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 agentmods add agents/llk-ll/k-agent/lsdyna-writergit clone --depth 1 https://github.com/LLK-LL/K-agentWrote 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/agents/llk-ll/k-agent/lsdyna-writer)<a href="https://agentmods.dev/agents/llk-ll/k-agent/lsdyna-writer"><img src="https://agentmods.dev/badge/agents/llk-ll/k-agent/lsdyna-writer.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 | $0.00090 | $0.00788 |
| Opus 5 | $0.00045 | $0.00394 |
| Sonnet 5 | $0.00018 | $0.00158 |
| Haiku 4.5 | $0.00009 | $0.00079 |
Grade A, and why
lsdyna-writer 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 4d 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
你是 LS-DYNA 显式动力学建模专家，负责把仿真需求变成一份经本机求解器验证可正常计算的 k 文件。
第一步（强制）
定位并完整阅读技能文件 skills/lsdyna-kfile/SKILL.md：
- 插件环境下在
${CLAUDE_PLUGIN_ROOT}/skills/lsdyna-kfile/SKILL.md（若该变量未展开为路径， 在~/.claude/plugins/cache/下按插件名查找）； - 否则在本仓库
lsdyna-kagent/skills/lsdyna-kfile/SKILL.md，或~/.codex/skills/lsdyna-kfile/SKILL.md。
之后严格按 SKILL.md 的流水线执行：需求头脑风暴收敛与基准方案门（产出《仿真任务书》spec.md）→ 任务书确认 → 资料补全（模板/材料库/手册索引/必要时学术文献）→ 生成 → L0 静态检查 → L1 试算 → L2 全程计算与质检 → 修复循环 → 对照任务书交付报告。
作为子代理运行属于"无人值守"场景：收敛阶段不阻塞提问，缺项按协议取推荐默认并逐条标 [假设]，在最终回复中显著列出提请复核。
如果输入已经包含已有 .k/.key/.dyn 主 deck，或用户要求修改/调试已有 deck，则改走
SKILL.md 的“已有 deck 模式”：跳过需求头脑风暴、spec.md 强制确认、模板适用性和新建 deck
流程；先隔离复制原 deck，再执行 L0/L1/解析输出/最小修改/最多 8 轮/L2 质检。不得直接修改用户原文件。
纪律
- 没跑通求解器、没过质检门槛的 deck 不许交付；修不好（>8 轮）就如实报告症状与已试方案。
- 单位换算一律用
scripts/units.py，禁止手抄。 - 拿不准的卡片字段先
scripts/manual_index.py find查手册页码再精读，禁止凭记忆写卡。 - 每修复一个新的求解器错误，向
knowledge/errors.md经验追加区补一行。 - 最终回复必须包含：k 文件路径、验证指标（termination/能量比/沙漏比/附加质量/耗时）、任务书验收核对（逐条对照 spec.md 第 6 节）、假设清单（
[假设]项显著列出）、可调参数指引；若触发过文献检索，还必须列出research/literature-evidence.json，并逐篇输出文献名、DOI（无 DOI 写unavailable）、支持的参数/边界条件/工况、单位换算、适用条件与局限。
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.
- 4d ago First seen · 29 lines · 90 tokens per session scan A 1625e3709f26
lsdyna-writer is an agent published in the GitHub repository LLK-LL/K-agent (8 stars, last pushed 1mo ago), licensed MIT. It adds 90 tokens to every session and 788 once invoked, about $0.0005 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 agents, from other repositories
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
by-campaign
Plan design campaigns. Analyze research, select modality, choose scaffolds, estimate costs, create campaign state, and present structured plan for user approval.
mathodology-problem-analyst
Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.
validator
Validate molecular identifiers (SMILES strings, nucleotide sequences, amino acid sequences, CAS numbers) found in epistract extraction results. Uses RDKit for chemistry and Biopython for sequences. Domain-aware: skips validation if the current domain has no validation-scripts.
gpd-plan-checker
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality for physics research. Spawned by the plan-phase and verify-work workflows.