Borrowing it
Nothing to install: this file belongs to Aptica-Solutions/a-mcp-runmeter. 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/Aptica-Solutions/a-mcp-runmeter/main/AGENTS.mdgit clone --depth 1 https://github.com/Aptica-Solutions/a-mcp-runmeterWrote 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/aptica-solutions/a-mcp-runmeter/agents-md)<a href="https://agentmods.dev/instructions/aptica-solutions/a-mcp-runmeter/agents-md"><img src="https://agentmods.dev/badge/instructions/aptica-solutions/a-mcp-runmeter/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/aptica-solutions/a-mcp-runmeter/agents-md"><img src="https://agentmods.dev/badge/instructions/aptica-solutions/a-mcp-runmeter/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 | $0.04700 | $0.04700 |
| Opus 5.5 | $0.01880 | $0.01880 |
| Sonnet 5.5 | $0.00940 | $0.00940 |
| Haiku 4.5 | $0.00470 | $0.00470 |
Grade C, and why
a-mcp-runmeter AGENTS.md scanned grade C 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 29d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Never** run `rm -rf`, force-push to main, or drop database tables without explicit confirmation How it starts
The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
The one authored rules file for this repository. Every AI coding agent in scope
reads it: Codex and GitHub Copilot in VS Code load it directly, and Claude loads it
through the one-line CLAUDE.md import stub. Edit rules here and nowhere else.
Keep this file well under 32 KiB, the Codex combined limit. Long reference material
belongs in _engineer/ or an a-brain document, fetched on demand.
A repository on the lightweight template profile receives this file, CLAUDE.md,
.claude/, the boundary workflow and the pre-commit config, and nothing else. There,
sections that point into _engineer/, docs/ or AI-TASKS.md do not apply; the rules
themselves still do.
Work Ledger: check it first
Before answering any question about prior work, history or status, and at the start
of every task, call brain_ledger_search on the a-brain MCP server (the Codex
namespace is a_brain) for the repo or topic. Treat what it returns as the first
source; use gh or git only to verify or extend it, and say which you used. When a
task finishes, call brain_ledger_add with one line. This is how one tool learns
what another already did.
This Repository
The block between the markers belongs to this repository. Template sync never touches it. Everything outside it is owned by a-repo-template: change it there.
OpenAI Codex CLI — Project Standards
This file is auto-loaded by the OpenAI Codex CLI.
Loading order: root → current directory (downward path only).
Also reads ~/.codex/AGENTS.md as a global file. Combined limit: 32 KiB.
Project Layout
| Path | Purpose |
|---|---|
AI-TASKS.md |
Canonical task list — read before starting any work |
_engineer/REQUIREMENTS.template.md |
Project scope and requirements (copy → REQUIREMENTS.md) |
_engineer/ENGINEER-FLOW.md |
Engineer lifecycle checklist |
_engineer/ENGINEER-README.md |
Shared AI rules, conventions, and guardrails |
_engineer/ado-sync/ |
ADO sync utilities and scripts |
_engineer/dev-env/ |
Terminal profile and dev-machine setup scripts |
_engineer/hipaa-sanitize/ |
HIPAA redaction utility |
_engineer/dev-env/log_util.py |
Structured JSON logging utility — import in all Python scripts |
_engineer/workbench/ |
Scratch space — not deployed, not reviewed |
requirements.txt |
Python dependencies — includes python-json-logger |
docs/ |
Human-facing documentation templates |
infra-setup/ |
Azure Bicep — main.bicep subscription-scoped orchestration; individual templates are standalone modules |
tests/fixture-library/ |
Shared fixtures — never real user data |
tests/test-case-N/ |
Scenario test cases; run tests/new-test-case.ps1 to scaffold |
logs/dev-testing/ |
Log output during active development |
logs/test-case-N/ |
Log output per scenario run |
publish/ |
Build output / release artefacts — gitignored |
.mcp.json |
Project-level MCP server configuration |
codex.json |
Codex project config including MCP servers |
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.
- 29d ago Changed · +3 lines · +54 tokens per session b6bcda4bb363
- 1mo ago Changed · +348 lines · +3,488 tokens per session 1ac63bef9874
- 1mo ago Changed · -44 lines · -459 tokens per session efb8fe80a70b
- 1mo ago First seen · 171 lines · 1,617 tokens per session scan C 486602393e97
a-mcp-runmeter AGENTS.md is an instructions file published in the GitHub repository Aptica-Solutions/a-mcp-runmeter (0 stars, last pushed 1mo ago), licensed MIT. It adds 4,700 tokens to every session, about $0.0188 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
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).
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.