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 skills add Lambenthan/paper-discipline-skills --skill paper-parallel-auditgit clone --depth 1 https://github.com/Lambenthan/paper-discipline-skillsWrote 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/lambenthan/paper-discipline-skills/paper-parallel-audit)<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.
<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>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 | $0.00129 | $0.01600 |
| Opus 5 | $0.00064 | $0.00800 |
| Sonnet 5 | $0.00026 | $0.00320 |
| Haiku 4.5 | $0.00013 | $0.00160 |
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.
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。
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.
- 11d ago First seen · 179 lines · 129 tokens per session scan A 7dae435f2465
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.
Other skills, from other repositories
secure-auth
Secure authentication patterns (OWASP, NIST). Use for login, registration, password reset, sessions, JWT, OAuth, MFA, passkeys.
academic-writing
Scholarly writing and research compliance. Use for CRediT, preregistration, Plan S, Nelson Memo, preprints, ORCID, LLM disclosure.
page-monitoring
Web page change detection, availability tracking, and RSS feed generation. Use to monitor changes, downtime, or make a feed.
web-archiving
Web archiving and retrieval via Wayback Machine and Archive.today. Use to preserve content, reach dead pages, or save evidence.
accessibility-compliance
Web accessibility patterns for news and academic sites. Use for WCAG audits, alt text, accessible data viz, and assistive tech.
one-way-door
Flags irreversible decisions before commit. Use for data models, infra, auth boundaries, API contracts, event schemas, CI/CD.