What is amazing-test-audit?

A read-only review of an existing test suite, looking for tests that provide little value or repeat what the source code already says.

It is for auditing test quality and producing plans for handling weak assertions, duplicated coverage, mock-heavy tests, and unnecessary production seams.

It helps identify tests to delete, repair, combine, or move without changing the code or tests during the review.

amazing-test-audit — Command for Claude Code by btspoony/mstar-harness

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/btspoony/mstar-harness

Made for: Claude Code.

Or install morning-star-harness, the plugin that ships this one along with the rest of its 27 skills, 8 commands, 14 agents, 2 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/btspoony/mstar-harness/amazing-test-audit/github.svg)](https://agentmods.dev/commands/btspoony/mstar-harness/amazing-test-audit)

Your own site

<a href="https://agentmods.dev/commands/btspoony/mstar-harness/amazing-test-audit"><img src="https://agentmods.dev/badge/commands/btspoony/mstar-harness/amazing-test-audit/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/btspoony/mstar-harness/amazing-test-audit"><img src="https://agentmods.dev/badge/commands/btspoony/mstar-harness/amazing-test-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 410 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.

Model	Per session	Once invoked
Fable 5.1	$0.00058	$0.00410
Opus 5.5	$0.00023	$0.00164
Sonnet 5.5	$0.00012	$0.00082
Haiku 4.5	$0.00006	$0.00041

Measured 15d ago against content hash 83135efb676f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

amazing-test-audit 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 15d 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.

commands/amazing-test-audit.md · 25 lines

What it actually says

Test-Suite Audit

A read-only audit of the repository's existing test surface, reported as one prioritized review report under {REVIEW_DIR}. No test or source edits, no state machine, no commits: deletions, assertion repairs, consolidations and seam removals are findings, and a baseline failure is reported as a suspected product bug (bug finding), never silently deleted.

Procedure SSOT → mstar-audit SKILL.md (common core) + references/test-audit.md (test-suite method §1–§9; campaign adds §9's ledger).

Boot

mstar-harness-core
mstar-audit → SKILL.md + references/test-audit.md
mstar-conventions (path symbols) · mstar-host → active host reference (invoke capability)

Execute

Execute mstar-audit § test-suite audit end to end (references/test-audit.md). Input tokens: a scope|subsystem narrows the sweep; quick / deep set the effort level (references/codebase-audit.md effort table); campaign switches to the whole-subsystem campaign; no token means a whole-repo sweep. quick + campaign are mutually exclusive — hard-stop and ask the user to drop one.

PM dispatches @code-reviewer (Task category: audit); lane fan-out stays read-only scout / explore under the Assignment's delegation grant.

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.

15d ago Changed · -11 lines · -47 tokens per session 83135efb676f
19d ago Changed · +1 tokens per session 2e07c85e6585
1mo ago First seen · 36 lines · 104 tokens per session scan A 0b222fd459cb

Subscribe to this mod's changes

amazing-test-audit is a command published in the GitHub repository btspoony/mstar-harness (68 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 410 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-29.

Testing harness-engineering knowledge-management omp-plugin sdd spec-driven subagents

amazing-test-audit next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
amazing-test-auditbtspoony/mstar-harness	Command	68	yesterday	MIT	A	58	Claude Code
analyzewordflowlab/novel-writer	Command	957	1y ago	MIT	A	7	Claude Code
convert-to-test-driven-promptcentminmod/my-claude-code-setup	Command	2.7k	29d ago	MIT	A	0	Claude Code
tddstudioKjm/ai-harness-template	Command	46	22d ago	MIT	A	0	Claude Code
bddstudioKjm/ai-harness-template	Command	46	22d ago	MIT	A	0	Claude Code
sddp-implement-qc-loopattilaszasz/sdd-pilot	Command	97	17d ago	MIT	A	0	GitHub Copilot
test-advanced-injectioncentminmod/my-claude-code-setup	Command	2.7k	29d ago	MIT	C	0	Claude Code