What is console-toolkit AGENTS.md?

A set of AGENTS.md instructions for the console-toolkit project, a zero-dependency JavaScript library for terminal and text-based interface output.

Guiding changes to console-toolkit while preserving its ESM structure, hand-written type files, source layout, and testing expectations.

It tells coding agents the project's required module format, file conventions, dependency policy, style, and type-definition rules.

console-toolkit AGENTS.md — Instructions file by uhop

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/uhop/console-toolkit/agents-md

Clone the repo

git clone --depth 1 https://github.com/uhop/console-toolkit

Made for: Codex, OpenCode.

Per session 966 This file is loaded in full into every session.

When invoked 966 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	$0.00966	$0.00966
Opus 5	$0.00483	$0.00483
Sonnet 5	$0.00193	$0.00193
Haiku 4.5	$0.00097	$0.00097

Measured 2d ago against content hash e383ee37fd4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

console-toolkit 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.

console-toolkit — AI Agent Rules

Project identity

console-toolkit is a zero-dependency ESM JavaScript library for rich CLI/TUI output: styled text, boxes, panels, tables, charts, plots, turtle graphics, and spinners. Node.js 22+, Bun, Deno.

Critical rules

ESM-only. All imports must use .js extensions: import Box from './box.js'.
No runtime dependencies. Never add packages to dependencies. Only devDependencies are allowed.
No build step. Source JS in src/ is shipped directly. Do not create build scripts or compiled output.
Hand-written .d.ts files. They are NOT generated. When modifying a public API, update both the .js and .d.ts files.
No JSDoc in .js files. API contracts live in the sidecar .d.ts only. Don't add /** ... */ blocks to src/*.js; they duplicate the .d.ts and rot out of sync.
Do not modify or delete test expectations without understanding why they changed.

Code style

Prettier: 120 char width, single quotes, no bracket spacing, no trailing commas, arrow parens "avoid".
2-space indentation (.editorconfig).
Imports at top of file. No dynamic imports unless necessary.
Comments are why-markers only — a non-trivial decision/constraint or an algorithm reference; never narration of what the code does. Type docs live in the .d.ts, not as JSDoc in .js.

Architecture quick reference

Box is immutable — methods return new Box instances.
Panel is mutable — methods mutate this and return this for chaining.
Method aliases use addAlias/addAliases from meta.js.
pad(t, r, b, l) follows CSS shorthand order.
Three text containers convert between each other: strings (string[]), Box, Panel.
SGR styling: Style class with fluent API; s/c tagged template literals.

Writing tests

Tests use tape-six. For the full testing API, patterns, and conventions see node_modules/tape-six/TESTING.md.

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.

2d ago First seen · 68 lines · 966 tokens per session scan A e383ee37fd4d

Subscribe to this mod's changes

console-toolkit AGENTS.md is an instructions file published in the GitHub repository uhop/console-toolkit (10 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 966 tokens to every session, about $0.0048 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.

Languages Planning Testing ansi box boxes chart charts color

microcharts AGENTS.md

Instructions for ganapativs/microcharts: Single source of truth: CLAUDE.md. All non-negotiables, stack picks, architecture map, catalog rules, quality bar, roadmap position, and session working rules live there — read it in full before any work. CONTRIBUTING.md covers what the project takes (bug fixes and fixes to…

ganapativs/microcharts · 160 tokens

microcharts CLAUDE.md

Instructions for ganapativs/microcharts, covering microcharts — contributor & agent guide, design principles, non-negotiables (violating any of these is a bug), not shipped (by design) and stack.

ganapativs/microcharts · 5,706 tokens

recharts AGENTS.md

Instructions for recharts/recharts: This is Recharts repository. Recharts is a React-based charting library. The goal is to provide a simple, declarative, and composable way to build charts. We value consistency, usability, and performance. Accessibility is important.

recharts/recharts · 310 tokens

console-toolkit AGENTS.md