Borrowing it
Nothing to install: this file belongs to denysosadchyi/figmosha2. 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/denysosadchyi/figmosha2/master/AGENTS.mdgit clone --depth 1 https://github.com/denysosadchyi/figmosha2Wrote 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/denysosadchyi/figmosha2/agents-md)<a href="https://agentmods.dev/instructions/denysosadchyi/figmosha2/agents-md"><img src="https://agentmods.dev/badge/instructions/denysosadchyi/figmosha2/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/denysosadchyi/figmosha2/agents-md"><img src="https://agentmods.dev/badge/instructions/denysosadchyi/figmosha2/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 | $0.05805 | $0.05805 |
| Opus 5.5 | $0.02322 | $0.02322 |
| Sonnet 5.5 | $0.01161 | $0.01161 |
| Haiku 4.5 | $0.00581 | $0.00581 |
Grade B, and why
figmosha2 AGENTS.md scanned grade B with 2 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 21d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s -X POST http://localhost:8787/exec -d '{"code":"...","target":"Icons"}' Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST http://localhost:8787/exec \ How it starts
The opening of the file, as written. The whole thing — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figmosha 2.0 — agent instructions
For any coding agent working in this repo: Codex reads this file directly, Claude Code through
CLAUDE.md (which just imports it). Machine-specific paths and hosts live in CLAUDE.local.md
(gitignored) — read it first if it exists, whichever agent you are.
Drive Figma by sending JS code through a local bridge that's connected to a custom plugin running inside Figma Desktop.
How to send code
macOS / Linux: there is no
pythoncommand on a stock Mac — wherever this file sayspython figmosha.py, run./venv/bin/python figmosha.py(orpython3 figmosha.py).
# Preferred — subcommand-style
python figmosha.py exec "return figma.currentPage.name"
python figmosha.py exec --file script.js
# Shorthand (auto-prepends `exec`)
python figmosha.py "return figma.currentPage.name"
# High-level commands (covered below) save tokens for common operations
python figmosha.py text 185:21880 "Привіт"
python figmosha.py variant 185:21883 "Property 1=Default"
# Quick HTTP (no Python needed)
curl -s -X POST http://localhost:8787/exec \
-H 'Content-Type: application/json' \
-d '{"code":"return figma.currentPage.id"}'
# Status
curl -s http://localhost:8787/status # {"plugin_connected": ..., "files": [...], "pending": 0, "abandoned": []}
Multiple files: targets (-T) — READ THIS FIRST
The bridge holds one connection per open Figma file that is running the plugin, not one globally.
python figmosha.py targets # name / doc id / fileKey / conn / queue (busy, waiting)
curl -s http://localhost:8787/targets
# -T is a per-subcommand flag — it goes AFTER the subcommand, never before it
python figmosha.py exec "return figma.root.name" -T "Component Library"
python figmosha.py tree 123:456 -T "Component Library"
curl -s -X POST http://localhost:8787/exec -d '{"code":"...","target":"Icons"}'
target matching (resolve_target in bridge.py): document id (the doc column, 6+ chars) →
connection id → exact file name (case-insensitive) → exact fileKey → unambiguous substring of the name.
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.
- 21d ago Changed · +59 lines · +1,065 tokens per session 8f5bb70caf38
- 25d ago First seen · 343 lines · 4,740 tokens per session scan B b5944ecd1ebc
figmosha2 AGENTS.md is an instructions file published in the GitHub repository denysosadchyi/figmosha2 (110 stars, last pushed 22d ago), licensed MIT. It adds 5,805 tokens to every session, about $0.0232 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-03.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.