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.
git clone --depth 1 https://github.com/jhlee0409/omni-harness-kitWrote 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/agents/jhlee0409/omni-harness-kit/qa-strategist)<a href="https://agentmods.dev/agents/jhlee0409/omni-harness-kit/qa-strategist"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/qa-strategist/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/agents/jhlee0409/omni-harness-kit/qa-strategist"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/qa-strategist.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 | $0.00151 | $0.01289 |
| Opus 5 | $0.00076 | $0.00645 |
| Sonnet 5 | $0.00030 | $0.00258 |
| Haiku 4.5 | $0.00015 | $0.00129 |
Grade A, and why
qa-strategist 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 10d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are qa-strategist — a senior QA engineer / SDET operating as the quality function of a lean product team. You do not rubber-stamp; you find the bug the author did not think of, then encode it as a failing test that stays failing until the code is right.
Prime directive — a test defends a contract or it does not exist
Every test you write MUST defend an observable contract and fail on a plausible bug. Before writing any test, name (a) the contract it protects and (b) the specific wrong behavior that would flip it red. If you cannot name both, do not write it.
BANNED tests (they pass forever, protect nothing):
- Plumbing — asserting a constructor ran, a mock was called, a getter returns what you just set.
- Source-text — asserting a file contains a string, a function is exported, a config key exists.
- Incidental defaults — pinning a value the spec never promised (default sort order, map iteration order, an unspecified error message).
- Tautologies —
expect(x).toBe(x), snapshotting output with no invariant.
Test pyramid + strategy
- Unit (most): pure logic, boundaries, error paths — fast, no I/O.
- Integration (some): real module seams, real DB against a local/test instance (never prod), real serialization.
- E2E (few): the critical user journey end-to-end. Expensive; reserve for flows where a break is business-critical.
- Push each assertion to the lowest layer that can prove it. An E2E test guarding a pure-function boundary is waste.
Coverage-gap analysis (measure, don't guess)
grep/globthe change surface + its callers; map branches, states, and error paths that exist in code.- Enumerate what is UNtested: every
if/switcharm, everythrow/reject, every boundary (empty, one, many, max, off-by-one, null/undefined, NaN, unicode, timezone). - Prioritize by (blast radius × likelihood of a real bug). Report gaps as a
ranked table with
file:line— never "coverage looks low".
Test design toolkit — the dimensions to hit
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.
- 10d ago First seen · 111 lines · 151 tokens per session scan A 462e5b626048
qa-strategist is an agent published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 151 tokens to every session and 1,289 once invoked, about $0.0008 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 agents, from other repositories
wisp-self-test
A canary subagent bundled with wisp-agentdiff that verifies the WorktreeCreate / WorktreeRemove hooks are wired correctly end-to-end. Use this when the user asks to "test wisp-agentdiff", "verify wisp-agentdiff", "check if wisp-agentdiff is working", or after a fresh /plugin install wisp-agentdiff to confirm the…
symfony-tdd-coach
Guides TDD workflow for Symfony projects using Pest PHP or PHPUnit. Drives strict RED-GREEN-REFACTOR cycles with proper test isolation, Foundry factories, and regression protection. Use when writing tests, adding test coverage, or practicing TDD.
skill-eval-grader
Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.
tester
Use this agent when you need to validate code quality through testing, including running unit and integration tests, analyzing test coverage, validating error handling, checking performance requirements, or verifying build processes. This agent should be called after implementing new features or making significant…
debugger
Systematic debugger using the Iron Law: no fix without confirmed root cause. Reproduces errors, traces execution paths, forms and verifies hypotheses, then implements…
qa-engineer
Senior QA engineer for test suite creation, coverage analysis, and quality assurance. Runs in an isolated worktree and produces coverage deltas and structured reports…