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/finbarr/yolobox/agents-mdgit clone --depth 1 https://github.com/finbarr/yoloboxWrote 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/finbarr/yolobox/agents-md)<a href="https://agentmods.dev/instructions/finbarr/yolobox/agents-md"><img src="https://agentmods.dev/badge/instructions/finbarr/yolobox/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 | $0.03354 | $0.03354 |
| Opus 5 | $0.01677 | $0.01677 |
| Sonnet 5 | $0.00671 | $0.00671 |
| Haiku 4.5 | $0.00335 | $0.00335 |
Grade C, and why
yolobox AGENTS.md scanned grade C with 1 finding 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Host Codex config import must preserve a valid existing container `/home/yolo/.codex/auth.json` when the host config has no usable auth file. Do not `rm -rf /home/yolo/.codex` before importing host Codex config. How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is the working agreement for changes in this repository.
Workflow
Default workflow for this repo:
- Make the requested code or docs change directly.
- Verify it thoroughly.
- Commit the change before finishing.
Whenever behavior, UX, defaults, flags, docs, or built-in agent guidance change, audit the matching user-facing surfaces in this repo and update them too:
- README.md
- the docs site under docs/
- the bundled skills under skills/
- the setup command/wizard in cmd/yolobox/main.go
Do not stop at unit tests when behavior can be exercised for real. If a change affects runtime behavior, flags, mounts, image builds, config loading, or release automation, run the actual path and verify the output.
If full end-to-end verification is blocked by the environment, state exactly what was run, what was not run, and why.
Any hard-earned lesson that changes how future work should be done belongs in AGENTS.md.
Build Commands
make build # Build the yolobox binary
make test # Run unit tests
make lint # Run go vet (and golangci-lint if installed)
make image # Build the Docker base image
make smoke-test # Run smoke tests on container tools
make install # Build and install to ~/.local/bin
make clean # Remove built binary
Verification Standard
For non-trivial code changes, start here:
make clean && make build && make test
make lint
./yolobox version
./yolobox help
./yolobox config
Before any release or tag push, update CHANGELOG.md with the release's user-facing changes. Release tags must be created only from a clean, up-to-date master branch; do not tag feature branches, and push only master plus the specific release tag. make lint is also mandatory and must include the same golangci-lint coverage that CI runs. If local make lint reports golangci-lint not installed, skipping, install/run golangci-lint locally or run the CI linter equivalent before shipping.
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.
- 4d ago First seen · 141 lines · 3,354 tokens per session scan C e9228c6b4570
yolobox AGENTS.md is an instructions file published in the GitHub repository finbarr/yolobox (639 stars, last pushed 6d ago), licensed MIT. It adds 3,354 tokens to every session, about $0.0168 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.