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/farukkamcici/mectrics/agents-mdgit clone --depth 1 https://github.com/farukkamcici/mectricsWrote 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/farukkamcici/mectrics/agents-md)<a href="https://agentmods.dev/instructions/farukkamcici/mectrics/agents-md"><img src="https://agentmods.dev/badge/instructions/farukkamcici/mectrics/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 | $0.04487 | $0.04487 |
| Opus 5 | $0.02243 | $0.02243 |
| Sonnet 5 | $0.00897 | $0.00897 |
| Haiku 4.5 | $0.00449 | $0.00449 |
Grade A, and why
mectrics 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 5d 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Working agreement for mectrics
This file is the source of truth for conventions in this repository. It applies to any
AI agent or human contributor. CLAUDE.md points here.
0. Golden rule: English-only repository
Everything committed to this repo is in English — no exceptions:
- Source code: identifiers, types, function names, variables.
- Comments and documentation comments.
- All Markdown docs (
README.md,docs/**). - Commit messages, branch names, PR titles/descriptions.
- User-facing UI strings: English is the base/development language (localized to other languages via the String Catalog — see §2).
The only place another language may appear is a live chat conversation with the user (who may write in Turkish). Nothing from that chat leaks into the repo in another language.
1. Project shape
Packages/MetricsKit/— UI-independent metric engine (SwiftPM). Providers, scheduler, ring-buffer store, engine. No UI, no localization (data-only, English identifiers).swift build,swift test,swift run metricskit-demo(internal live provider readout).swift run mectricsruns the read-only user CLI. It reads alert configuration from the app and offerscheck,snapshot, event streaming, and rule listing.Tests/MectricsCLITestsowns its process, exit-code, JSON-fixture, and failure-path contracts.- Builds in the Swift 6 language mode and must stay warning-free.
MetricProviderrequiresSendable; providers are@unchecked Sendablebecause the engine samples them on one serial queue. Guard anything read outside that queue with a lock.
Mectrics/— the menu bar app (SwiftUI + AppKit).project.yml— XcodeGen project definition. This is the source;Mectrics.xcodeprojis generated. After editingproject.ymlor adding/removing source files, runxcodegen generate.docs/— the architecture deep dive, and nothing else. Contributor-facing only: planning notes, roadmaps, backlogs, and maintainer-only runbooks do not belong in the public repository. The release procedure lives inscripts/release.sh, which is self-documenting through its required environment variables.
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.
- 5d ago First seen · 291 lines · 4,487 tokens per session scan A 2d83e88c1167
mectrics AGENTS.md is an instructions file published in the GitHub repository farukkamcici/mectrics (143 stars, last pushed 4d ago), licensed MIT. It adds 4,487 tokens to every session, about $0.0224 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 2026-08-30.
Other instructions, from other repositories
CodexBar CLAUDE.md
Claude Code instructions for bob-zebedy/CodexBar, covering claude.md, 写作风格, 代码和注释, 项目文档 and 项目概述.
CodexBar AGENTS.md
AGENTS.md instructions for bob-zebedy/CodexBar, covering repository guidelines, 项目结构与模块组织, 构建、测试与开发命令, 写作风格 and 代码和注释.
Applite CLAUDE.md
Instructions for milanvarady/Applite, covering claude.md, project overview, build & run, architecture and data flow.
scarf AGENTS.md
AGENTS.md instructions for awizemann/scarf: This repo carries its own agent memory — plain files in git, served by the in-repo memophant-mcp MCP server, managed by the Memophant macOS app. It works the same for every agent (Claude Code, Codex, Cursor, Gemini, Copilot). This block is regenerated between the memophant…
scarf copilot-instructions.md
Copilot instructions for awizemann/scarf: File memory notes under one of six folders (architecture/conventions/decisions/operations/project/roadmap), never the root. When a note is grounded in code, pass sourcepaths (the repo files it depends on) so Memory Health can drift-check it — an unanchored code note can't be…
cuda-metal AGENTS.md
AGENTS.md instructions for Lulzx/cuda-metal, covering agents.md — cumetal development guide, project identity, current focus, repository structure and non-negotiable constraints.