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 ziwang-Physics/AgentChat --skill agentchat-independenttasksgit clone --depth 1 https://github.com/ziwang-Physics/AgentChatWrote 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/ziwang-physics/agentchat/agentchat-independenttasks)<a href="https://agentmods.dev/skills/ziwang-physics/agentchat/agentchat-independenttasks"><img src="https://agentmods.dev/badge/skills/ziwang-physics/agentchat/agentchat-independenttasks/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/ziwang-physics/agentchat/agentchat-independenttasks"><img src="https://agentmods.dev/badge/skills/ziwang-physics/agentchat/agentchat-independenttasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 50 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 50 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 60 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 235 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 235 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00087 | $0.04246 |
| Opus 5 | $0.00044 | $0.02123 |
| Sonnet 5 | $0.00017 | $0.00849 |
| Haiku 4.5 | $0.00009 | $0.00425 |
Grade A, and why
AgentChat-IndependentTasks 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 10d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentChat-IndependentTasks：独立任务并行分发 + 解答手册合成
⛔ 角色边界
你是管道的调用者，只做三件事：准备输入 → 调用脚本 → 报告结果。禁止手工模拟管道任何环节（提取题目、分组、编写 prompt、审校答案、编译 PDF）。
核心模型
N 道独立任务，M 个能力等同的 AI（最多 7：gemini/chatgpt/qwen/kimi/minimax/mimo/deepseek），纯分发、零协作。
题目 → 按主题分组 → JSON Plan → node index.js 并行派发 → 校验 → 合成 → md2pdf.sh → PDF
三条铁律：
- 所有 AI 同一 prompt 模板，只是题目子集不同。禁止差异化角色设定。
- 每题一个权威答案（择优或融合，统一口吻重写），不并列展示多版本。
- 零 AI 署名——PDF 中不得出现 provider 名称/徽章/覆盖矩阵/审计报告/AI 元数据。
强制执行规则（不可跳过、不可绕过）
-
必须真实派发。 一切 AI 查询必须通过
node ~/.claude/skills/AgentChat-IndependentTasks/index.js实际执行，禁止 Claude Code 自行代答。 -
必须生成运行回执（receipt）。 由
skills/lib/receipt.js生成，回执缺失 = 未执行。 -
文件修改分级:
- 冻结（只读）:
index.js（编排层）、AgentChat-OneWeb/index.js（Provider 层） - 共享库（改动需跨技能验证 + 全量测试）:
lib/*.js（含lib/plan.js、lib/execute.js、lib/locks.js等） - 可自由修改:
SKILL.md、synthesize.js、validate_answers.js、md2pdf.sh
- 冻结（只读）:
-
失败分级降级协议。 失败 = provider 超时/桥接失败/Step 2.5 答非所问。三级路径：
- L1（自动）：补发一次，改派 fallback 链下一可用 provider。foreign anchor 失败（路由串扰）→ 逐组串行补发；锚行缺失/伪造检测（拒答/bridge 空返回）→ 并行补发。
- L2（停下等用户）：L1 后仍失败 → 输出失败报告 + 两选项（用户指定方案再补发 / 授权生成部分 PDF，缺答以
> ⚠ 本题答案待补占位标出）后 STOP。 - 绝对禁止：Claude Code 自答填补 / 同一回合报告失败又擅自生成"完整"PDF。
-
合成前强制通过内容校验门（机器执行）。 派发后必须跑
validate_answers.js（校验锚行逐字出现、外来锚检测、噪声剥离）。退出码非 0 → L1。合成材料用clean/目录，不用原始 stdout。 -
用户 provider 约束写进
exclude，覆盖 fallback 链与 L1。 只不设 primary 不够——fallback 链会自动路由到被禁 provider。必须 plan 顶层"exclude": ["claude"]并在 L1 补发时同样跳过。 -
每次 validation
--out目录必须唯一（带时间戳）。 旧目录残留历史 clean 文件会导致误取错误回答。 -
semantic_check.json 必须"生成→读取→批量改 verdict→写回"。
validate_answers.js自动生成，初始PENDING。 必须 Read → 逐条对照原始题目核实（不得跳过任何条目）→ 在内存中构造完整 JSON → 一次性 Write 回同一路径。 约束:- 仅修改
verdict与note字段；其余字段（subtask/question/restatement等）原样保留。 note为单句（≤30 字），须指出判定依据，禁止空泛的"内容匹配"。- 写回前自查 JSON 合法性（引号转义、尾逗号）。
- 条目数 ≤3 时可用 Edit 逐条改；>3 条时必须用 Write 批量替换以省 token。
禁止从零手写。
md2pdf.sh遇PENDING/MISMATCH拒绝编译（退出码 5）。
- 仅修改
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- fonts/Inter-400.ttf 66 KB
- fonts/Inter-600.ttf 66 KB
- fonts/Inter-700.ttf 66 KB
- fonts/InterVariable-Italic.ttf 873 KB
- fonts/InterVariable.ttf 843 KB
- index.js 58 KB runs code
- math_render.py 12 KB runs code
- md2pdf.sh 3.7 KB runs code
- references/prompt-templates.md 5.9 KB
- synthesize.js 12 KB runs code
- validate_answers.js 20 KB runs code
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.
- 10d ago First seen · 264 lines · 87 tokens per session scan A 9f8780640fea
AgentChat-IndependentTasks is a skill published in the GitHub repository ziwang-Physics/AgentChat (761 stars, last pushed 29d ago), licensed MIT. It adds 87 tokens to every session and 4,246 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 2026-08-30.
Other skills, from other repositories
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.