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/cyberuni/cyber-figma/agents-mdgit clone --depth 1 https://github.com/cyberuni/cyber-figmaWrote 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/cyberuni/cyber-figma/agents-md)<a href="https://agentmods.dev/instructions/cyberuni/cyber-figma/agents-md"><img src="https://agentmods.dev/badge/instructions/cyberuni/cyber-figma/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 | $0.04529 | $0.04529 |
| Opus 5 | $0.02264 | $0.02264 |
| Sonnet 5 | $0.00906 | $0.00906 |
| Haiku 4.5 | $0.00453 | $0.00453 |
Grade A, and why
cyber-figma 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 4d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding assistants when working with code in this repository.
Skill Augmentations
When reading any SKILL.md file, always check whether a SKILL.local.md exists in the same directory. If it does, treat its contents as additional instructions that extend the base skill. Local augmentations take precedence over the base skill where they conflict.
Commit Discipline
Auto-commit rule: When a unit of work is complete and verified, commit it immediately — do not wait for the user to ask. Batching multiple units into one commit, or finishing all work before committing, are both violations of this rule.
Unit of work: one coherent, independently revertable change — one domain's refactor, one feature, one bugfix, one test suite expansion for one concern, one config change. Never two unrelated concerns in the same commit. A TDD red-green-refactor cycle alone is not a commit boundary; commit when the full intended change is complete and tests pass. If the working tree has unrelated changes, leave them unstaged — commit the current unit first, then continue.
- Conventional Commits:
feat:,fix:,refactor:,test:,docs:,chore: - One concern per commit; never batch unrelated changes
- Stage only files for this unit:
git add <files>, then verify withgit diff --cached - Never use
git add .,git add -A, orgit add -p(interactive commands agents cannot run) - Never commit with red tests; run validation commands first
References
commit-workskill — staging, splitting, and message writing when committingnpx cyber-skills@<version> governance show skill-repo-structure— discipline section format rules
Development Workflow
Before writing any production code, invoke the test-driven-development skill. This applies whether coding starts from a user request or from your own initiative after plan approval.
What This Repo Is
cyber-figma — an npm package that wraps the Figma REST API as:
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.
- 4d ago First seen · 216 lines · 4,529 tokens per session scan A 38ddd654f20b
cyber-figma AGENTS.md is an instructions file published in the GitHub repository cyberuni/cyber-figma (0 stars, last pushed 10d ago), licensed MIT. It adds 4,529 tokens to every session, about $0.0226 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
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).
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.
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 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.
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.