unit-tests-eval-sdd

unit-tests-eval-sdd is a skill for Claude Code, Codex from Plazmodium/odin-workflow. It costs 34 tokens per session (552 once invoked), scanned A, original, MIT.

A review protocol for judging whether newly added or changed unit tests are trustworthy. Unit tests check small pieces of code in isolation, while this protocol also checks how well those tests prove behavior.

In plain words
What is it for?
Use it when reviewing test changes to verify the right files are tested, tests pass, checks are run, and the test structure and data are sound.
Why use it?
It prevents weak tests, vague assertions, unsafe mocks, missing edge cases, and changes that pass without providing meaningful coverage.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when reviewing test changes to verify the right files are…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/plazmodium/odin-workflow/unit-tests-eval-sdd
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.

Any agent
npx skills add Plazmodium/odin-workflow --skill unit-tests-eval-sdd
Clone the repo
git clone --depth 1 https://github.com/Plazmodium/odin-workflow

Made for: Claude Code, Codex.

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 unit-tests-eval-sdd

README.md
[![agentmods](https://agentmods.dev/badge/skills/plazmodium/odin-workflow/unit-tests-eval-sdd.svg)](https://agentmods.dev/skills/plazmodium/odin-workflow/unit-tests-eval-sdd)
Your own site
<a href="https://agentmods.dev/skills/plazmodium/odin-workflow/unit-tests-eval-sdd"><img src="https://agentmods.dev/badge/skills/plazmodium/odin-workflow/unit-tests-eval-sdd.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 552 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 $0.00034 $0.00552
Opus 5 $0.00017 $0.00276
Sonnet 5 $0.00007 $0.00110
Haiku 4.5 $0.00003 $0.00055

Measured 6d ago against content hash 5dec4156d8d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

unit-tests-eval-sdd 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.

agents/skills/testing/unit-tests-eval-sdd/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unit Test Evaluation Protocol

Use this skill during Reviewer when the feature includes new or changed tests.

Reviewer Goal

Do not only ask whether tests exist. Judge whether the tests are strong enough to trust the implementation.

Required Review Flow

  1. Verify test files exist for changed production code.
  2. Verify tests pass with the repo-native test command.
  3. Verify lint/type expectations relevant to tests still pass.
  4. Inspect the changed source and the corresponding tests.
  5. Evaluate test quality across these dimensions:
    • coverage quality
    • assertion specificity
    • Arrange / Act / Assert structure
    • mock hygiene
    • naming quality
    • async correctness
    • fixture/data quality
  6. Decide whether the test suite is acceptable, acceptable with recommendations, or needs Builder rework.

Automatic Rework Triggers

Send the feature back to Builder when any of these are true:

  • changed production code has no meaningful unit tests
  • tests are failing
  • coverage is below the project hard gate
  • assertions are mostly vague or vacuous
  • tests rely on implementation details instead of behavior
  • mocks bleed between tests or mock the unit under test
  • async behavior is unawaited, flaky, or only partially covered

Reviewer Output Expectations

  • Cite concrete evidence: file paths, line numbers, and command output.
  • Separate blocking issues from non-blocking recommendations.
  • If test quality is insufficient, record needs_rework and send the workflow back to Builder.
  • If tests are acceptable, still capture recommendations for the next iteration.

Minimal Scoring Rubric

  • PASS: tests are trustworthy and compliant
  • PASS_WITH_RECOMMENDATIONS: acceptable now, but improvements are still warranted
  • NEEDS_REWORK: Builder must fix tests before integration
  • ESCALATE: test evidence reveals a deeper production bug or ambiguous requirement

Reviewer Checklist

  • Test files present for changed code
  • Tests pass
  • Coverage meets hard gate
  • Assertions are specific
  • Mock cleanup is correct
  • Async paths are handled correctly
  • Result is either approved or routed back to Builder with precise feedback

Read the full file on GitHub · 74 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. 6d ago First seen · 74 lines · 34 tokens per session scan A 5dec4156d8d2

Subscribe to this mod's changes

unit-tests-eval-sdd is a skill published in the GitHub repository Plazmodium/odin-workflow (0 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 552 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 2026-09-01.

Related

Other skills, from other repositories

api-testing

Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.

cyanheads/pubmed-mcp-server · 46 tokens

api-testing

Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.

cyanheads/sports-mcp-server · 46 tokens

api-testing

Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.

cyanheads/internet-archive-mcp-server · 46 tokens

api-testing

Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.

cyanheads/smithsonian-mcp-server · 46 tokens

api-testing

Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.

cyanheads/stackexchange-mcp-server · 46 tokens

add-test

Scaffold a test file for an existing tool, resource, or service. Use when the user asks to add tests, improve coverage, or when a definition exists without a matching test file.

cyanheads/stackexchange-mcp-server · 41 tokens