cad-decision-review SKILL.md skillA

cad-decision-review from crenshawdev/cadence is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add crenshawdev/cadence/cad-decision-review@git:20261029.0ae5ff0

Pins git:20261029.0ae5ff0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
crenshawdev/cadence
Path
skills/cad-decision-review/SKILL.md
Versions recorded
6
Latest version
git:20261029.0ae5ff0, committed Oct 29, 2026
First version recorded
Jul 23, 2026
Size
2,734 bytes
Repository stars
8
License
MIT

Adversarial refute-then-adjudicate pass over one load-bearing decision - a CONTEXT D-NN line or a PROJECT Key Decisions row - with per-objection rulings.

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

<objective>
Stress-test ONE decision the user names, rather than take it on faith. The
review capability lives entirely in cadence-core/workflows/decision-review.md:
`cad-reviewer` (and, when configured, a cross-model provider) refutes the
decision through the review subsystem's reviewer resolution; the main model
then grounds each objection against documentation (library/API claims:
Context7 when its tools are available, else the installed source, lockfile
or vendored docs, with any claim none could check listed as unchecked) and
the real codebase (factual claims) and rules it `survives | partial | refuted`
with a concrete amendment where the decision needs one. When refutation
returns nothing, the grounding retargets onto the decision's own load-bearing
claims rather than lapsing, so a clean pass still rests on checked facts.

This is a manual, on-demand entry point only - it never auto-fires and there
is no review-trigger wiring for it. Durability (cad-context's `## Durable
decisions` filter) names candidates worth this deeper pass; picking one and
invoking this skill is the user's call, not a mechanical handoff.
</objective>

<execution_context>
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add crenshawdev/cadence/cad-decision-review@sha256:64205477fb156f90

The line at the top of this page pins the label git:20261029.0ae5ff0, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_it2qsyvx5tunj6bz.svg)](https://markdownregistry.com/a/art_it2qsyvx5tunj6bz)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 6 versions of this file, between Jul 23, 2026 and Oct 29, 2026, about one every 20 days.

versioncommittedcommitsizeaudit
git:20261029.0ae5ff0 latest2026-10-29 0ae5ff0 2,734 BA view · diff
git:20261005.9328cf82026-10-05 9328cf8 2,743 BA view · diff
git:20260805.6a634452026-08-05 6a63445 2,483 BA view · diff
git:20260730.8c99cd62026-07-30 8c99cd6 2,603 BA view · diff
git:20260727.71d30ce2026-07-27 71d30ce 2,448 BA view · diff
git:20260723.a046be62026-07-23 a046be6 2,192 BA view

Audit of the latest version

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 (2734 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

crenshawdev/cadence · 8 stars · license MIT · pushed 2026-11-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_it2qsyvx5tunj6bz
GET https://markdownregistry.com/api/v1/resolve?ref=crenshawdev/cadence/cad-decision-review
GET https://markdownregistry.com/api/v1/blob/64205477fb156f90243fa5ded079af601d393de3c2051fe1f66e815c1bc0c848

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.

More from crenshawdev/cadence

DESIGN.md DESIGN.md file
crenshawdev/cadence · DESIGN.md
git:20261030.096ea8a · audit A · 8 stars
cad-adopt SKILL.md skill
crenshawdev/cadence · skills/cad-adopt/SKILL.md · Initialize .planning/ from a repo that already exists - PROJECT.md, REQUIREMENTS.md and a remaining-work ROADMAP.md…
git:20261029.0ae5ff0 · audit A · 8 stars
cad-assumptions-analyzer-contract SKILL.md skill
crenshawdev/cadence · skills/cad-assumptions-analyzer-contract/SKILL.md · Role contract preloaded at spawn by the cad-assumptions-analyzer, cad-assumptions-analyzer-low…
git:20261028.dd1f3d4 · audit A · 8 stars
cad-audit SKILL.md skill
crenshawdev/cadence · skills/cad-audit/SKILL.md · Pre-ship traceability audit - every requirement traced to a phase, plan and verification, orphan detection both…
git:20261029.0ae5ff0 · audit A · 8 stars
cad-capture SKILL.md skill
crenshawdev/cadence · skills/cad-capture/SKILL.md · Capture a phase-linked todo, a seed idea for a future milestone, or a note, without losing your place -…
git:20261029.0ae5ff0 · audit A · 8 stars
cad-config SKILL.md skill
crenshawdev/cadence · skills/cad-config/SKILL.md · Configure Cadence's config.json - workflow toggles, the per-role model and effort interview, and interactive…
git:20261103.88a7eae · audit A · 8 stars
cad-context SKILL.md skill
crenshawdev/cadence · skills/cad-context/SKILL.md · Gather phase context before planning - codebase assumptions, locked decisions, falsifiable acceptance criteria - in one…
git:20261029.0ae5ff0 · audit A · 8 stars
cad-coverage SKILL.md skill
crenshawdev/cadence · skills/cad-coverage/SKILL.md · Find a completed phase's requirements with no failing-capable test coverage and generate tests to close the gaps, in…
git:20261103.1c9f757 · audit A · 8 stars
cad-debug SKILL.md skill
crenshawdev/cadence · skills/cad-debug/SKILL.md · Systematic debugging - hypothesis and symptom tracked in a state file that survives /clear, with a user-gated…
git:20261029.0ae5ff0 · audit A · 8 stars
cad-docs-verify SKILL.md skill
crenshawdev/cadence · skills/cad-docs-verify/SKILL.md · Verify docs claims against the live codebase - paths, commands, symbols, config keys - each reported accurate, stale or…
git:20261029.0ae5ff0 · audit A · 8 stars
cad-execute SKILL.md skill
crenshawdev/cadence · skills/cad-execute/SKILL.md · Execute a phase's plans - a subagent per plan, an atomic commit per task, a slim per-phase SUMMARY
git:20261029.0ae5ff0 · audit A · 8 stars
cad-executor-contract SKILL.md skill
crenshawdev/cadence · skills/cad-executor-contract/SKILL.md · Role contract preloaded at spawn by the cad-executor, cad-executor-low, cad-executor-medium, cad-executor-xhigh and…
git:20261103.4869f23 · audit A · 8 stars

Every file in crenshawdev/cadence

Browse by kind, by grade A, or by owner.