What is dexuse AGENTS.md?

A set of AGENTS.md instructions for working on dexuse, a Rust command-line program that displays AI usage data in a terminal dashboard.

For guiding changes to the Rust terminal interface, JSON output, data aggregation, npm wrapper, screenshots, tests, builds, and packaging.

It gives the coding assistant the project's technology choices, privacy requirements, workflow commands, and quality checks in one place.

dexuse AGENTS.md — Instructions file by yashau

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/yashau/dexuse/agents-md

Clone the repo

git clone --depth 1 https://github.com/yashau/dexuse

Made for: Codex, OpenCode.

Per session 2,021 This file is loaded in full into every session.

When invoked 2,021 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.

Model	Per session	Once invoked
Fable 5	$0.02021	$0.02021
Opus 5	$0.01010	$0.01010
Sonnet 5	$0.00404	$0.00404
Haiku 4.5	$0.00202	$0.00202

Measured 2d ago against content hash 499db58d1b01, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dexuse 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 · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This repo is a Rust/Ratatui CLI packaged for npx @yashau/dexuse with a dexuse binary. Keep it fast, local-first, modular, and screenshot-polished.

Product promise

dexuse reads local AI usage stores and turns them into a fancy terminal dashboard plus JSON summaries. It must never upload user history or print secrets. Treat local session files, transcript text, database rows, and paths as sensitive. Usage totals are fine; raw prompts/messages are not.

Stack

Rust CLI and TUI: src/
TUI framework: Ratatui + Crossterm
JSON output: src/output.rs
Aggregation/model types: src/model.rs, src/aggregate.rs
npm wrapper: scripts/dexuse.js
screenshot harness: scripts/render_tui_screenshots.cjs
deterministic usage fixtures: fixtures/usage/
primary repo tool: mise (mise.toml pins Rust/Node and defines install, quality gates, build, bundle, screenshot, smoke, and packaging tasks)
JS package manager: pnpm (packageManager is pinned in package.json)

Use mise first for repo workflows (mise install, mise run check, mise run screenshots, mise run pack). Use pnpm, not npm, when managing JS dependencies directly.

Quality gates

Before saying a change is done, run the relevant mise task subset. For user-facing, parser, fixture, or packaging changes, run the primary gate and any artifact-specific tasks:

mise install
mise run check
mise run screenshots
mise run pack

Underlying commands, useful when isolating a failing step:

cargo fmt --check
python scripts/smoke_json.py
cargo test
cargo clippy --all-targets --all-features -- -D warnings
cargo build --release
python scripts/bundle_current.py
pnpm run screenshots
pnpm pack --dry-run

Notes:

Rebuild release before trusting pnpm exec dexuse or screenshot output. The JS wrapper may prefer bin/dexuse-<platform>-<arch>.
scripts/with_timeout.py is the preferred timeout wrapper in automation.
Miri uses nightly. Hermes SQLite tests are ignored under Miri because SQLite/file FFI is not supported by Miri on Windows.

Read the full file on GitHub · 288 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.

2d ago First seen · 288 lines · 2,021 tokens per session scan A 499db58d1b01

Subscribe to this mod's changes

dexuse AGENTS.md is an instructions file published in the GitHub repository yashau/dexuse (1 stars, last pushed 2mo ago), licensed MIT. It adds 2,021 tokens to every session, about $0.0101 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.

codex codex-cli hermes-agent mise npm openai

dexuse AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Product promise

Stack

Quality gates

What this file has done since we first saw it

Other instructions, from other repositories

codexia AGENTS.md

flowix CLAUDE.md

CodexPotter AGENTS.md

rembric CLAUDE.md

codex-howto AGENTS.md

codex-docs AGENTS.md