codex-trace AGENTS.md

Project instructions for a Tauri desktop application with a React frontend and Rust backend. They document the commands used to run, check, format, lint, type-check, and test the project.

In plain words
What is it for?
Use them when changing code, tests, or build-related configuration, then run the documented formatting, linting, type-checking, and test commands before committing.
Why use it?
They give coding agents a consistent way to work on the project and verify changes across both JavaScript or TypeScript and Rust code.

Instructions file for CodexOpenCode

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/pixelpaw-labs/codex-trace/agents-md
Clone the repo
git clone --depth 1 https://github.com/PixelPaw-Labs/codex-trace

Made for: Codex, OpenCode.

Per session 611 This file is loaded in full into every session.
When invoked 611 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 $0.00611 $0.00611
Opus 5 $0.00305 $0.00305
Sonnet 5 $0.00122 $0.00122
Haiku 4.5 $0.00061 $0.00061

Measured 2d ago against content hash 3b24dd304f52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-trace 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 · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Commands

# Dev
npm run dev              # Vite dev server
npm run tauri dev        # Full Tauri desktop app
npm run dev:web          # Web mode (opens browser)

# Lint
npx oxlint              # JS/TS lint
cargo clippy --manifest-path src-tauri/Cargo.toml  # Rust lint

# Format
npx oxfmt               # JS/TS format
cargo fmt --manifest-path src-tauri/Cargo.toml     # Rust format

# Test
npx vitest run           # Frontend tests
cargo test --manifest-path src-tauri/Cargo.toml    # Rust tests

# Type check
npx tsc --noEmit

# All at once
npm run check            # tsc + oxlint + oxfmt --check + clippy + cargo fmt --check + vitest + cargo test

Rule

After every code change (src, tests, config that affects build), always add enough tests for the changes, then run lint, format, and test before committing:

npx oxfmt && npx oxlint && npx tsc --noEmit && cargo fmt --manifest-path src-tauri/Cargo.toml && cargo clippy --manifest-path src-tauri/Cargo.toml -- -D warnings && cargo test --manifest-path src-tauri/Cargo.toml

Architecture

  • Backend: Rust + Tauri v2 + axum HTTP server (port 11424)
  • Frontend: React 19 + TypeScript + Vite
  • Sessions: ~/.codex/sessions/YYYY/MM/DD/rollout-*.jsonl

Key files

  • src-tauri/src/parser/ — JSONL parsing pipeline
    • entry.rs — raw line parsing, format detection
    • discover.rs — session discovery + metadata scan
    • session.rs — full session parse
    • turn.rs — turn boundary detection (new + old format)
    • toolcall.rs — tool call classification by end event
  • src-tauri/src/http_api.rs — axum routes (port 11424)
  • src/App.tsx — 3-view state machine (picker → list → detail)
  • src/components/SidebarTree.tsx — CRITICAL: date-grouped JSONL folder structure
  • shared/types.ts — TypeScript types (must match Rust structs)

JSONL format

Three session_meta variants (new/mid/oldest). Turn boundary detection uses task_started/task_complete for newer CLI; user_message boundaries for older. Tool calls classified by end event type, not function name.

Read the full file on GitHub · 68 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 · 68 lines · 611 tokens per session scan A 3b24dd304f52

Subscribe to this mod's changes

codex-trace AGENTS.md is an instructions file published in the GitHub repository PixelPaw-Labs/codex-trace (93 stars, last pushed 3d ago), licensed MIT. It adds 611 tokens to every session, about $0.0031 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.