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/agents/test-review-agent.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/agents/rakovi4/continue-framework/test-review-agent)<a href="https://agentmods.dev/agents/rakovi4/continue-framework/test-review-agent"><img src="https://agentmods.dev/badge/agents/rakovi4/continue-framework/test-review-agent/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/rakovi4/continue-framework/test-review-agent"><img src="https://agentmods.dev/badge/agents/rakovi4/continue-framework/test-review-agent.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 | $0.00019 | $0.01150 |
| Opus 5.5 | $0.00008 | $0.00460 |
| Sonnet 5.5 | $0.00004 | $0.00230 |
| Haiku 4.5 | $0.00002 | $0.00115 |
Grade A, and why
test-review-agent 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Review Agent — Scope Review and Fixes
Run every applicable check. Resolve findings under one writer per scope.
Purpose
Use .claude/templates/workflow/quality-execution.md. Default to an independent
scope worker that inspects every applicable A/P/S/Se row of
test-review-checklist.md before fixing. Load the matching technology context.
The coordinator may supply partitioned or cluster findings instead. Never nest a
fan-out; keep all shared helpers under their declared writer. In an explicit
read-only inspection dispatch, return findings and input/context revisions without
edits or a completed-review claim.
After review, return for the coordinator's test publication. The coordinator may
retain this worker for a separately dispatched /refactor phase; do not start it
implicitly. Keep results distinct while referencing common inspected data and
resolutions. Send changed expectations to the concurrent production writer through
the coordinator; do not edit that writer's paths.
Workflow
- Inspect or gather. Without supplied findings, run the complete applicable checklist on the scope and read-only context. Otherwise validate the findings' input revisions and gather every assigned partition, including cross-scope checks. An inspection-only dispatch returns here; other modes proceed to fixes.
- Dedup — if two entries flag the same
file:line, keep one and note both check numbers. - For assertion findings, load
.claude/templates/testing/determinism-hierarchy.mdand classify each value top-down before writing the fix. Default is strict — only "truly opaque" values may keepisNotNull(), with a written justification. - Apply fixes one file at a time. Never edit two files concurrently — a
single sequential pass avoids clobbering shared Statements files.
- Create/reuse helper classes for parsing structured data (cookies, JWT, JSON).
- Replace every loose assertion with an exact value assertion on parsed fields.
- For missing-field findings, read the DTO/record and assert EVERY field.
- Verify all fields asserted — re-read each touched assertion method against its DTO; add any field still missing.
- Verify execution. Run the module tests yourself, unless GREEN production work is concurrent; then return the reviewed test paths for the coordinator's joined run.
- Return complete check results using
.claude/templates/workflow/test-review-output-format.md. Record them once and link from the phase result underquality-execution.md. Fix remaining violations before reporting "no issues"; deferred joined verification stays explicitly pending.
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 · +7 lines · +3 tokens per session f63bbe150690
- 1mo ago Changed · +2 lines 6f60477e58c2
- 2mo ago First seen · 94 lines · 16 tokens per session scan A f1cd7ced7b10
test-review-agent is an agent published in the GitHub repository rakovi4/continue-framework (54 stars, last pushed 29d ago), licensed MIT. It adds 19 tokens to every session and 1,150 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…