Borrowing it
Nothing to install: this file belongs to tetracoralla/armorial. 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/tetracoralla/armorial/main/AGENTS.mdgit clone --depth 1 https://github.com/tetracoralla/armorialWrote 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/tetracoralla/armorial/agents-md)<a href="https://agentmods.dev/instructions/tetracoralla/armorial/agents-md"><img src="https://agentmods.dev/badge/instructions/tetracoralla/armorial/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 | $0.00522 | $0.00522 |
| Opus 5 | $0.00261 | $0.00261 |
| Sonnet 5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
armorial 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 6d 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 — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Armorial repository contract
Before any review, read docs/REVIEW_CONTRACT.md. A plain owner request to
review, audit, 审核, or 复核 invokes that contract end to end; treat it as the
minimum scope and report tools-dev workspace escalations without asking the
owner for another checklist.
This repository owns a design-system-aware icon selection kernel. Current source and executable contracts outrank generated examples or prior reports.
Product boundary
- The current asset provider is the pinned
@icon-park/svgpackage. Reuse its geometry; do not invent, redraw, or silently mutate SVG paths. - The kernel owns metadata validation, deterministic search, project policy resolution, per-call render overrides layered over the effective policy, capability reporting, ambiguity, rendering, and stable errors.
- CLI, local web UI, MCP/MCP App, and Figma are adapters over the same
IconKernel; do not duplicate search, policy, rendering, or selection-decision rules in an adapter. - A policy supplies default/context IconPark parameters and may pin semantic selections. A per-call render override that changes those values must be reported as
overridden, not silently called policy-compliant. The product must not claim that arbitrary filled SVG libraries can be normalized by changing stroke attributes. - MCP tool inputs never accept paths, URLs, raw SVG, source code, or unrestricted objects. The server operator may load one policy file at startup.
- Generated SVG must be deterministic for the same icon and effective policy, have bounded size, and contain no scripts, event handlers, or external references.
icon-policy.schema.jsonis generated fromIconPolicySchema;npm run schema:checkmust detect drift.
Acceptance lanes
- Development regression:
npm run check. - Runtime Agent transport: start
armorial-mcp, verify five model-visible tools plus one app-only helper, execute resolve/search/get/batch/choose through MCP with and without therenderoverride, and read the MCP App resource. - Runtime human surface: execute CLI search, ambiguity, policy-pinned resolve, SVG output, and invalid-policy recovery; launch the web UI and exercise search, selection, appearance override and reset, Copy SVG, download, drag data, Copy for Agent, and narrow layout; import the Figma development plugin and exercise click/drop insertion, real Component creation, outline, layer structure/naming, settings persistence, and readback on a disposable page.
- Business and experience acceptance remains an owner judgment; green checks do not make that verdict.
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.
- 6d ago First seen · 26 lines · 522 tokens per session scan A e5a8f115a34e
armorial AGENTS.md is an instructions file published in the GitHub repository tetracoralla/armorial (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 522 tokens to every session, about $0.0026 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
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).
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.
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 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).
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.