evidence-discipline SKILL.md skillA
evidence-discipline from rikvanriel/code-hygiene is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add rikvanriel/code-hygiene/evidence-discipline@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- rikvanriel/code-hygiene
- Path
skills/evidence-discipline/SKILL.md- Versions recorded
- 3
- Latest version
- v1.0.0, committed Oct 16, 2026
- First version recorded
- Sep 27, 2026
- Size
- 11,568 bytes
- Repository stars
- 2
- License
- MIT
Use when measuring, benchmarking, or validating anything — proves the instrument, the sample, and the artifact.
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
# Evidence Discipline Capability: turns a number into a defensible one — the instrument is validated, the sample is representative, the conditions are stated, and the artifact you deliver is the artifact you verified. A number that fails any of these is not evidence, it is an impression. Companion to `factual-integrity`: that skill forbids inventing a value; this one says what makes a measured value trustworthy enough to report. ## Trigger Any time you measure, benchmark, profile, sample, or compare: performance work, tuning a threshold, validating a fix, reporting a metric in a changelog or PR description. ## Rules ### GC-60 — Validate the instrument before trusting its numbers Calibrate the metric against a signal whose ground truth you control (a known input, a synthetic case with a known answer, two independent measurements of one quantity). An unvalidated metric manufactures confident wrong answers: it can be wrong in sign, scale, or ordering and still look plausible. Say in the report how the instrument was validated; if it was not, say that too. ### GC-61 — A metric must be able to fail, and you must say where …
Read the whole file at its exact version.
How to install
mdr add rikvanriel/code-hygiene/evidence-discipline@sha256:434e651912c254f6The line at the top of this page pins the label v1.0.0, 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.
[](https://markdownregistry.com/a/art_bxns533avmtvnift)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Sep 27, 2026 and Oct 16, 2026, about one every 10 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-10-16 | 8a0e8f9 | 11,568 B | A | view · diff |
| v1.0.0 | 2026-10-16 | db7078a | 9,740 B | A | view · diff |
| v1.0.0 | 2026-09-27 | 6332860 | 8,948 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 (11568 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
rikvanriel/code-hygiene · 2 stars · license MIT · pushed 2026-10-16 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_bxns533avmtvnift GET https://markdownregistry.com/api/v1/resolve?ref=rikvanriel/code-hygiene/evidence-discipline GET https://markdownregistry.com/api/v1/blob/434e651912c254f61ddac7eab96746a3d1a14ad20f9ac245c18f458c6f0e4641
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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.