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 instructions/lynkbyte/ensemble/agents-mdgit clone --depth 1 https://github.com/LynkByte/ensembleWhat 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 | $0.01001 | $0.01001 |
| Opus 5 | $0.00500 | $0.00500 |
| Sonnet 5 | $0.00200 | $0.00200 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
ensemble 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 yesterday.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Overview
Python MCP server (ensemble-mcp) providing vector memory, drift detection, model routing, skills discovery, session management, codebase indexing, context compression, prompt caching, and a local web dashboard. Fully implemented — 19 MCP tools across 11 subpackages, CLI with serve/install/uninstall/add-agents/add-skills/web commands.
Commands
pip install -e . # editable install
ensemble-mcp # run server (or: python -m ensemble_mcp)
ensemble-mcp install # auto-detect AI tools and register MCP
ensemble-mcp uninstall # remove MCP registration from AI tool configs
ensemble-mcp add-agents # copy agent files (no MCP registration)
ensemble-mcp add-skills # copy skill files (no MCP registration)
ensemble-mcp web # launch web dashboard at localhost:8787
ensemble-mcp web --port 9000 # custom port
ensemble-mcp web --no-open # start without auto-opening browser
python -m pytest tests/ # run tests
ruff check src/ tests/ # lint
ruff format src/ tests/ # format
mypy src/ # typecheck
python -m build # build sdist + wheel
docker build -t ensemble-mcp . # build container
ruff and mypy are fully configured in
pyproject.toml(strict mode, Python 3.11 target).
Architecture
src layout — package lives at src/ensemble_mcp/, mapped via [tool.hatch.build.targets.wheel].
Entry point: __main__.py → server.serve() (stdio MCP server).
| Subpackage | Role |
|---|---|
config/ |
Layered settings, defaults |
contracts/ |
Response envelope and error taxonomy |
memory/ |
ONNX embeddings, SQLite vector store, cosine similarity |
security/ |
Secret redaction, trust boundary enforcement |
state/ |
Session/step lifecycle, idempotency, locks |
tools/ |
19 MCP tool implementations + call-recording utility (8 categories below) |
installer/ |
Auto-detect AI tools, register MCP server |
dashboard/ |
Web dashboard: aiohttp server, JSON API, Alpine.js SPA |
compress/ |
Rule-based text compression engine |
cli/ |
Startup banner |
data/ |
Bundled agent and skill files |
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.
- yesterday First seen · 77 lines · 1,001 tokens per session scan A b95da61ca934
ensemble AGENTS.md is an instructions file published in the GitHub repository LynkByte/ensemble (1 stars, last pushed 29d ago), licensed MIT. It adds 1,001 tokens to every session, about $0.0050 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
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.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.