agentmods.dev

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.

In plain words
What is it for?
Use them when changing cxstat’s commands, project or token reports, parsing logic, packaging, configuration, or when running its Pyright and Ruff validation.
Why use it?
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.

Instructions file for CodexOpenCode

5 10mo ago A scan 1,222 tokens original MIT
View the source file takeshiD/cxstat
Install

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.

agentmods
npx agentmods add instructions/takeshid/cxstat/agents-md
Clone the repo
git clone --depth 1 https://github.com/takeshiD/cxstat

Made for: Codex, OpenCode.

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. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01222 $0.01222
Opus 5 $0.00611 $0.00611
Sonnet 5 $0.00244 $0.00244
Haiku 4.5 $0.00122 $0.00122

Measured 2d ago against content hash 32b579270e96, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

  1. 2d 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 10mo ago), licensed MIT. It adds 1,222 tokens to every session, about $0.0061 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.

LLMcodex-climetricsvibe-coding
Related

Other instructions, from other repositories

coco AGENTS.md

Instructions for pcopu/coco, covering repository memory notes, auto memory log, session start prompt, runtime notes and self-update safety.

pcopu/coco · 351 tokens

sessions-chronicle AGENTS.md

Instructions for supermaciz/sessions-chronicle, covering repository guidelines, where to look first, terminology, project structure & module organization and fast dev loop.

supermaciz/sessions-chronicle · 1,610 tokens

codex-bee AGENTS.md

AGENTS.md instructions for usulpro/codex-bee, covering agents.md, project summary, product goals, current stack and working agreements.

usulpro/codex-bee · 1,560 tokens

sessions-chronicle CLAUDE.md

Instructions for supermaciz/sessions-chronicle, a project described as: A Gtk/Adwaita app to browse and search your AI coding sessions.

supermaciz/sessions-chronicle · 5 tokens

apm python.instructions.md

Python development guidelines.

microsoft/apm · 78 tokens

vibe-coding-prompt-template backend.instructions.md

Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.

KhazP/vibe-coding-prompt-template · 139 tokens