Borrowing it
Nothing to install: this file belongs to rakovi4/continue-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rakovi4/continue-framework/main/.claude/skills/test-review/SKILL.mdgit clone --depth 1 https://github.com/rakovi4/continue-frameworkWrote 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/rakovi4/continue-framework/test-review)<a href="https://agentmods.dev/skills/rakovi4/continue-framework/test-review"><img src="https://agentmods.dev/badge/skills/rakovi4/continue-framework/test-review/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/rakovi4/continue-framework/test-review"><img src="https://agentmods.dev/badge/skills/rakovi4/continue-framework/test-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00699 |
| Opus 5.5 | $0.00011 | $0.00280 |
| Sonnet 5.5 | $0.00006 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
test-review 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/test-review - Improve Test Assertions
Usage
/test-review— review all tests/test-review {TestTarget}— review one test target
Available Templates
| Template | Purpose |
|---|---|
.claude/templates/testing/test-review-patterns.md |
Universal rules, anti-pattern catalog, assertion rules |
.claude/tech/{backend}/templates/testing/test-review-usecase.md |
Usecase test patterns (Statements purity, 3-tier DSL) |
.claude/tech/{backend}/templates/testing/test-review-rest.md |
REST controller test patterns (mock matching) |
.claude/tech/{backend}/templates/testing/test-review-storage.md |
Persistence test patterns |
.claude/tech/{backend}/templates/testing/test-review-acceptance.md |
Acceptance test patterns (HTTP response assertions) |
.claude/tech/{backend}/templates/testing/test-review-other.md |
Selenium, email, scheduling, security patterns |
Workflow
Load .claude/templates/workflow/quality-execution.md for scope ownership,
parallel scheduling, retained workers, and compact phase evidence.
- Resolve the test scope and layer (usecase / rest / storage / acceptance /
selenium), including helpers and relevant collaborators. Load the matching
technology template and
.claude/templates/workflow/test-review-checklist.md. - Dispatch one independent
test-review-agentper coherent scope. The worker must be independent of the test author, run all applicable A, P, S, and Se checks, then apply fixes under.claude/agents/test-review-agent.mdfor an unpartitioned scope. Se applies to selenium/frontend tests only. A small scope uses this same route. - For large scopes, partition by cohesive capability with all applicable checks per partition and a named cross-capability owner. Shared helpers have one write owner. Dispatch partitions read-only initially; gather every partition and cross-capability result before granting fixes. Workers must not nest fan-outs.
- The worker runs the affected tests unless Stage 2 production work is concurrent;
then it returns reviewed test paths and the coordinator owns joined execution.
Review findings that affect required production behavior go to that writer.
Return a distinct
/test-reviewresult. The coordinator may publish reviewed tests and dispatch RED refactoring while joined verification remains owed; keep the review gate pending until that verification completes. - Retain the quality worker for RED
/refactorwhen available, preserving its context. It must stop after the review result. Only the coordinator's explicit/refactordispatch after publication of reviewed tests starts that phase; skill invocations, evidence, and commits remain distinct.
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 · +4 lines f8476f0e2d0c
- 1mo ago Changed · +1 lines · -18 tokens per session 74f30214330a
- 2mo ago First seen · 54 lines · 46 tokens per session scan A 89717c67061b
test-review is a skill published in the GitHub repository rakovi4/continue-framework (54 stars, last pushed 29d ago), licensed MIT. It adds 28 tokens to every session and 699 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 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.