test-audit

test-audit is a skill for Claude Code, Codex from postindustria-tech/agentic-toolkit. It costs 116 tokens per session (1,492 once invoked), scanned A, original, MIT.

A test-review method that traces each test assertion to the document, code rule, or other source that says the result is correct.

In plain words
What is it for?
Use it to review test files, describe what each test checks, find its source of truth, and classify tests whose correctness is uncertain.
Why use it?
It shows which tests are based on a clear authority and which only reflect coverage, past behavior, or assumptions.

Skill for Claude CodeCodex

Part of the dev-practices plugin — 9 skills, 9 agents shipped together

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 skills/postindustria-tech/agentic-toolkit/test-audit
Any agent
npx skills add postindustria-tech/agentic-toolkit --skill test-audit
Clone the repo
git clone --depth 1 https://github.com/postindustria-tech/agentic-toolkit

Made for: Claude Code, Codex.

Or install dev-practices, the plugin that ships this one along with the rest of its 9 skills, 9 agents.

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/postindustria-tech/agentic-toolkit/test-audit.svg)](https://agentmods.dev/skills/postindustria-tech/agentic-toolkit/test-audit)
Your own site
<a href="https://agentmods.dev/skills/postindustria-tech/agentic-toolkit/test-audit"><img src="https://agentmods.dev/badge/skills/postindustria-tech/agentic-toolkit/test-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,492 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 $0.00116 $0.01492
Opus 5 $0.00058 $0.00746
Sonnet 5 $0.00023 $0.00298
Haiku 4.5 $0.00012 $0.00149

Measured 3d ago against content hash 8cf291efae04, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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/dev-practices/skills/test-audit/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Source-of-Truth Audit

Classify every test assertion by its authority level. Tests derived from obligations have a clear source of truth. Tests written for coverage, regression, or transport contract don't -- this skill fills that gap.

Args

/dev-practices-test-audit tests/unit/test_format_resolver.py
/dev-practices-test-audit tests/unit/test_products_transport.py tests/unit/test_dynamic_products.py

One or more test file paths. Each file is audited independently.

The Three Questions

For every test function, answer:

  1. What behavior does this test assert? One sentence: "asserts that X returns Y when Z"

  2. What authoritative source says this is correct? Check sources in priority order (see below). Record the source or "none found."

  3. Classification? Based on the source (or lack thereof), classify the test.

Sources of Truth (Priority Order)

Priority Source Where to check Example
1 Protocol/API spec JSON schemas, Python types in spec libraries "Format resolution returns ValueError when format not found"
2 Architecture patterns Project CLAUDE.md, architecture docs "Transport wrapper returns protocol-specific result, impl returns model"
3 Structural guards test_architecture_*.py -- guards define enforceable contracts "ValidationError in wrapper -> specific error type"
4 Explicit product decision Code comments, PR descriptions, task descriptions, docstrings with rationale "list_available_formats returns [] on error (graceful degradation)"
5 None found No external authority -- test documents current implementation behavior "DB row not found -> returns None"

Classification Labels

Label Meaning Action
SPEC_BACKED Spec or library defines this behavior Keep as-is, add spec permalink
ARCH_BACKED Architecture pattern or structural guard enforces this Keep as-is, add pattern reference
DECISION_BACKED Explicit product decision documented somewhere Keep as-is, add decision reference
CHARACTERIZATION No external source -- locks current behavior Keep, but add comment: # Characterization: locks current behavior, no spec backing
SUSPECT Current behavior may be wrong -- no source AND the logic seems questionable Flag for product decision, file beads issue

Read the full file on GitHub · 181 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. 3d ago First seen · 181 lines · 116 tokens per session scan A 8cf291efae04

Subscribe to this mod's changes

test-audit is a skill published in the GitHub repository postindustria-tech/agentic-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 1,492 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens