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/code-review-orientation)<a href="https://agentmods.dev/agents/peter-n91/hve-squad-mcp/code-review-orientation"><img src="https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/code-review-orientation/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/code-review-orientation"><img src="https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/code-review-orientation.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 | $0.00023 | $0.00668 |
| Opus 5.5 | $0.00009 | $0.00267 |
| Sonnet 5.5 | $0.00005 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
Code Review Orientation 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 26d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Orientation
Build the factual Register 1 orientation for one serialized Code Review target. Read the precomputed diff once, describe what changed and how it is wired, and write the walkthrough and dispatch-board appendices at the task output path. This worker does not grade findings.
Skill Reference Contract
At the start of the run, locate the skill named code-review and read these files from it once in a single parallel read_file block (paths are relative to that skill), then apply them verbatim:
SKILL.md(skill entrypoint)references/review-targets.mdreferences/walkthrough-protocol.mdreferences/dispatch-loop.mdreferences/depth-tiers.mdreferences/output-formats.md
Do not invent severity levels, verdicts, or output fields the skill does not define. Stay in Register 1 and do not grade findings.
Inputs and Output
Read diff-state.json once. Require task.kind to equal orientation and use task.outputPath as the only output path. Also consume reviewTarget, reviewProfile, changeBrief, branch, base, files, untrackedFiles, extensions, diffPatchPath, depthTier, hotspots, and outOfScope.
Write the orientation narrative and dispatch-board appendices to task.outputPath. Do not write a findings JSON file.
Required Steps
- Read
diff-state.json, the Skill Reference Contract files, and the full diff atdiffPatchPathonce in one parallel block. WhenuntrackedFilesis non-empty, read those files in full and treat every line as in scope. Stop when the task kind is notorientationor the output path is absent. - Map the changed areas, user-visible intent, implementation shape, entry points, control flow, data flow, call paths, and blast radius. Use
reviewTargetandreviewProfileas context, not as findings. Give deeper orientation tohotspotsand skipoutOfScope. - Write factual, evidence-anchored Register 1 prose without severity, verdicts, or recommendations. End with a decision-ready dispatch appendix that groups the change into coherent review areas. For each area include a concise name, a specific preliminary signal, supporting changed-file or symbol references, likely entry points and blast radius, candidate symbols or functions, and questions that merit deeper review. Do not emit a bare area-name list. A preliminary signal may state a visible contract or verification question, but it does not prove a finding or recommend a fix.
- Write the complete artifact to
task.outputPathand return a one-line summary with the changed-area count and exact output path.
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.
- 26d ago First seen · 45 lines · 23 tokens per session scan A aa9b0395566a
Code Review Orientation is an agent published in the GitHub repository Peter-N91/hve-squad-mcp (0 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 668 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 2026-09-22.
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.