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 sruthir28/enterprise-ai-skills --skill top-down-memogit clone --depth 1 https://github.com/sruthir28/enterprise-ai-skillsWrote 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/sruthir28/enterprise-ai-skills/top-down-memo)<a href="https://agentmods.dev/skills/sruthir28/enterprise-ai-skills/top-down-memo"><img src="https://agentmods.dev/badge/skills/sruthir28/enterprise-ai-skills/top-down-memo/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/sruthir28/enterprise-ai-skills/top-down-memo"><img src="https://agentmods.dev/badge/skills/sruthir28/enterprise-ai-skills/top-down-memo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00093 | $0.02274 |
| Opus 5 | $0.00046 | $0.01137 |
| Sonnet 5 | $0.00019 | $0.00455 |
| Haiku 4.5 | $0.00009 | $0.00227 |
Grade A, and why
top-down-memo 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 11d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Top-Down Memo
The McKinsey writing rule: lead with the answer. Chronological narratives ("first we did X, then Y, then Z, and concluded W") are how thinking happens, not how communication should land. Top-down inverts the order — conclusion first, then the structure that supports it, then the evidence.
This is also called BLUF (Bottom Line Up Front) in military writing and Minto Pyramid in consulting. Same idea. Different name.
The test: can the reader stop after the first paragraph and still know what you think and what you want? If yes, top-down. If they need to read to the end to find the answer, you wrote a story.
Why people don't do this naturally
The way you thought about something is the opposite of how the reader needs to hear it.
| You (writer) | Reader |
|---|---|
| Gathered data → found patterns → drew conclusion | Wants the conclusion → then patterns → then data only if they push back |
Chronological narrative is easier to write because it matches your discovery path. It's harder to read because the reader doesn't know where you're going. Reversing the order is unnatural but obviously correct.
Design choices
- Lead is the answer, not the setup. The first sentence states what you think. The reader can stop here.
- 2–4 supporting arguments. Rule of 3 is best. >4 means you haven't synthesized; <2 means it's a one-liner, not a memo.
- MECE at the argument level. The supports should not overlap and should jointly defend the lead.
- Evidence under each argument, not in a separate section. Reader skims to the argument they doubt, then drops down for proof.
- Background last (if at all). Most "background" sections exist because the writer felt anxious about jumping to the answer. Cut.
- One memo, one answer. If you have two recommendations, write two memos.
The pyramid structure
[LEAD]
The answer.
One sentence.
│
┌──────────────┼──────────────┐
│ │ │
[ARG 1] [ARG 2] [ARG 3]
Because… Because… Because…
│ │ │
• evidence • evidence • evidence
• evidence • evidence • evidence
• evidence • evidence • evidence
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.
- 11d ago First seen · 193 lines · 93 tokens per session scan A c133e4cae4a0
top-down-memo is a skill published in the GitHub repository sruthir28/enterprise-ai-skills (139 stars, last pushed 10d ago), licensed MIT. It adds 93 tokens to every session and 2,274 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 2026-08-30.
Other skills, from other repositories
lyrik
Security assessment of a codebase — minimal mode for runner validation.
librarian
Read-only retrieval over the daily-digest kept set. Slash-invoke with /librarian ; returns items verbatim with citations.
notes
Create and manage text notes in the workspace.
tdx-assets
Look up staff devices, assets, and locations in TeamDynamix (TDX). Given a list of names, emails, or partial identifiers, resolve each person and return the assets assigned to them with location, model, ownership type, and status. Read-only.
aggregator
Daily fetch from a fixed public allowlist; score against the user's interests file; cluster into themes; push the digest to the configured channel.
file-search
Find files and search content across directories.