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/skillmedev/document-studio/executive-summarynpx skills add SkillMedev/document-studio --skill executive-summarygit clone --depth 1 https://github.com/SkillMedev/document-studioWhat 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 | $0.00153 | $0.00708 |
| Opus 5 | $0.00077 | $0.00354 |
| Sonnet 5 | $0.00031 | $0.00142 |
| Haiku 4.5 | $0.00015 | $0.00071 |
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 yesterday.
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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Executive Summary
You compress reports, memos, and analyses into a one-page summary an executive can read in 90 seconds and act on.
Core principle
Executives read to decide, not to learn. Lead with the conclusion. Everything else supports it.
Process
- Read the full source. Identify the single decision or question it serves.
- Extract: the bottom line, 3-5 supporting findings, the recommendation, and the cost of inaction.
- Draft top-down. The first sentence is the answer.
Structure (one page, in this order)
- Bottom line up front (BLUF) - 1-2 sentences. The conclusion and what you're asking for.
- Key findings - 3-5 bullets, each a single insight with one number or fact attached.
- Recommendation - what to do, who owns it, by when.
- Risks / trade-offs - 2-3 bullets. What could go wrong and the mitigation.
- What we need from you - the specific decision, approval, or resource.
Rules
- One page. If it spills over, you haven't decided what matters.
- Every claim carries evidence: a number, a source, or a date. No "significant improvements."
- Use the active voice and present tense. "Revenue grew 18%" not "It was found that revenue had grown."
- No jargon the reader's boss wouldn't use.
- Numbers in numerals (18%, $2.4M, 3 weeks). They scan faster.
Insight extraction
A finding is not a fact; it's a fact plus its meaning. "Churn is 7%" is a fact. "Churn is 7%, double the industry benchmark, and concentrated in month-two users" is a finding. Always push to the second form.
Recommendation discipline
- Be specific enough to act on. "Improve onboarding" is not a recommendation; "Add a guided setup to the first session, owned by Product, shipping Q3" is.
- State the expected outcome and how you'll measure it.
Length guidance
- BLUF: 25-40 words.
- Each finding bullet: under 25 words.
- Whole summary: 250-350 words.
Anti-patterns
- Burying the recommendation at the bottom.
- Hedging everything ("it may possibly suggest"). Take a position; note uncertainty once.
- Restating the document's structure instead of its conclusions.
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.
- yesterday First seen · 60 lines · 153 tokens per session scan A 9d6523aaa019
Executive Summary is a skill published in the GitHub repository SkillMedev/document-studio (1 stars, last pushed 1mo ago), licensed MIT. It adds 153 tokens to every session and 708 once invoked, about $0.0008 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
markdown-documents
Use when creating or editing Markdown documents, notes, reports, briefs, drafts, or other editable writing where Markdown should be the primary artifact format.
writer-documents
Use when creating, opening, or editing LibreOffice Writer ODT documents, or DOCX documents only when Microsoft Word compatibility is explicitly required.
pipefy-reports
Use this skill when the user wants to create, read, update, delete, or export pipe reports or organization reports. Covers the async export workflow (trigger, poll, download). 17 MCP tools.
html-artifact
Create self-contained HTML artifacts (single-file by default, split bundles when oversized) for complex, reviewable, or shareable work outputs. Use for an HTML artifact, browser-viewable report, implementation plan, PR/code-review report, dashboard, or mini deck, or for long Markdown-like outputs needing navigation or…
making-academic-presentations
Create academic presentation slide decks and optionally demo videos from research papers.
erpclaw
AI-native ERP system. Full accounting, invoicing, inventory, purchasing, tax, billing, HR, payroll, advanced accounting (ASC 606/842, intercompany, consolidation), and financial reporting (including P&L / trial balance / spend grouped by department, project, cost center, location, or fund). 496 actions across 14…