kaozheng

kaozheng is a skill for Claude Code from MidnightDarling/collate. It costs 40 tokens per session (588 once invoked), scanned A, original, Apache-2.0.

An evidence checker for historical papers or final drafts. It examines whether claims are supported by the cited sources, whether quotations keep their original meaning, and whether the reasoning connecting evidence to claims is sound.

In plain words
What is it for?
Use it to audit a paper's claims, citations, quotations, source quality, reasoning, and argument structure.
Why use it?
It catches weak evidence and overextended citations that ordinary proofreading may miss. It also flags reliance on a single source or on lower-quality authorities.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the collate plugin — 15 skills, 2 commands, 2 agents shipped together

Good fit Use it to audit a paper's claims, citations, quotations, source quality, reasoning, and argument structure.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/midnightdarling/collate/kaozheng
Install

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.

Any agent
npx skills add MidnightDarling/collate --skill kaozheng
Clone the repo
git clone --depth 1 https://github.com/MidnightDarling/collate

Made for: Claude Code.

Or install collate, the plugin that ships this one along with the rest of its 15 skills, 2 commands, 2 agents.

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 kaozheng

README.md
[![agentmods](https://agentmods.dev/badge/skills/midnightdarling/collate/kaozheng.svg)](https://agentmods.dev/skills/midnightdarling/collate/kaozheng)
Your own site
<a href="https://agentmods.dev/skills/midnightdarling/collate/kaozheng"><img src="https://agentmods.dev/badge/skills/midnightdarling/collate/kaozheng.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 588 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00040 $0.00588
Opus 5 $0.00020 $0.00294
Sonnet 5 $0.00008 $0.00118
Haiku 4.5 $0.00004 $0.00059

Measured 8d ago against content hash d9f43fac0a35, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

kaozheng 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 8d 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.

skills/kaozheng/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kaozheng

The work this skill is for

This is not typo-catching. That is proofread.

kaozheng reads in the Qian-Jia evidential tradition: not asking whether the paper sounds plausible, but whether its evidentiary bridge bears weight. The source may be real and the bridge still false. A citation may be accurate and still be pressed into service beyond what it can support.

What it audits

For a post-OCR, post-proofread paper, test:

  • whether the claim is actually supported by the data cited
  • whether quotations are complete enough to preserve original sense
  • whether cited authorities are first-rank, second-rank, or hearsay
  • whether the warrant is visible and defensible
  • whether the paper leans on a solitary witness (孤证不立)

Input

Target: $ARGUMENTS

  • workspace directory → read <ws>/final.md
  • .md file → read it directly
  • empty → ask what to read

If only raw.md exists, note that the text has not yet been proofread and mark the report accordingly.

Method

Read the argument in layers:

  1. Extract the paper's main claims.
  2. Pair each claim with its offered evidence.
  3. Identify the warrant that connects the two.
  4. Audit quotations and citation framing:
    • what is quoted
    • what is omitted
    • what rank the source holds
    • whether a footnote quietly carries more force than the body text
  5. Flag cardinal errors first; breadth comes second.

The framework is a scale, not a blade. Do not deform the paper merely to force it into Toulmin language.

Output

  • workspace mode → <workspace>/analysis/{stem}_kaozheng.md
  • single-file mode → analysis/{stem}_kaozheng.md

Report structure:

  1. Argument skeleton — claim / data / warrant / backing / qualifier / rebuttal
  2. Citation audit table — original fragment → suspected source → verifiable? → truncated?
  3. Cardinal errors — one to three, ranked by severity, with repair suggestions
  4. Suspicious but unverified — handed off for further checking

Guardrails

  • Never modify the source text.
  • Do not confuse disagreement with disproof.
  • One decisive structural error outweighs twenty decorative observations.
  • If verification is impossible from available material, mark it as unverified rather than pretending certainty.

Read the full file on GitHub · 75 lines

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. 8d ago First seen · 75 lines · 0 tokens per session scan A d9f43fac0a35

Subscribe to this mod's changes

kaozheng is a skill published in the GitHub repository MidnightDarling/collate (7 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 588 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

nft-standards

Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.

wshobson/agents · 48 tokens

postgresql-table-design

Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.

wshobson/agents · 37 tokens

spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

wshobson/agents · 63 tokens

parallel-feature-development

Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…

wshobson/agents · 105 tokens

cost-optimization

Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.

wshobson/agents · 48 tokens

istio-traffic-management

Configure Istio traffic management including routing, load balancing, circuit breakers, and canary deployments. Use when implementing service mesh traffic policies, progressive delivery, or resilience patterns.

wshobson/agents · 40 tokens