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.
npx agentmods add instructions/antoinetoussaint/lazybox/agents-mdgit clone --depth 1 https://github.com/AntoineToussaint/lazyboxWrote 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/antoinetoussaint/lazybox/agents-md)<a href="https://agentmods.dev/instructions/antoinetoussaint/lazybox/agents-md"><img src="https://agentmods.dev/badge/instructions/antoinetoussaint/lazybox/agents-md.svg" alt="Measured on agentmods" 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 | $0.04504 | $0.04504 |
| Opus 5 | $0.02252 | $0.02252 |
| Sonnet 5 | $0.00901 | $0.00901 |
| Haiku 4.5 | $0.00450 | $0.00450 |
Grade A, and why
lazybox 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
What is lazybox?
A reactive PR inbox TUI. Instead of checking GitHub, events flow to you — new comments, CI failures, review requests surface automatically with read/unread tracking. Each task becomes a session with an embedded terminal for running Codex or a shell in a git worktree.
Source-agnostic: GitHub is one provider, but Linear/Jira/etc. plug in the same way.
Build & Run
cargo build # build (first build compiles SQLite, takes ~30s)
cargo run -p lazybox-tui-boot # run (uses `gh auth token` automatically)
cargo test --workspace # tests
cargo clippy --workspace # lint
make run # same as cargo run -p lazybox-tui-boot
Logs go to /tmp/lazybox.log. State persisted in ~/.lazybox/v2/state.db.
Before you compile or test — check shared resources
Lazybox routinely runs many agents on one box. Before cargo build,
cargo test, or cargo clippy, check for available resources — sample the
system load (uptime vs. nproc) and back off, throttle the job count
(CARGO_BUILD_JOBS), or scope to the crate you touched (cargo test -p <crate>) while iterating when the machine is already busy. Blindly grabbing
every core when fifteen other agents are doing the same is what drives the box
to 100% CPU. Throttling changes how hard you compile, never whether the
full gate suite runs before you push — scoped runs miss cross-crate gates.
Full guidance: docs/agent-resource-awareness.md.
Staying current (outdated-build guard)
A uniformly-stale build — daemon and client compiled from the same
old commit — passes every wire check silently and reproduces
already-fixed bugs. At startup crates/tui/src/build_guard.rs checks
the channel appropriate to the running build and opens a dismissable
update modal when something newer exists:
- Dev/source builds compare the baked
LAZYBOX_BUILD_GIT_SHAwith the baked checkout's currentHEADand, when it can fast-forward safely, that branch's tracking upstream. This path performs no network request and still runs for dirty builds. - Cargo-dist release builds compare
CARGO_PKG_VERSIONwith GitHub's latest published release through a bounded, cached API request.
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.
- 3d ago First seen · 311 lines · 4,504 tokens per session scan A 366130cca358
lazybox AGENTS.md is an instructions file published in the GitHub repository AntoineToussaint/lazybox (5 stars, last pushed 3d ago), licensed MIT. It adds 4,504 tokens to every session, about $0.0225 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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.