OpenByline: Skill for Claude Code

.claude/skills/completeness-critic/SKILL.md

completeness-critic is a skill for Claude Code from bailutingyu/OpenByline. It costs 76 tokens per session (1,071 once invoked), scanned A, original, MIT.

A final review guide for checking whether earlier fact, logic, and style reviews covered the whole document. It also requires independent spot checks instead of simply trusting the earlier reviewers.

In plain words
What is it for?
Use it during final quality control to verify review coverage, sample-check important facts and reasoning, and count unresolved critical issues for the current draft.
Why use it?
It catches missed claims, arguments, or style problems before approval and prevents a final reviewer from merely repeating previous conclusions.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is bailutingyu/OpenByline's own configuration. It tells Claude Code how to work on OpenByline itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything OpenByline configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bailutingyu/OpenByline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bailutingyu/OpenByline/main/.claude/skills/completeness-critic/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/bailutingyu/OpenByline

Made for: Claude Code.

Wrote 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.

agentmods badge for completeness-critic

README.md
[![agentmods](https://agentmods.dev/badge/skills/bailutingyu/openbyline/completeness-critic.svg)](https://agentmods.dev/skills/bailutingyu/openbyline/completeness-critic)
Your own site
<a href="https://agentmods.dev/skills/bailutingyu/openbyline/completeness-critic"><img src="https://agentmods.dev/badge/skills/bailutingyu/openbyline/completeness-critic.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,071 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.01071
Opus 5 $0.00038 $0.00535
Sonnet 5 $0.00015 $0.00214
Haiku 4.5 $0.00008 $0.00107

Measured 6d ago against content hash 788fa68ffa4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

completeness-critic 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 6d 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.

.claude/skills/completeness-critic/SKILL.md · 50 lines

What it actually says

覆盖率核验手册(completeness-critic)

终审最容易犯的错:把上游三道审查的结论再读一遍、盖个章就放行。这不是终审——上游若漏检(尤其 fact-checker 只扫了一遍、漏抽了断言),终审跟着一起漏。终关的职责是 completeness critic:不复述结论,只核覆盖率 + 独立抽样复核。

一、覆盖率核对(三查,缺一不可)

  1. 事实覆盖率:读 fact-checker 产出的断言清单(编号|原文|类型|来源状态|判定|置信度),确认它覆盖全文每一条可证伪断言。自己把 draft 通读一遍,随手点几处数字/专名/时间,看断言清单里有没有。覆盖率 < 100%(有断言没被抽到核)→ 直接打回 fact-checker 补全,不放行。
  2. 逻辑覆盖率:读 logic-reviewer 的论证链,确认它覆盖 outline 的每个主体点——draft 是否覆盖 outline 全部要点、有无超纲/缺章/跳跃。覆盖不全 → 打回 logic-reviewer / outline-architect。
  3. 风格覆盖率:确认 style-aligner 给了符合篇幅的逐句举证(≥1000 字 ≥5 条)、五条硬否决逐条判过、密度四数字带定位。缺项 → 打回 style-aligner。

二、独立抽样复核(终关自己动手,不靠转述)

不要只信上游"已核"。自己抽 N 条重新验证

  • 事实:抽 2-3 条关键数字/引文,自己用 Read(research-dossier)或常识/检索快速复核一遍;与 fact-checker 结论不一致 → 升级(标 Critical 打回)。
  • 逻辑:抽 1-2 条核心论证,自己问一次"这个因果成立吗、有没有反例";站不住 → 打回。
  • 抽样命中问题 = 上游核查质量存疑,不是补一条就完事,要让对应 reviewer 整轮重核。

三、结构化 Critical 计数(别数散文)

消费 review-log 的结构化字段 round / reviewer-agent / severity / draft-version按字段计数针对当前 draft-v{n} 的 severity=critical 条数:

  • Critical > 0 → 一律打回 needs-rework,不进定稿。
  • 用 Grep 按字面查 review-log 里的 [Critical] / critical 做交叉核对,防止散文叙述里漏数一个

四、通用 completeness 凭证格式(所有 reviewer 落地,终关消费)

每个审查 agent 末尾都给一张待检清单,终关据此判覆盖率:

## completeness 凭证
| 编号 | 检查项(断言/论点/风格点) | 状态 | 判定 |
|---|---|---|---|
| 1 | 第2段"全球80%…" | 已核 | [Critical] 无源,打回 |
| 2 | 第3段因果"A导致B" | 已核 | 通过 |
| … | … | … | … |
本稿共抽取 N 项、已核 N 项、覆盖率 = 100%、收敛轮数 R = 2

终关核对:覆盖率必须 = 100%、收敛轮数 R ≥1(fact 的 loop-until-dry 至少跑到一轮 0 新增),否则打回。

五、终关补充的总判据(金线判据)

覆盖率过关后,再补两问(写进 final-qc 终审第 1 条):

  • 认知改变:这篇能否帮读者完成一次"认知改变",而不只是多知道一个信息?(金线 9 条的收敛核心)
  • 缝合检验:读者能否用一句自己的话把核心复述出去?复述不出来 = 没真正"收到",回去改。
Changes

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.

  1. 6d ago First seen · 50 lines · 76 tokens per session scan A 788fa68ffa4c

Subscribe to this mod's changes

completeness-critic is a skill published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 1,071 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 2026-08-31.