paper-parallel-audit

paper-parallel-audit is a skill for Claude Code, Codex from Lambenthan/paper-discipline-skills. It costs 129 tokens per session (1,600 once invoked), scanned A, original, MIT.

A batch-audit workflow for checking or updating at least 30 independent items, such as citations, terminology, formatting, or publication details.

In plain words
What is it for?
Use it for large document or reference audits when items can be processed independently and the same checking method applies to each one.
Why use it?
It divides large repetitive jobs among agents, saves each part as JSON, and allows failed parts to be rerun without repeating completed work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it for large document or reference audits when items can be processed independently and the same checking method applies to each one.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lambenthan/paper-discipline-skills/paper-parallel-audit
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 Lambenthan/paper-discipline-skills --skill paper-parallel-audit
Clone the repo
git clone --depth 1 https://github.com/Lambenthan/paper-discipline-skills

Made for: Claude Code, Codex.

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 paper-parallel-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/lambenthan/paper-discipline-skills/paper-parallel-audit/github.svg)](https://agentmods.dev/skills/lambenthan/paper-discipline-skills/paper-parallel-audit)
Your own site
<a href="https://agentmods.dev/skills/lambenthan/paper-discipline-skills/paper-parallel-audit"><img src="https://agentmods.dev/badge/skills/lambenthan/paper-discipline-skills/paper-parallel-audit/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.

agentmods 80×15 button for paper-parallel-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/lambenthan/paper-discipline-skills/paper-parallel-audit"><img src="https://agentmods.dev/badge/skills/lambenthan/paper-discipline-skills/paper-parallel-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,600 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 $0.00129 $0.01600
Opus 5 $0.00064 $0.00800
Sonnet 5 $0.00026 $0.00320
Haiku 4.5 $0.00013 $0.00160

Measured 11d ago against content hash 7dae435f2465, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

paper-parallel-audit 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.

paper-parallel-audit/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

paper-parallel-audit:大批量核查的并行 Agent 模式

核心理念

156 篇引用串行核查 ≈ 5 小时 + 中间挂了从头来。 3 个 Agent 并行 + 每个 50 篇 + JSON 落盘 ≈ 1 小时 + 任意一个挂了只重跑那一个。

批量任务的瓶颈不是 AI 的速度,是"挂了从头来"的恐惧。 并行 + 落盘 = 把恐惧拆成可控的小块。


触发条件

满足全部 → 触发:

  • 任务规模 ≥ 30(条目 / 引用 / 文件 / 段落)
  • 各条目之间无依赖(核查 A 的结论不影响 B 的核查)
  • 操作是同质的(每条用的方法 / 标准都一样)
  • 已经通过 paper-pilot-before-batch 跑过样本,逻辑确认无误

任意一条不满足 → 不并行,老老实实串行 + 落盘(仍然要落盘)。


标准模式(4 个组件,缺一不可)

组件 1:分片

total = 156 条
shard_size = 50(按 Agent 数倒推)
shards = [0:50, 50:100, 100:156]

组件 2:每个 Agent 独立输出 JSON

每个 Agent 处理自己的分片,输出:

{
  "shard_id": "0-50",
  "total": 50,
  "results": [
    {"item_id": 1, "status": "pass", "issue": null},
    {"item_id": 2, "status": "fail", "issue": "作者名拼写错误", "suggestion": "..."}
  ],
  "completed_at": "<ISO 8601 timestamp>"
}

组件 3:主进程汇总 + 落盘

# 等所有 Agent 返回后
python merge_shards.py shard-*.json > audit_report.json

组件 4:断点续跑

  • 每个 Agent 跑完立即落盘 JSON 到磁盘
  • 任何一个挂了,只重跑那个分片
  • 主进程读已有 JSON,跳过已完成

强制流程

检测到 ≥ 30 条目的同质批量任务
        │
        ▼
确认已经跑过 paper-pilot-before-batch
        │
        ▼
分片:N 个 Agent,每个 ≤ 50 条
        │
        ▼
告诉用户:「派 N 个 Agent 并行,每个负责 [区间],
各自落盘 JSON。预计 [时间],挂了只重跑挂掉的分片。」
        │
        ▼
用 Task 工具派 Agent(subagent_type 选 general-purpose)
单条消息里多个 Task 调用 = 真正并行
        │
        ▼
等所有 Agent 返回 → 汇总 JSON → 给用户报告

派 Agent 的标准 prompt 模板

你是引用核查 Agent,负责本批 [分片区间]。

任务:核查每条引用的 [核查标准列表]。
输入:[引用列表 / 文件路径]
输出:JSON 文件,路径 `shard-<分片 ID>.json`,格式:
  {
    "shard_id": "...",
    "total": N,
    "results": [
      {"item_id": ..., "status": "pass|fail", "issue": "...", "suggestion": "..."}
    ],
    "completed_at": "..."
  }

完成后只返回一句话:「分片 X 完成,pass M 条,fail K 条,已落盘 shard-X.json」。
不要把详细结果写在回复里——一律只在 JSON 里。

❌ 反例(书 §10.2)

用户:「把这 156 条引用核查一遍。」

错误做法:在主会话里串行跑——

  • 跑到第 80 条 rate limit 了
  • claude --continue 接续,但中间结果在内存里没存
  • 重跑要么从头来,要么人工记到第几条
  • 用户的耐心已经磨没了

正确做法:分 3 片 → 派 3 个 Agent → 各自 JSON 落盘 → 主进程汇总 → 用户拿到完整报告。


Read the full file on GitHub · 179 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. 11d ago First seen · 179 lines · 129 tokens per session scan A 7dae435f2465

Subscribe to this mod's changes

paper-parallel-audit is a skill published in the GitHub repository Lambenthan/paper-discipline-skills (19 stars, last pushed 3mo ago), licensed MIT. It adds 129 tokens to every session and 1,600 once invoked, about $0.0006 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.