Borrowing it
Nothing to install: this file belongs to jfarcand/mirroir-mcp. 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/jfarcand/mirroir-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/jfarcand/mirroir-mcpWrote 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/jfarcand/mirroir-mcp/agents-md)<a href="https://agentmods.dev/instructions/jfarcand/mirroir-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jfarcand/mirroir-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.08303 | $0.08303 |
| Opus 5 | $0.04151 | $0.04151 |
| Sonnet 5 | $0.01661 | $0.01661 |
| Haiku 4.5 | $0.00830 | $0.00830 |
Grade B, and why
mirroir-mcp AGENTS.md scanned grade B with 1 finding 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 3d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
I can run any command WITHOUT permission EXCEPT: How it starts
The opening of the file, as written. The whole thing — 645 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRITICAL: Which Keyboard Shortcuts Reach iOS
Key events DO reach iOS through mirroring. What decides the outcome is whether the focused iOS app implements that shortcut — not whether the keystroke arrives. Do not assume "keyboard never works"; assume "only shortcuts iOS itself defines work", and verify on the device.
Verified working (on-device, 2026-08-31, in a focused text field):
Cmd+Aselect all,Cmd+Ccopy,Cmd+Vpaste — a full type → Cmd+A → Cmd+C → Cmd+A → delete → Cmd+V round-trip restores the text.Cmd+Lselects Safari's address bar —open_urlhas always depended on this.
These are the standard iOS text-editing and Safari shortcuts. type_text RELIES
on Cmd+V: characters with no keycode (CJK, emoji) are routed through the
clipboard, because CGEvent cannot drive an input method — see the next
paragraph for the failure mode that comes with it.
Universal Clipboard is the fragile part, not the keystroke. Cmd+V pastes the
iPhone's clipboard. Getting the Mac's pasteboard onto the phone is Continuity:
Handoff on both ends, Bluetooth + Wi-Fi, same iCloud account. With it off, the
paste silently produces nothing; worse, the sync is asynchronous, so a paste
issued too soon pastes the device's PREVIOUS clipboard value and looks like it
worked. type_text waits pasteboardSyncUs (1.5s) and pastes at most once per
call for exactly this reason.
Still true — back navigation. press_key(key: "[", modifiers: ["command"])
does NOT navigate back: Cmd+[ is a macOS convention that iOS apps do not
implement, so the event arrives and nothing handles it. Back navigation is
OCR-detecting the "<" chevron in the top 15% of the screen and tapping it. The
explorers use tapBackButton(); desktop targets, which DO implement Cmd+[,
use it via DesktopAppStrategy.
Gestures remain the way to drive app UI: tap, swipe, drag, long press,
double tap, and type_text (which needs a focused text field on the iPhone).
Not yet verified: the shortcuts above were confirmed in system UI (Spotlight)
and, for Cmd+L, in Safari. Behaviour inside an arbitrary third-party app has
not been measured — if you depend on a shortcut there, test it first.
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.
- 3d ago Changed · +34 lines · +557 tokens per session 59817707f14b
- 8d ago First seen · 611 lines · 7,746 tokens per session scan B ef83a17a7616
mirroir-mcp AGENTS.md is an instructions file published in the GitHub repository jfarcand/mirroir-mcp (209 stars, last pushed yesterday), licensed Apache-2.0. It adds 8,303 tokens to every session, about $0.0415 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
spec-kit AGENTS.md
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.