test

A command that runs diagnostic checks for a compaction-advisor plugin, which helps manage context when a coding session gets long. It checks installation files, session state, status-line settings, hooks, and recent state content.

In plain words
What is it for?
Use it to inspect the plugin installation, configuration, hook setup, and latest saved session state, then report the results.
Why use it?
It shows which parts of the plugin are working and helps explain why context-management status may or may not appear.

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/vignesh07/compaction-advisor/test
Clone the repo
git clone --depth 1 https://github.com/vignesh07/compaction-advisor
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 208 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00000 $0.00208
Opus 5 $0.00000 $0.00104
Sonnet 5 $0.00000 $0.00042
Haiku 4.5 $0.00000 $0.00021

Measured 2d ago against content hash a9d5961a05aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

test scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Run: `cat ~/.claude/plugins/cache/compaction-advisor/compaction-advisor/*/hooks/hooks.json | head -20`
commands/test.md · 26 lines

What it actually says

Compaction Advisor Diagnostic Test

Run these diagnostic checks and report results:

1. Plugin Installation

Run: ls ~/.claude/plugins/cache/compaction-advisor/compaction-advisor/

2. Session State Files

Run: ls -la ~/.claude/context_state_*.json

If no files found, the status line hasn't written state yet.

3. Status Line Config

Run: jq '.statusLine' ~/.claude/settings.json

4. Plugin Hook Config

Run: cat ~/.claude/plugins/cache/compaction-advisor/compaction-advisor/*/hooks/hooks.json | head -20

Note: For plugin installs, hooks load from the plugin's hooks.json (not user's settings.json).

5. Latest State File Content

Run: cat ~/.claude/context_state_*.json | head -20

Summary

Report what's working. Note: If status is "safe", the hook correctly outputs nothing (0 tokens).

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. 2d ago First seen · 26 lines · 0 tokens per session scan B a9d5961a05aa

Subscribe to this mod's changes

test is a command published in the GitHub repository vignesh07/compaction-advisor (17 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 208 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.