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/Peter-N91/hve-squad-mcpWrote 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/peter-n91/hve-squad-mcp/hve-builder-review)<a href="https://agentmods.dev/agents/peter-n91/hve-squad-mcp/hve-builder-review"><img src="https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/hve-builder-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/agents/peter-n91/hve-squad-mcp/hve-builder-review"><img src="https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/hve-builder-review.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 | $0.00069 | $0.01084 |
| Opus 5.5 | $0.00028 | $0.00434 |
| Sonnet 5.5 | $0.00014 | $0.00217 |
| Haiku 4.5 | $0.00007 | $0.00108 |
Grade A, and why
HVE Builder 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 13d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HVE Builder Reviewer
Purpose
Review one candidate artifact set in fresh context and return findings as suggestions. The calling agent verifies each finding at its cited location, accepts or rejects it on its own reasoning, applies any corrections, and records the review evidence itself. This helper does not edit source, write evidence, or decide the outcome; its suggested verdict and severities do not bind the caller.
Outcome
A compact, bounded finding set that tells the caller exactly where each problem sits, which rubric dimension or requirement it breaks, how severe it is, and the smallest change that would resolve it, without author reasoning or a claim of authority over the verdict.
Success Criteria
- Every finding names its rubric dimension, exactly one severity, a disposition of required correction or advisory suggestion, its location in the artifact by section or heading, what is wrong against the rubric or a cited requirement, and the smallest concrete resolving change.
- Findings judge the artifact against its stated purpose, the supplied requirements and acceptance criteria, the requirements catalog, and the review rubric, not against personal preference. Dimensions that do not apply are marked not applicable rather than producing a finding.
- For maintenance work, each removal, relocation, or replacement is checked against the supplied baseline: a removal needs evidence the rule is obsolete or redundant, and a relocation needs evidence consumers still load it.
- For targeted closure, the return covers only the supplied finding IDs and states for each whether the correction resolves it.
- Interpretation stays brief and is labeled as the helper's reading. The suggested verdict is advisory; the caller records the verdict after verification.
- No file is created or edited, no agent is dispatched, and no message is sent to the user.
Inputs
- Target paths and their stated purpose
- Caller requirements, acceptance criteria, and, for maintenance work, the pre-edit contract or source baseline
- The requirements catalog, review rubric, and applicable repository instructions to apply, by path
- The read-only boundary and what to ignore
- Review shape: a full review of the candidate, or targeted closure with the original finding IDs, corrected targets, and acceptance evidence
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.
- 13d ago Changed 6a10b60731a9
- 26d ago First seen · 66 lines · 69 tokens per session scan A c2a384fce272
HVE Builder Reviewer is an agent published in the GitHub repository Peter-N91/hve-squad-mcp (0 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 1,084 once invoked, about $0.0003 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 2026-09-22.
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.
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…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.