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/whitequeen306/code-cortex-loop/test-strategynpx skills add whitequeen306/code-cortex-loop --skill test-strategygit clone --depth 1 https://github.com/whitequeen306/code-cortex-loopWhat 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 | $0.00039 | $0.01316 |
| Opus 5 | $0.00019 | $0.00658 |
| Sonnet 5 | $0.00008 | $0.00263 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade A, and why
test-strategy 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 2d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Strategy (Deep)
Depth skill for pass 3 (tests). Pair with cortexloop-expert-core and edge-case-and-state-analysis.
Go deep on verification. Name missing behaviors, design better tests, spot weak assertions and flaky patterns. Production logic bugs → defer review; exploit paths → defer security.
Goal
Not maximum coverage percentage — confidence that important behavior will not silently regress. Every finding should name a concrete test someone could write tomorrow.
Depth checklist — what to examine
Behavior & contracts
- Public API contracts (inputs, outputs, errors, side effects)
- CLI flags, HTTP status codes, event payloads, schema evolution
- Idempotency and retry semantics as tested (not just implemented)
- Feature flags / config branches with no test matrix
Test level fit
| Level | Use when | Red flags |
|---|---|---|
| Unit | Pure logic, single module | Mocking entire world; testing implementation details |
| Integration | DB, FS, queue, HTTP client with real or test double | None — gap if boundary untested |
| E2E | Critical user journeys | One E2E replacing 20 unit tests for pure logic |
Find wrong level: brittle E2E for math; unit test that mocks the thing you're trying to verify.
Boundary & edge coverage
- empty, zero, max, null, malformed, unicode, oversized payload
- first item / last item / single item / duplicate items
- clock skew, timeout, slow dependency (where tests exist)
- permission denied vs resource missing (as test scenarios, not auth audit)
Error & failure paths
- network/DB timeout, 500 from dependency, partial write
- validation failure, conflict, rate limit
- cleanup after failure (teardown, rollback) — tested?
Error handling quality (swallowed errors) → defer
errorHandling. Frame here as "no test proves recovery/failure surface."
Regression & change sensitivity
- Code changed in this PR without adjacent test update?
- Previously fixed bug class without regression test?
- Copy-pasted logic with tests only on one copy?
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.
- 2d ago First seen · 146 lines · 39 tokens per session scan A e0a72ae93cc8
test-strategy is a skill published in the GitHub repository whitequeen306/code-cortex-loop (15 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,316 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…