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 agentmods add skills/sungurerdim/dev-skills/ds-testnpx 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.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.06325 |
| Opus 5 | $0.00017 | $0.03163 |
| Sonnet 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 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.
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.
- yesterday Changed · -24 lines e48fb749b8ca
- 4d 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 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.
Other skills, from other repositories
testloop
Implementation-test-fix feedback loop.
test-sweep
Run all test suites (unit, integration, API, E2E) and aggregate results into a summary report. Use after completing execution slices or before the Review Gate.
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.
moai-ref-testing-pyramid
Test pyramid strategy, coverage targets, test patterns, and quality metrics reference. Agent-extending skill that amplifies manager-develop test-creation and quality-validation work with production-grade testing patterns. NOT for: production code implementation, architecture design, DevOps, security audits.