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 decision-memo-buildergit 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/decision-memo-builder)<a href="https://agentmods.dev/skills/sruthir28/enterprise-ai-skills/decision-memo-builder"><img src="https://agentmods.dev/badge/skills/sruthir28/enterprise-ai-skills/decision-memo-builder/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/decision-memo-builder"><img src="https://agentmods.dev/badge/skills/sruthir28/enterprise-ai-skills/decision-memo-builder.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 | $0.00094 | $0.01730 |
| Opus 5 | $0.00047 | $0.00865 |
| Sonnet 5 | $0.00019 | $0.00346 |
| Haiku 4.5 | $0.00009 | $0.00173 |
Grade A, and why
decision-memo-builder 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 12d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decision Memo Builder
A 1-page memo that forces a decision. Not a status update. Not a brief. Not a FYI. The reader walks away knowing exactly what they are being asked to approve, by when, and why.
Memo DNA — four non-negotiables
Every decision memo must pass all four. If the draft fails one, rewrite. Do not ship a memo that fails Memo DNA.
- Brutal brevity — 1 page, ~400 words max. Every sentence earns its place or gets cut.
- Storyline clarity (SCP) — Situation → Complication → Resolution flow. Reader never asks "so what?"
- Decision-forcing — Last line is a yes/no ask with owner and date. Never "further analysis needed."
- Evidence density — Every claim backed by a number, quote, or source. No adjectives doing load-bearing work.
Structure
Title (≤10 words)
Name the decision, not the topic.
- ✅ "Sunset legacy reporting engine by Q3"
- ❌ "Reporting strategy update"
Context (3–4 sentences)
State of the world before the ask. Facts only. Baseline numbers. No history-of-the-universe framing.
Complication (2–3 sentences)
What changed, or what's at risk if we don't decide now. Include the number that makes this urgent.
- ✅ "Usage down 15% QoQ; 3 enterprise deals ($1.2M) flagged the gap in Q1 QBRs."
- ❌ "Usage has been declining and customers are concerned."
Options (2–3 options, 1–2 lines each)
Mutually exclusive. Each option gets:
- Name
- One-line description
- The single most important trade-off (cost, time, or risk)
Do not sneak a recommendation in here.
Recommendation (1 short paragraph)
State the chosen option and why it wins on the decision criteria that matter most. Cite the evidence that tips the call.
Risks & Mitigations (≤3 bullets)
The top 3 things that could go wrong, each paired with a 1-line mitigation. Not a risk inventory — the three the reader would actually ask about.
The Ask (1 line)
A specific yes/no request with an owner and a date.
- ✅ "Approve sunset by EOD Friday; Sarah owns migration plan by 5/1."
- ❌ "Let's discuss next steps."
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.
- 12d ago First seen · 162 lines · 94 tokens per session scan A 7c6ac01a1152
decision-memo-builder is a skill published in the GitHub repository sruthir28/enterprise-ai-skills (139 stars, last pushed 10d ago), licensed MIT. It adds 94 tokens to every session and 1,730 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.