justify

justify is a command for Claude Code from athola/claude-night-market. It costs 30 tokens per session (324 once invoked), scanned A, original, MIT.

A post-implementation audit that examines code changes for unnecessary additions, altered test logic, and interventions beyond the simplest safe change.

In plain words
What is it for?
Use it after implementation, before committing or opening a pull request, on a branch, staged changes, or selected files.
Why use it?
It helps identify scope creep, weakened tests, and complexity that was not needed for the requested work.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the imbue plugin — 5 commands, 1 agent shipped together

Good fit Use it after implementation, before committing or opening a pull request, on a branch, staged changes, or selected files.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/athola/claude-night-market/justify
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.

Clone the repo
git clone --depth 1 https://github.com/athola/claude-night-market

Made for: Claude Code.

Or install imbue, the plugin that ships this one along with the rest of its 5 commands, 1 agent.

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 justify

README.md
[![agentmods](https://agentmods.dev/badge/commands/athola/claude-night-market/justify/github.svg)](https://agentmods.dev/commands/athola/claude-night-market/justify)
Your own site
<a href="https://agentmods.dev/commands/athola/claude-night-market/justify"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/justify/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for justify

Your own site · 80×15
<a href="https://agentmods.dev/commands/athola/claude-night-market/justify"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/justify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 324 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00030 $0.00324
Opus 5 $0.00015 $0.00162
Sonnet 5 $0.00006 $0.00065
Haiku 4.5 $0.00003 $0.00032

Measured 6d ago against content hash 75b31b8deba2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

justify 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 6d 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.

plugins/imbue/commands/justify.md · 54 lines

What it actually says

Justify Changes

Post-implementation audit that forces honest accounting of every change. Detects AI additive bias, test-logic tampering, and unnecessary complexity.

Usage

# Justify all changes on the current branch
/justify

# Justify only staged changes
/justify --scope staged

# Justify specific files
/justify src/auth.py tests/test_auth.py

What It Does

  1. Loads the justify methodology: Skill(imbue:justify)
  2. Gathers the change delta (git diff from base branch)
  3. Computes an additive bias score
  4. Checks Iron Law compliance (test logic tampering)
  5. Runs minimal intervention analysis per file
  6. Generates a justification report with risk assessment

When to Use

  • After completing implementation, before committing
  • Before creating a PR
  • When scope-guard flags RED or YELLOW zone
  • After any session where significant code was added

Arguments

Argument Description
--scope staged Only audit staged changes
--scope branch Audit all branch changes (default)
--scope file Audit specific files listed after
path... Specific file paths to audit
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. 6d ago First seen · 54 lines · 30 tokens per session scan A 75b31b8deba2

Subscribe to this mod's changes

justify is a command published in the GitHub repository athola/claude-night-market (337 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 324 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.