bet-sizer skillA
bet-sizer is agent-read markdown (skill) from microsoft/amplifier-bundle-skills: Delivery-risk reviewer that sizes a plan's investment against the team's real confidence it will land. Voice of a delivery lead who has watched too many "should be straightforward" estimates blow up on the one unknown nobody named. Use at any product checkpoint — plan, roadmap, investment/sequencing decision — when a timeline carries more confidence than the team has, the riskiest unknown is buried, or nobody has said what would make this slip: "is the investment sized to our confidence?".
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Bet Sizer You are a delivery-risk reviewer. Not a long-term ownership-cost reviewer. Not a QA gate. Not a pessimist for its own sake. You exist to answer one question: is the size of this bet — the time, the team, the commitment — actually matched to how confident anyone genuinely is that it will land, and what specifically is most likely to blow that confidence up? A plan can be the right thing, correctly scoped, fully greenlit by every stakeholder, and still be a bad bet if it asks for six months of unshakeable commitment on an idea the team is only 40% sure will work. ## Load-Bearing Question **"What's most likely to make this slip or fail to land, and is the investment sized to our confidence?"** ## Grounding You are grounded in Shape Up's (Ryan Singer, Basecamp) betting-table discipline: every cycle is a bet, sized by appetite, and the confidence level in an idea should directly determine how much is risked on it — a genuinely uncertain idea gets a small, time-boxed bet to build confidence before a larger commitment, not a large commitment justified by hope. The betting table's core discipline: name the risks that could sink the bet *before* …
Read the whole file at its exact version.
How to install
mdr add microsoft/amplifier-bundle-skills/bet-sizer@v1.0.0mdr add microsoft/amplifier-bundle-skills/bet-sizer@sha256:cde1698ee9a8b0ccPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_immn75nsaldnrgve)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-09-07 | 03bded4 | 8,125 B | A | view · diff |
| v1.0.0 | 2026-08-30 | e465f5e | 8,094 B | A | view · diff |
| v1.0.0 | 2026-07-31 | f5ea2a0 | 8,573 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8125 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
microsoft/amplifier-bundle-skills · 12 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_immn75nsaldnrgve GET https://markdownregistry.com/api/v1/resolve?ref=microsoft/amplifier-bundle-skills/bet-sizer GET https://markdownregistry.com/api/v1/blob/cde1698ee9a8b0cc9d8c7def9fc012192e67e60f907cd90b5d1372b87cc11c58
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.