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.
npx skills add sungurerdim/dev-skills --skill ds-testgit clone --depth 1 https://github.com/sungurerdim/dev-skillsWrote 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.
[](https://agentmods.dev/skills/sungurerdim/dev-skills/ds-test)<a href="https://agentmods.dev/skills/sungurerdim/dev-skills/ds-test"><img src="https://agentmods.dev/badge/skills/sungurerdim/dev-skills/ds-test/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00034 | $0.06325 |
| Opus 5.5 | $0.00014 | $0.02530 |
| Sonnet 5.5 | $0.00007 | $0.01265 |
| Haiku 4.5 | $0.00003 | $0.00632 |
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 1mo 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.
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/OKonly with the machine-checkable evidence the gates name — the exact command run and its observed output (orfile:linediff). Missing evidence → reportINCOMPLETEplus 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.mdwhen available; own analysis when absent. - Writes
ds/audit/findings.mdonly when a test run confirms an application bug (scopeapp-bugs) or files a critical-flow-wiring gap (scopetesting) — never for test-quality-only observations; verifiesds/audit/is in.gitignorebefore 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.
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.
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.
- 1mo ago Changed · -24 lines e48fb749b8ca
- 1mo ago First seen · 308 lines · 34 tokens per session scan A 029683180c6e
ds-test is a skill published in the GitHub repository sungurerdim/dev-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 6,325 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
testloop
Implementation-test-fix feedback loop.
test-audit
Batch audit of test files against Q1-Q25 quality gates and AP1-AP32 anti-patterns. Detects orphan tests, phantom mocks, untested public methods. Tiered output (A/B/C/D) with critical gate enforcement and optional post-audit fix workflow. Flags: zuvo:test-audit all | [path] | [file] | --deep | --quick | --include-e2e |…
execution/testing-executor
Internal: Testing Executor. Writes unit, integration, and e2e tests. Read spec and segment. Write evidence on completion.
test-plan-writing
Write risk-based test plans with coverage matrices, test level decisions, pass/fail criteria, and environment requirements — deciding what to test, at which level, and why.
memstack-development-test-writer
Use this skill when the user says 'write tests', 'add tests', 'test coverage', 'unit tests', 'integration tests', 'component tests', 'mocking', 'edge cases', or needs to generate tests with proper mocking and edge case coverage. Do NOT use for refactoring plans or database migrations.
testing-patterns
Testing strategy: pyramid, AAA, mocks/fakes/stubs, flaky tests, coverage. Triggers: test, fixture, mock, stub, e2e, TDD, Playwright, Cypress, flaky, coverage, property-based.