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 skills/arcadi4/nerdy/parallel-algorithmsnpx skills add Arcadi4/nerdy --skill parallel-algorithmsgit clone --depth 1 https://github.com/Arcadi4/nerdyWhat 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 | $0.00049 | $0.03324 |
| Opus 5 | $0.00024 | $0.01662 |
| Sonnet 5 | $0.00010 | $0.00665 |
| Haiku 4.5 | $0.00005 | $0.00332 |
Grade A, and why
parallel-algorithms 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 2d 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 — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Algorithms
Overview
Core principle: analyze correctness before speed. A fork-join keyword says work may run in parallel; it does not prove race freedom, useful speedup, or production scalability.
Shared CLRS Conventions
Use the parent clrs skill for mathematical formatting, theorem tone, and answer discipline. Keep every bound, recurrence, ratio, and inequality in display LaTeX blocks. Keep Markdown tables verbal; put the formulas in nearby display blocks.
Output Discipline for Parallel Answers
Parallel-algorithm answers are notation-heavy, so formatting leaks are common. Do not announce that this skill is being used. Start with the review or solution.
Use prose names in sentences and tables, then put the notation in display blocks. For example, say "the work is quadratic" in prose, then show the bound below in a display block. Do not put work/span symbols, processor-count formulas, slackness ratios, or asymptotic bounds in table cells, headings, inline math, or inline code spans.
When a table needs a formula, write a verbal label in the cell, such as "quadratic work" or "polylogarithmic span," and put the exact expression immediately after the table.
Arithmetic is also a formula. Processor estimates such as a work term divided by a processor count plus a span term must be displayed in LaTeX blocks, not written as prose-line arithmetic with +, =, /, ÷, powers, or asymptotic notation.
Safe pattern:
The estimate for the first candidate is below.
$$
\frac{2048}{512} + 1 = 5
$$
The estimate for the second candidate is below.
$$
\frac{1024}{512} + 8 = 10
$$
Unsafe pattern:
Version A: 2048 / 512 + 1 = 5 seconds.
When to Use
Use this skill for:
- fork-join pseudocode using
spawn,sync, orparallel for; - serial projection, trace DAGs, strands, critical paths, and sequential consistency;
- work, span, speedup, parallelism, slackness, and greedy scheduling analysis;
- determinacy race reviews and shared-memory update patterns;
- parallel loops, matrix-vector multiplication, matrix multiplication, Strassen, parallel merge, and parallel merge sort;
- parallel reductions, scans, stencils, and randomized parallel algorithms;
- production reviews of textbook parallel algorithms, task granularity, scheduler overhead, work stealing, and coarsening.
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.
- 2d ago First seen · 397 lines · 49 tokens per session scan A b30d99f442e2
parallel-algorithms is a skill published in the GitHub repository Arcadi4/nerdy (7 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 3,324 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.
Other skills, from other repositories
pptx
从论文、大纲或结构化文本生成 PowerPoint (.pptx) 演示文稿。Use when 用户需要把一篇论文/文章/大纲做成幻灯片、slides、演示文稿、PPT、deck。Don't use when 只需纯文本总结、生成 Word/PDF、或修改已有 pptx 的单个像素级样式。.
ai-style
当任务是用中文撰写或改写面向读者的文案（产品发布稿、公众号文章、邮件、README 等）， 或用户反馈文字「AI 味太重」「不像人写的」时，加载本 Skill。.
curly-quote-sft
Skill "curly-quote-sft" from bojieli/ai-agent-book, covering 中文技术文档符号与引用规范, 何时加载, 符号定义, 决策优先级 and 正反例约束.
triage
你是当前任务的分诊协调者。先识别用户的全部目标、顺序依赖和验收条件，再按 “事实检索 → 计算/执行 → 写作”顺序逐步请求切换到需要的专业能力。不要替专业 能力完成它的工作，也不要在信息缺失时臆造结果。.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
research
用真实检索工具查找可追溯的事实、数据和来源。.