Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Explain the Number
- **Ask "why not double?"** Name the resource or code path that bounds the result, such as a core, a lock, the disk, the network, or the load generator itself. Get it from a profile or from system counters taken during a run, then map it to source. A guess from reading the code is not a limiter. If you cannot say why the number is not twice as good, you do not know what you measured.
- **List what else the number could be measuring, and rule out each one with evidence.** The usual suspects are errors, skipped or cached work, code that never ran, an untuned side (one left on default settings), noise, and a piece too small to matter end to end.
- **Keep the evidence with the number.** Put the run count, the spread, and the limiter in the notes or a linked artifact.
For a performance number, run the full procedure with the [benchmark-checklist](../benchmark-checklist/SKILL.md) skill. For an eval result, ask the same of the trials: did every run do the task, does the gap hold across trials and models, and does the scenario matter.
…
The line at the top of this page pins the label git:20261013.9e6954c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (1663 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
GitHub
nightly-labs/openbot · 5,267 stars · license a license file GitHub does not identify · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7exkuzxmiqbayxmx
GET https://markdownregistry.com/api/v1/resolve?ref=nightly-labs/openbot/principle-explain-the-number
GET https://markdownregistry.com/api/v1/blob/cd5a25f9e7cf023627ccb470dc5faa97542f29b4319496a32b839a8e1e988047
Your AI assistant 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.
nightly-labs/openbot · .agents/skills/babysit/SKILL.md · Babysit a pull request through the NorbiAI review loop until no valid issue remains. Fix valid findings, rebut false…
nightly-labs/openbot · .agents/skills/biome-anti-slop/SKILL.md · Install and configure vendored Biome anti-slop GritQL rules in a local TypeScript or JavaScript repository. Use when a…
nightly-labs/openbot · .agents/skills/prototype/SKILL.md · Build several different design directions (3 by default) for a feature or issue as Storybook stories, show them to the…
nightly-labs/openbot · .agents/skills/release-upgrade-safety/SKILL.md · Audit a pending OpenBot release for upgrade and data-loss hazards before the version is bumped or tagged. Use when…
nightly-labs/openbot · .agents/skills/ship/SKILL.md · Ship the current branch to main. Review the diff, fix findings, open the pull request, babysit the NorbiAI review and…
nightly-labs/openbot · .agents/skills/signal-deploy/SKILL.md · Check and deploy Signal (the `remote-api` service in `remote/`) to production from a release tag. Use when asked to…
nightly-labs/openbot · .agents/skills/smoke-and-ship/SKILL.md · Smoke test the current branch, then ship it to main only when all smoke items pass. Use when the user asks to smoke and…
nightly-labs/openbot · .agents/skills/smoke/SKILL.md · Start one or more local OpenBot dev instances and smoke test the features that the current changes or a pull request…
nightly-labs/openbot · .agents/skills/triage/SKILL.md · Triage one GitHub issue or bug report. Decide if it is valid, find the root cause, and fix it. Push back with evidence…
nightly-labs/openbot · .agents/skills/zaidan/SKILL.md · Install and configure the Zaidan component registry in an existing SolidJS codebase, and recommend Zaidan components…
cursor/plugins · harness/pstack/claude-code/skills/principle-explain-the-number/SKILL.md · Apply before you measure, and before you trust, report, or act on a number you measured: a speedup, a regression, a…
cursor/plugins · pstack/skills/principle-explain-the-number/SKILL.md · Apply before you measure, and before you trust, report, or act on a number you measured: a speedup, a regression, a…
michael-denyer/pstack-claude · plugins/pstack/skills/principle-explain-the-number/SKILL.md · Apply before you measure, and before you trust, report, or act on a number you measured: a speedup, a regression, a…
backnotprop/pstack · skills/principle-explain-the-number/SKILL.md · Apply before you measure, and before you trust, report, or act on a number you measured: a speedup, a regression, a…
theonlyfusioncube/potetos-for-everyone · skills/principle-explain-the-number/SKILL.md · Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or…
creedants/pstack-t3 · skills/principle-explain-the-number/SKILL.md · Apply before you measure, and before you trust, report, or act on a number you measured: a speedup, a regression, a…
arjitj2/open-pstack · plugins/pstack/skills/principle-explain-the-number/SKILL.md · Apply before you measure, and before you trust, report, or act on a number you measured: a speedup, a regression, a…
painhardcore/pstack · .opencode/skills/principle-explain-the-number/SKILL.md · Apply before you measure, and before you trust, report, or act on a number you measured: a speedup, a regression, a…
