What is cxstat AGENTS.md?

Repository instructions for cxstat, a command-line tool that reads Codex session logs and reports usage of tools, tokens, and projects. They describe its Python command structure, data aggregation, output, configuration, and required checks.

Use them when changing cxstat’s commands, project or token reports, parsing logic, packaging, configuration, or when running its Pyright and Ruff validation.

They give agents the project’s intended architecture and quality rules, including the commands that must pass before a coding change is accepted. This keeps maintenance work consistent and verifiable.

How takeshiD/cxstat configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to takeshiD/cxstat. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/takeshiD/cxstat/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/takeshiD/cxstat

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/takeshid/cxstat/agents-md/github.svg)](https://agentmods.dev/instructions/takeshid/cxstat/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/takeshid/cxstat/agents-md"><img src="https://agentmods.dev/badge/instructions/takeshid/cxstat/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/takeshid/cxstat/agents-md"><img src="https://agentmods.dev/badge/instructions/takeshid/cxstat/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,222 This file is loaded in full into every session.

When invoked 1,222 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01222	$0.01222
Opus 5.5	$0.00489	$0.00489
Sonnet 5.5	$0.00244	$0.00244
Haiku 4.5	$0.00122	$0.00122

Measured 2mo ago against content hash 32b579270e96, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cxstat 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 2mo 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.

AGENTS.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cxstat Agent Design

Overview

Purpose: gather MCP and shell tool usage from Codex CLI session logs under ~/.codex/sessions and expose user-friendly CLI reports.
Success criteria: Typer-based command structure, Rich-formatted summaries, and project-wide plus per-project token statistics.
Constraints: Python 3.12+, existing parsing utilities in cxstat/main.py, mandatory Pyright/Ruff validation in follow-up implementation.
Quality gate: every coding iteration must run uv run pyright and uv run ruff check before changes are considered complete.

CLI Architecture

Replace the standalone main() argparse entry point with a Typer application (cxstat/cli.py).
Root callback defines shared options (--sessions-root, --top, --detail, --theme).
Commands:
- cxstat (default action mapped to summary) prints global usage breakdown across all projects and tools.
- cxstat list-project lists each project (derived from session path) with aggregated token totals and call counts.
Packaging: update pyproject.toml script entry to cxstat = "cxstat.cli:app"; expose app from cxstat/__init__.py.

Data Model & Aggregation

Reuse CallRecord and Aggregate to capture per-invocation details and token metrics.
Introduce structures:
- ProjectUsage: project identifier plus per-tool Aggregate map.
- UsageReport: overall totals, project summaries, and optional detailed rankings.
Enhance parse_logs to emit project-aware records by inferring the project root from each log file path.
Expand aggregation logic (aggregate_usage) to compute:
- Global tool/provider/detail stats (existing functionality).
- Per-project totals for shell vs MCP (extendable to other tools).

Presentation Layer

Build dedicated rendering helpers in cxstat/view.py (or similar) that accept aggregation results and produce Rich tables.
Use Console.print with Table objects, configuring column alignment, styles, and optional zebra striping for readability.
summary command: render counts of total tokens, input/output split, call volume, and top-N rankings (limit via --top, colour palette via --theme).
list-project command: render project name/path, combined token totals, per-tool splits, and latest invocation timestamp (if available).
Provide graceful empty-state messaging ([yellow]No data found[/yellow]) when logs are absent.

Read the full file on GitHub · 102 lines

Changes

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.

2mo ago First seen · 102 lines · 1,222 tokens per session scan A 32b579270e96

Subscribe to this mod's changes

cxstat AGENTS.md is an instructions file published in the GitHub repository takeshiD/cxstat (5 stars, last pushed 1y ago), licensed MIT. It adds 1,222 tokens to every session, about $0.0049 per session on Opus 5.5. 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.

LLM codex-cli metrics vibe-coding

cxstat AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cxstat AGENTS.mdtakeshiD/cxstat	Instructions file	5	1y ago	MIT	A	1,222	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

cxstat: Instructions file for Codex