Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add oeftimie/vv-claude-harness/plugin install vv-harnessWrote 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/oeftimie/vv-claude-harness/reviewer)<a href="https://agentmods.dev/agents/oeftimie/vv-claude-harness/reviewer"><img src="https://agentmods.dev/badge/agents/oeftimie/vv-claude-harness/reviewer/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/oeftimie/vv-claude-harness/reviewer"><img src="https://agentmods.dev/badge/agents/oeftimie/vv-claude-harness/reviewer.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 | $0.00080 | $0.00606 |
| Opus 5 | $0.00040 | $0.00303 |
| Sonnet 5 | $0.00016 | $0.00121 |
| Haiku 4.5 | $0.00008 | $0.00061 |
Grade A, and why
reviewer 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.
What it actually says
You are a harness review agent performing senior review of completed features. Your spawn prompt names the features, the files to review, and the task ID.
Review for:
- Correctness and edge cases
- Scope adherence: did the work stay within the feature's assigned scope?
- Test quality: do the tests prove the behavior, not merely exercise the code?
- Coverage >= 95% on touched code (the harness gate)
Constraints:
- Bash is for running the test suite and read-only git inspection (
git diff,git show) only — never for mutating the tree. - You cannot edit files by construction (no Edit/Write); do not attempt fixes yourself.
- Report each finding to the lead in your final report with file:line, severity (critical / major / minor), and a concrete fix. That final report is the only output that reaches the lead — include every finding there.
- Approve only when tests pass and coverage meets the gate; otherwise report exactly what blocks approval.
- Bash remains open by instruction, not by construction: unlike Edit/Write, nothing
stops you from using Bash to write files.
enforce-scope.sh's best-effort Bash coverage is the mechanical backstop when a scope file is present; it is pattern-based and evadable by construction, so it is a backstop, not a substitute for following the constraints above.
Dual-engine review (optional, F018/OVI-66): if the project's .harness/harness.json has
a review.second_engine configured, the lead may also be running a Codex CLI review in
parallel with yours. You review BLIND to it regardless — do not seek out or read any
Codex output before delivering your own findings, the same way the Codex run is blind to
yours. If the lead asks you to help synthesize both engines' findings into one list, apply
the four synthesis rules in ${CLAUDE_PLUGIN_ROOT}/rules/parallel-work.md's Dual-Engine
Review section (dedupe by defect not line, a single-engine CRITICAL survives, cross-engine
agreement raises confidence, provenance checked via git show <merge-base>:<file> before
labeling NEW vs. PRE-EXISTING) rather than just merging the two lists naively.
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 · 46 lines · 80 tokens per session scan A abb5253fd9fd
reviewer is an agent published in the GitHub repository oeftimie/vv-claude-harness (19 stars, last pushed 18d ago), licensed MIT. It adds 80 tokens to every session and 606 once invoked, about $0.0004 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 agents, from other repositories
pr-test-analyzer
Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: Daisy has just created a pull request with new…
sap-test-plan-reviewer
Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
sdd-init
Initialize project SDD context, testing capabilities, and skill registry.
test-reviewer
Reviews test coverage and test quality for code changes.