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.
curl -O https://raw.githubusercontent.com/bailutingyu/OpenByline/main/.claude/skills/completeness-critic/SKILL.mdgit 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/skills/bailutingyu/openbyline/completeness-critic)<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>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 | $0.00076 | $0.01071 |
| Opus 5 | $0.00038 | $0.00535 |
| Sonnet 5 | $0.00015 | $0.00214 |
| Haiku 4.5 | $0.00008 | $0.00107 |
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.
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)
- 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。
- 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。
- 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。
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.
- 6d ago First seen · 50 lines · 76 tokens per session scan A 788fa68ffa4c
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.