.test.mjs— Node tests (node --test); mock the pi client + inject fake call.tests/test_fusion.py+tests/test_looped.py— Python tests (python3 -m unittest discover -s tests); same hermetic pattern.config.example.json— template. Copy tolocal-fusion.config.json(the runtime config) and point each entry at a server you actually run.looped-fusion.config.jsonholds the roster + role→model policy for Looped PI Fusion..pi/extensions/looped-fusion.ts— Pi/loopedslash command (auto-loaded project extension)..mcp/local-fusion.json— example Claude Code MCP config for the local-fusion stdio server.docs/— design docs, includingprd-pi-agent-fusion-loop.md(the Looped PI Fusion spec, now implemented),using-with-pi.md,using-looped-fusion.md, andusing-mcp-connector.md.
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.
- 9d ago First seen · 41 lines · 918 tokens per session scan A fedbe0e52de4
local-fusion AGENTS.md is an instructions file published in the GitHub repository kelvincushman/local-fusion (0 stars, last pushed 2mo ago), licensed MIT. It adds 918 tokens to every session, about $0.0046 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.