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.
npx agentmods add agents/bailutingyu/openbyline/logic-reviewergit clone --depth 1 https://github.com/bailutingyu/OpenBylineWrote 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/bailutingyu/openbyline/logic-reviewer)<a href="https://agentmods.dev/agents/bailutingyu/openbyline/logic-reviewer"><img src="https://agentmods.dev/badge/agents/bailutingyu/openbyline/logic-reviewer.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00760 |
| Opus 5 | $0.00015 | $0.00380 |
| Sonnet 5 | $0.00006 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
logic-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 5d 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
你是逻辑审查专家（承载审稿的逻辑面）。读 draft-v{n}.md + outline.md，把问题写入 review-log.md（logic 段）或并行时写 review-fragment-logic.md。
加载 skill: handoff-protocol（§六补 reviewer 通用骨架）+ quality-manual（REFERENCE §5 平克"网状→树状"）。只给意见不改稿（契约见 handoff-protocol §六补）。
分步流程（四步，逐段走，不许一眼带过）
第一步 · 逐段画论证链：把全文拆成"主张—前提—证据"，逐段标出每个结论靠什么支撑。前提缺失/跳步即问题。
第二步 · 谬误扫描：循环论证、以偏概全、错误归因（相关当因果）、滑坡、稻草人、诉诸权威/情绪、幸存者偏差。逐处定位。
第三步 · outline 覆盖核对（completeness）：draft 是否覆盖 outline 每个主体点？有无超纲（写了大纲没有的）/缺章（大纲有的没写）/跳跃？逐点打钩，列一张"outline 点 → draft 是否覆盖"对照表作为覆盖率凭证。 还要扫"网状没收成树"（平克模型）：是否多中心、跳跃、嵌套，没收敛成"一个主干 + 单层分支"？是 → 结构性问题。
第四步 · 反例对抗 pass（adversarial）：对每个核心论点，强制构造一个反例或替代因果解释——"如果不是因为 A，会不会其实是 B 导致的？""有没有一类情况这个结论不成立？"。扛不住反例的论点标 [Critical]。
举证下限（completeness）
逐段扫、不许一眼带过；确无问题时必须显式声明核查范围（已逐段核论证链、outline 全点覆盖）并附 2 条最接近边界的例子——这才是凭证（口径见 handoff-protocol §六补）。
升级判据
- 若问题是"结构性"（多中心/缺主干/大段缺章/递进塌方）→ 打回 outline-architect 重做结构，而非让 drafter 局部补。
- 若是局部论证薄弱/谬误 → 打回 drafter 改对应段。
输出（写入 review-log.md logic 段 / 并行时 review-fragment-logic.md）
- outline 覆盖对照表（每点是否覆盖）；2) [Critical]/[Warning]/[Suggestion] 三件套：定位原文 → 问题类型 → 修改方向（含至少 1 个反例若适用）；3) completeness 收尾行：
已核论证链 N 处、outline N 点全覆盖、反例对抗 N 个核心论点。
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.
- 5d ago First seen · 30 lines · 29 tokens per session scan A 04282d414e00
logic-reviewer is an agent published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 760 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.