Borrowing it
Nothing to install: this file belongs to FortiumPartners/ensemble. 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/FortiumPartners/ensemble/main/CLAUDE.mdgit clone --depth 1 https://github.com/FortiumPartners/ensembleWrote 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/fortiumpartners/ensemble/claude-md)<a href="https://agentmods.dev/instructions/fortiumpartners/ensemble/claude-md"><img src="https://agentmods.dev/badge/instructions/fortiumpartners/ensemble/claude-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/fortiumpartners/ensemble/claude-md"><img src="https://agentmods.dev/badge/instructions/fortiumpartners/ensemble/claude-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 | $0.04301 | $0.04301 |
| Opus 5.5 | $0.01720 | $0.01720 |
| Sonnet 5.5 | $0.00860 | $0.00860 |
| Haiku 4.5 | $0.00430 | $0.00430 |
Grade A, and why
ensemble CLAUDE.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 1mo 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 — 475 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ensemble Plugins - Claude Code Configuration
Modular plugin ecosystem for Claude Code (v6.9.3) | 27 plugins | 48 commands | 38 agents | 4-tier architecture
Where the plugin comes from
Since 2026-09-06 the ensemble marketplace in every Claude config root is a directory source pointed at a worktree we control:
~/projects/.worktrees/ensemble-live branch `live`, tracks sunstone/main
Nothing pulls from a remote marketplace. That worktree decides what every session loads, and nothing lands in it without scripts/ensemble-sync.sh being run.
The hook and watcher must never be referenced at a path inside this repo. They are
installed to ~/.claude/scripts/ by scripts/install-ensemble-hooks.sh; run it after
changing either script. Wiring a machine-wide hook at projects/ensemble/scripts/...
means it exists only while this tree has the right branch checked out — switching branches
deleted it under 44 of 48 live sessions and silently killed the launchd watcher for a day
(#97). The installer is idempotent and rewrites any entry that points back into a worktree. Sunstone-Partners/ensemble is the live upstream; FortiumPartners/ensemble is dormant. Run scripts/ensemble-sync.sh for a dry report and --apply to land it; scripts/provision-ensemble.sh --check reports every config root. Each script's header comment carries its full usage — none of them implements --help.
Quick Reference
Picking a workflow
The full PRD → TRD pipeline is for large features. Running it on a bug costs hours.
| Size of work | Use |
|---|---|
| A bug or small issue | /ensemble:fix-issue — analysis straight to PR |
| A contained feature | create-prd → create-trd, then stop |
| Large or cross-cutting | The full five-step sequence |
| One task in an existing TRD | /ensemble:implement-trd-task --task <id> |
/ensemble:analyze-complexity routes automatically, but pass --route simple\|medium\|complex explicitly — the automatic score under-routes and fails toward less planning (#95). The override is validated; the score is advisory.
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.
- 1mo ago Changed · +39 lines · +679 tokens per session 7e46c8f9683e
- 1mo ago Changed · +23 lines · +321 tokens per session 945de2df041f
- 1mo ago First seen · 413 lines · 3,301 tokens per session scan A da2eee31e9ac
ensemble CLAUDE.md is an instructions file published in the GitHub repository FortiumPartners/ensemble (12 stars, last pushed 11d ago), licensed MIT. It adds 4,301 tokens to every session, about $0.0172 per session on Opus 5.5. 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 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.