ds-test

ds-test is a skill for Claude Code, Codex from sungurerdim/dev-skills. It costs 34 tokens per session (6,325 once invoked), scanned A, original, MIT.

A general-purpose testing assistant for writing, updating, running, and fixing unit, integration, and end-to-end tests in any software project.

In plain words
What is it for?
Use it to add tests, improve test coverage, investigate failing tests, repair broken tests, or update tests after a refactor.
Why use it?
It helps avoid tests that merely imitate code without checking useful results, and catches failures after code changes. It also requires command output or file changes as proof that work is complete.

Skill for Claude CodeCodex

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/sungurerdim/dev-skills/ds-test
Any agent
npx skills add sungurerdim/dev-skills --skill ds-test
Clone the repo
git clone --depth 1 https://github.com/sungurerdim/dev-skills

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 ds-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/sungurerdim/dev-skills/ds-test.svg)](https://agentmods.dev/skills/sungurerdim/dev-skills/ds-test)
Your own site
<a href="https://agentmods.dev/skills/sungurerdim/dev-skills/ds-test"><img src="https://agentmods.dev/badge/skills/sungurerdim/dev-skills/ds-test.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 6,325 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 $0.00034 $0.06325
Opus 5 $0.00017 $0.03163
Sonnet 5 $0.00007 $0.01265
Haiku 4.5 $0.00003 $0.00632

Measured yesterday against content hash e48fb749b8ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ds-test 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 yesterday.

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.

ds-test/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ds-test

AI-generated tests often mock everything, assert nothing useful, and break on the first refactor. Skill generates tests that follow project's patterns and verifies they actually pass.

Universal Test Skill — Generate, update, run, and fix tests for any stack.

Completion Evidence — applies to every phase: Report done/OK only with the machine-checkable evidence the gates name — the exact command run and its observed output (or file:line diff). Missing evidence → report INCOMPLETE plus what is missing. Self-assessment is never evidence. (This band repeats at file end by design — both copies are normative.)

Triggers

  • User runs /ds-test
  • User asks to write, add, generate tests, or improve test coverage
  • User asks to run tests and fix failures
  • User asks to add E2E, integration, or unit tests
  • User asks "why is this test failing" or "update tests after refactor"
  • After a refactor or feature change, suggest updating affected tests

Triggers — INVOKE / DON'T INVOKE

INVOKE DON'T INVOKE
"write tests for this function", "improve test coverage" "framework setup decisions for greenfield" (→ ds-init or ds-research)
"generate E2E tests", "update tests after refactor" "audit test discipline at architecture level" (→ ds-review --strategic --scope=testing)
"why is this test failing — fix the test" "fix the code so the test passes" (→ ds-fix or manual)
"add regression test for this bug" "audit functional completeness" (→ ds-review --strategic)
"capture current behavior before I refactor this", "baseline this module" "refactor the module" (→ ds-fix or manual after baseline is green)

Contract

Dimensions: B3

  • Generates tests that follow project's existing test patterns and conventions; preserves existing passing tests — overwrites only with explicit confirmation
  • Always runs generated tests to verify they pass before declaring done
  • Uses project's existing test framework — never introduces a new framework unless none exists; test files go in project's established test directory (auto-detected)
  • Does NOT fix application code to make tests pass — fixes the TEST if test is wrong, or reports app bug if app is wrong
  • Standalone. Uses blueprint profile or ds/audit/findings.md when available; own analysis when absent.
  • Writes ds/audit/findings.md only when a test run confirms an application bug (scope app-bugs) or files a critical-flow-wiring gap (scope testing) — never for test-quality-only observations; verifies ds/audit/ is in .gitignore before the first write, appending the line when absent.
  • State-exempt: generated/updated test files on disk are the progress record; re-running naturally resumes.
  • Full accounting enforced: every finding and planned check ends in an explicit disposition (fixed / skipped + reason / only you can do); summary totals balance.
  • Pre-existing / out-of-scope errors detected during work are NOT skipped — fixed inline or escalated with concrete blocker.

Read the full file on GitHub · 284 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday Changed · -24 lines e48fb749b8ca
  2. 4d ago First seen · 308 lines · 34 tokens per session scan A 029683180c6e

Subscribe to this mod's changes

ds-test is a skill published in the GitHub repository sungurerdim/dev-skills (1 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 6,325 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 2026-08-31.