test-bar

test-bar is a command for coding agents from axiomantic/spellbook. It costs 34 tokens per session (2,975 once invoked), scanned A, original, MIT.

A temporary React overlay that adds buttons for viewing different UI states on the current code branch. It changes client-side values such as feature flags, permissions, and API results, then opens the relevant page.

In plain words
What is it for?
It helps with visual quality checks for UI changes, especially screens that depend on different data or settings.
Why use it?
It lets developers check conditional screens without manually preparing data or navigating through each state. The changes are development-only and designed to be removed afterward.

Command

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 commands/axiomantic/spellbook/test-bar
Clone the repo
git clone --depth 1 https://github.com/axiomantic/spellbook

Wrote 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.

agentmods badge for test-bar

README.md
[![agentmods](https://agentmods.dev/badge/commands/axiomantic/spellbook/test-bar.svg)](https://agentmods.dev/commands/axiomantic/spellbook/test-bar)
Your own site
<a href="https://agentmods.dev/commands/axiomantic/spellbook/test-bar"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/test-bar.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,975 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00034 $0.02975
Opus 5 $0.00017 $0.01488
Sonnet 5 $0.00007 $0.00595
Haiku 4.5 $0.00003 $0.00298

Measured yesterday against content hash 99d00a4fe9c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-bar 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 yesterday.

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.

commands/test-bar.md · 305 lines

How it starts

The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MISSION

Analyze the current branch's code changes against its merge base, identify every conditional rendering path and its data triggers, then generate a self-contained floating React overlay component with one-click scenario buttons. Each button transforms client-side state (store, entitlements, feature flags, API responses) and navigates to the correct page so the developer can visually QA each scenario without manual data setup.

Invariant Principles

  1. Throwaway code - Everything you create will be reverted via /test-bar-remove. Optimize for "works correctly" over "production quality." But it MUST work.
  2. No test file changes - Only modify source/component files. Never touch __tests__/, *.test.*, or *.spec.* files.
  3. Track all changes - Write a manifest so /test-bar-remove can cleanly revert. No untracked modifications.
  4. Dev-only guard - Wrap ALL injected code in __DEV__ or process.env.NODE_ENV !== 'production' checks.
  5. Minimal footprint - Inject at the highest possible level. One overlay component, one injection point. Scattered changes are forbidden.
  6. Reversible state - Every scenario button must be reversible. Capture original state before overriding. "Reset" restores it.

Phase 1: Branch Analysis

Step 1: Determine merge base and changed files

TARGET=$(git rev-parse --abbrev-ref HEAD@{upstream} 2>/dev/null | sed 's|origin/||' || echo "master")
MERGE_BASE=$(git merge-base HEAD "origin/$TARGET" 2>/dev/null || git merge-base HEAD origin/master 2>/dev/null || git merge-base HEAD origin/main)

# Detect source directory
if [ -d "src" ]; then SRC_DIR="src"
elif [ -d "app" ]; then SRC_DIR="app"
elif [ -d "lib" ]; then SRC_DIR="lib"
else echo "ERROR: No src/, app/, or lib/ directory found. Identify the source directory manually."; exit 1
fi

# Changed source files (exclude tests, configs, assets)
git diff "$MERGE_BASE"...HEAD --name-only --diff-filter=ACMR \
  | grep -E '\.(tsx?|jsx?)$' \
  | grep -v -E '(__tests__|\.test\.|\.spec\.|\.stories\.|\.mock\.)' \
  | sort

Read the full file on GitHub · 305 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. yesterday First seen · 305 lines · 34 tokens per session scan A 99d00a4fe9c2

Subscribe to this mod's changes

test-bar is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 2,975 once invoked, about $0.0002 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 2026-09-03.