Mirage is a virtual terminal for AI agents that presents files, command-line tools, and configurable runtimes through one interface. It helps agents access data and run computations across services with controlled visibility and actions, and the catalogue entries provide related integrations.
Borrowing it
Nothing to install: this file belongs to strukto-ai/mirage. 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/strukto-ai/mirage/main/CLAUDE.mdgit clone --depth 1 https://github.com/strukto-ai/mirageWrote 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/strukto-ai/mirage/claude-md)<a href="https://agentmods.dev/instructions/strukto-ai/mirage/claude-md"><img src="https://agentmods.dev/badge/instructions/strukto-ai/mirage/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/strukto-ai/mirage/claude-md"><img src="https://agentmods.dev/badge/instructions/strukto-ai/mirage/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 | $0.04363 | $0.04363 |
| Opus 5.5 | $0.01745 | $0.01745 |
| Sonnet 5.5 | $0.00873 | $0.00873 |
| Haiku 4.5 | $0.00436 | $0.00436 |
Grade A, and why
mirage 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 today.
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 — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
MIRAGE is a virtual terminal for AI agents: a bash-compatible shell over one virtual filesystem that mounts anything (object stores, SaaS, databases, disk) at a prefix. It is the control plane between an agent and its data: every backend is reached through one async-native op dispatcher, with an index, a read-through cache and per-mount policy in the path, so a listing costs one request and a refused action never reaches the service. It is implemented in Python and in TypeScript with the same layout and the same semantics.
Development
Commands
- Python lives in
python/(mirage/,tests/). Setup:cd python && uv sync --all-extras. Add dependencies withuv add. Test:uv run pytest. - TypeScript lives in
typescript/(packages/core,node,browser,cli,server,agents,dsh,opencode):pnpm install,pnpm build,pnpm typecheck,pnpm test. Rebuild the dists after a merge; integ and the examples import them. - Rust lives in
rust/, one Cargo workspace:mirage-rsholds the command streams both hosts run,rust/pythonis its PyO3 module (mirage._rs, which maturin builds into mirage-ai:uv syncbuilds it and rebuilds it after a Rust change) andrust/wasmthe module the TypeScript core embeds (typescript/packages/core/scripts/embed-rs.mjs, run byprepare,build,testandtypecheck). Both need cargo onPATH;rust/rust-toolchain.tomlpins it. Test:cargo test --workspaceinrust/.scripts/gen_unicode_width.py(Unicode's data files) andscripts/gen_rust_notices.py(cargo about0.9.2) regenerate their outputs; CI fails when either is stale. - Lint everything:
./python/.venv/bin/pre-commit run --all-filesfrom the repo root (the venv binary, soexamples/is included). - Examples run from the repo root with the venv interpreter:
./python/.venv/bin/python examples/python/vfs/s3/s3.py. - Do not add a changeset.
typescript/.changeset/stays as it is for now: the public interface is still moving, so a per-PR version note describes a surface that changes again before it ships. Nothing gates on one. The release notes get written once the interface settles.
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.
- today Changed · +3 lines · +47 tokens per session b45832f02a07
- yesterday Changed · +2 lines · +23 tokens per session 0e5cdc499348
- 6d ago Changed · +6 lines · +114 tokens per session fdaf16010eb1
- 7d ago Changed · +8 lines · +123 tokens per session 8f759354b4d3
- 9d ago Changed · +42 lines · +648 tokens per session c750506a56e2
- 10d ago Changed 860ad5ae98d6
- 15d ago Changed · +2 lines · +46 tokens per session 0e442fdc1e13
- 17d ago Changed · +4 lines · +60 tokens per session dee2c15e188a
- 20d ago Changed · -1 lines · +18 tokens per session 47740a7cddda
- 23d ago First seen · 254 lines · 3,284 tokens per session scan A c95721cd7403
mirage CLAUDE.md is an instructions file published in the GitHub repository strukto-ai/mirage (3,739 stars, last pushed today), licensed Apache-2.0. It adds 4,363 tokens to every session, about $0.0175 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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.