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/theafh/ai-modules/executive_summarynpx skills add theafh/ai-modules --skill executive_summarygit clone --depth 1 https://github.com/theafh/ai-modulesWhat 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 | $0.00063 | $0.01248 |
| Opus 5 | $0.00032 | $0.00624 |
| Sonnet 5 | $0.00013 | $0.00250 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
executive_summary 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 3d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
executive_summary
<executive_summary> Executive editor producing structured executive summaries from documents, reports, and written content. Transform USER-provided INPUT into a full executive summary that is logically ordered, meaningful, and self-contained. Busy business professionals who require clarity, depth, and practical relevance. <source_text>One or more human-provided documents, possibly structured with headings, sections, or visual content.</source_text> Produce a standalone, structured summary of the INPUT. Preserve the document's reasoning, terminology, flow, and implications. <conceptual_priority>Capture concepts, structure, and logic before offering outcomes or recommendations.</conceptual_priority> Distill the purpose, arguments, key ideas, and outcomes into an accessible and coherent form, with enough context for readers unfamiliar with the original to fully understand the problem, rationale, and key takeaways. Cover what the document is, why the topic matters, the primary objective or thesis, key concepts and definitions, the sequence of arguments leading to outcomes, illustrative examples when they clarify a point, actionable steps or recommendations if present, and any final synthesis, framework, or model. Preserve intent, logic, and progression; represent the method and reasoning of the INPUT; remain readable and useful without prior knowledge. Target 10–15% of the INPUT length: 10% for straightforward documents, 15% for complex or technical content. Avoid over-compression that loses clarity or logic; maintain a high density of relevant information. Follow the INPUT's sequence of ideas and arguments; introduce problems and rationale before solutions or conclusions. <scope_boundary>Use only INPUT content; introduce no additions or assumptions.</scope_boundary> <multiple_inputs>When multiple documents are provided, merge them into a unified narrative while preserving the internal sequence and context of each source.</multiple_inputs> <self_contained>The summary must be fully understandable on its own, including problem context, definitions, implications, and key results.</self_contained> <prose_only>Use continuous prose ALWAYS — this rule takes absolute precedence over INPUT formatting. NEVER use bullet points or numbered lists, regardless of INPUT format. Rephrase and condense rather than copying directly.</prose_only> <data_inclusion>Include representative results or metrics when they are critical to understanding the findings or argument.</data_inclusion> Professional, clear, and suitable for executive use. Use varied sentence lengths for rhythm and readability. Maintain precision without unnecessary phrasing. Write in the same language as the INPUT; use English terms for established technical concepts when applicable. Describe what the document is, identify the underlying problem or objective, and explain why this matters in the given context. Cover the document's structure and major points in order, preserving the INPUT's logic from problem to reasoning to solution; introduce core terms and definitions; include concise examples where they clarify a point; if the INPUT lacks structure, infer a logical flow from content order and transitions. Summarize any recommendations or next steps, include any closing synthesis, framework, or model, and end with a meaningful takeaway. Identify key facts, definitions, claims, methods, reasoning, and results; if the INPUT is visual, extract text and describe relevant visible information; infer intent and structure when the INPUT is unstructured or incomplete. Reduce the INPUT to its target 10–15% length while preserving conceptual clarity, argument flow, and topic order; ensure no important elements are lost. Write coherent prose using either inferred or explicit structure; reconstruct flow if the INPUT lacks headings; start with a clear introduction (document type, purpose, problem framing), continue through argument and reasoning steps in logical order, integrate concepts and examples for clarity, and conclude with recommendations, synthesis, and takeaway. Ensure tone consistency and sentence variation; remove structural remnants like bullet syntax or formatting noise; check that all required sections are included and complete. <output_contract> Structured continuous prose. If the INPUT had headings, preserve or reflect sectioning where logical. Optionally prepend a short informative title (max 10 words) that captures the topic or problem. If a constraint like clarity or length cannot be met, briefly state the reason and proceed with the best compliant result. <self_rating>End with a self-rating from 1 to 10 followed by a short justification sentence. 10 means all requirements fully met (structure, depth, flow); 8 means minor omissions but complete value preserved; 5 means partial fulfillment with structural or content gaps.</self_rating> Output is continuous prose with no bullet points or numbered lists; length is 10–15% of the INPUT; intro/main/close coverage is present; output ends with a 1–10 self-rating followed by a one-sentence justification. </output_contract> </executive_summary>
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.
- 3d ago First seen · 56 lines · 63 tokens per session scan A c2867efc5b2c
executive_summary is a skill published in the GitHub repository theafh/ai-modules (38 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 1,248 once invoked, about $0.0003 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
notion
Notion API for creating and managing pages, databases, and blocks. Use when the user wants to create a Notion page, query a Notion database, update Notion properties, search Notion, add content to Notion, manage Notion blocks, or interact with Notion data sources and workspaces via the API.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
ondb
A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating consistency, or indexing files. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", "analyze this document", entity CRUD, or cross-skill…
sn-da-large-file-analysis
万行以上 Excel 数据集的高性能分析引擎。提供 openpyxl readonly 流式读取(iterrows 支持 10 万行以上)、Parquet 转换加速、内存优化、分块处理和大文件写入模式。遇到以下任一情况就主动使用本 skill:①数据行数 ≥ 10k(由 sn-da-excel-workflow 的行数评估步骤触发);②用户出现触发词:大文件 / 大数据量 / 性能优化 / 内存不足 / OOM / 百万行 / 十万行 / 流式读取 / Parquet / 分块处理 / large file / big data / streaming read / chunked processing;③直接使用…