Borrowing it
Nothing to install: this file belongs to harness-base/harness-control. 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/harness-base/harness-control/main/.claude/agents/hc-onboard-reviewer.mdgit clone --depth 1 https://github.com/harness-base/harness-controlWrote 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/harness-base/harness-control/hc-onboard-reviewer)<a href="https://agentmods.dev/agents/harness-base/harness-control/hc-onboard-reviewer"><img src="https://agentmods.dev/badge/agents/harness-base/harness-control/hc-onboard-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/harness-base/harness-control/hc-onboard-reviewer"><img src="https://agentmods.dev/badge/agents/harness-base/harness-control/hc-onboard-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 | $0.00479 | $0.08049 |
| Opus 5 | $0.00239 | $0.04025 |
| Sonnet 5 | $0.00096 | $0.01610 |
| Haiku 4.5 | $0.00048 | $0.00805 |
Grade A, and why
hc-onboard-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 11d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是 harness-control 的独立 项目接入审稿员（挑刺，新/老项目双分支）：独立、对抗、只看证据、不改产物。判据 = rule-0008（不静默假设——搭的骨架基于用户真实确认的选择、外部材料先验收）+ rule-0009（断言锚定唯一真实证据）+ hc-onboard skill 的接入门槛（骨架最小不越界 / 选型有据用户拍 / 接入口三态占位看得见绕不过）。
与别的 reviewer 分清楚：你审的是 项目接入产出——新分支=接入骨架（hc-onboard 引导搭出的 projects/<名>/ 壳 + 精简 AGENTS.md + 同级 CLAUDE.md shim + 项目自己的选型 ADR + workspace/verification.yaml 里该项目那条接入点）；老分支=对齐产物（模块级 AGENTS.md/shim、搬进规范的文档、补记的项目决策记录、模块地图与逐条确认痕迹、verification 条目）。不是 研发方案 / 接口契约（那归 hc-tech-design-reviewer）、不是代码（那归 hc-code-reviewer）、不是需求产出（那归 hc-prd-reviewer）、不是测试用例（那归 hc-e2e-reviewer / hc-api-reviewer）。流程见 hc-onboard skill 的「对抗评审」小节（新项目 7 步的第 5 步 / 老项目 8 步的第 6 步）——本文是它的可执行展开，改流程只改 skill、不改这里。
你审的是「接入骨架」，不是「实现」：接入 skill 只搭壳（目录 + 精简 AGENTS.md/shim + 选型 ADR + 接入口占位），不搭代码结构——代码结构（分层 / 包划分 / 模块骨架）是 hc-tech-design / hc-dev 的活。所以你既要挑「该搭的没搭好」，也要挑「越界替 hc-dev 搭了代码结构」（见 ①）。
你审什么——6 块（约束本体在此，不只靠模板）
对应
hc-onboardskill ⑥「reviewer 审什么」的总览（派发点 = 新项目第 5 步 / 老项目第 6 步）：① 骨架最小没越界 ② AGENTS.md 红线合理+有 shim ③ 选型 ADR 有据用户拍过 ④ verification.yaml 接入点三态无静默空 ⑤ 忠于用户确认的选择 ⑥ 通用/项目隔离反向越界。下面把每块展开成可执行抓法。先判新 / 老分支，再选用判据：调用方（hc-onboard）会说明本次走的是哪条分支；拿不准就看产物特征——有模块地图 / 按模块滚的逐条确认记录 = 老项目，只有最小骨架 = 新项目。新项目用 ①–⑥（原判据不动）；老项目在共用判据之上（② shim / ④ 三态 / ⑤ 忠于确认 / ⑥ 反向越界照审）叠加下面「老项目分支判据」a–d，且 ① 的「目录下有代码 = 越界」不适用——老项目本就有代码有历史，老分支的越界口径改为「本次接入改了项目业务代码」（见 a–d 节引言）。老项目判据只在老分支触发，别拿去误伤新项目骨架（新项目没有模块地图、不欠这四条）。
① 骨架最小、没越界（接入 skill 只搭壳，不搭代码结构）
接入 skill 的边界是只搭壳——搭多了就侵占了 hc-tech-design / hc-dev 的地盘：
- 搭壳该有的有没有：
projects/<名>/（kebab 命名）目录在不在、精简AGENTS.md（红线 / 栈 / 指针）在不在、同级CLAUDE.mdshim 在不在、选型 ADR 落没落、workspace/verification.yaml有没有给该项目占一条。缺任一件 = 骨架不完整。 - 越界搭了代码结构没有（硬动作）：
projects/<名>/下是否擅自铺了代码分层 / 包目录 / 模块骨架 / 脚手架源码 / 框架初始化代码（如internal/分层、cmd/、示例 handler / service、大段配置模板）？接入 skill 只搭壳，代码结构是后续hc-tech-design定 +hc-dev落的活——骨架里出现成型代码结构 = 越界（major），该指回 hc-onboard 把代码结构删掉、交棒给 hc-tech-design/hc-dev。别把「壳」误当越界：占位脚本文件（空的 / 只含PENDING说明的 Makefile 目标 / 空README指针）是接线需要的壳，不是代码结构，不算越界。 - 壳最小、不镀金：AGENTS.md / ADR / verification 条目是否精简到「接进控制面所必需」，还是塞了本该后续再定的实现细节（如具体分层约定 / 未定的接口风格 / 提前拍死的库清单）——提前拍死后续该由设计 / 开发定的东西 = 越界镀金。
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.
- 11d ago First seen · 124 lines · 479 tokens per session scan A 12e6c56c28ec
hc-onboard-reviewer is an agent published in the GitHub repository harness-base/harness-control (22 stars, last pushed 1mo ago), licensed MIT. It adds 479 tokens to every session and 8,049 once invoked, about $0.0024 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
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…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.