design-decisions SKILL.md skillA

design-decisions from cercano-ai/cercano is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add cercano-ai/cercano/design-decisions@git:20260709.887cd3f

Pins git:20260709.887cd3f in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
cercano-ai/cercano
Path
.claude/skills/design-decisions/SKILL.md
Versions recorded
1
Latest version
git:20260709.887cd3f, committed Jul 9, 2026
Size
3,924 bytes
Repository stars
11
License
Apache-2.0

Stop and weigh real options before coding a structural decision.

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

# Design Decision Protocol

## When This Applies

Any time there are multiple viable implementation approaches — data modeling, encoding choices, interface changes, module boundaries, state machine structure, anything structural. If you can think of more than one way to do it, this protocol is mandatory.

## The Rule

**STOP. Do not write code.** Present options to the human first.

## Steps

1. **Identify the decision point.** State what needs to be decided and why.

2. **Enumerate at least 2–3 real options.** Not strawmen. Each must be a genuinely viable approach.

3. **For each option, quantify these four dimensions:**

   - **Cost/complexity**: lines of code, files touched, new dependencies introduced, test surface added. Be specific — "~50 new lines across 3 files" not "small." (Hardware analog: gates, registers, mm².)
   - **Risk**: what can go wrong? Is the failure silent (wrong output) or loud (crash/hang)? What testing catches it? How hard is it to debug if it breaks?
   - **Reward/outcome**: what does this solve? Does it unlock future work? Does it close off future options?
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add cercano-ai/cercano/design-decisions@sha256:c617ee7167ade0ec

The line at the top of this page pins the label git:20260709.887cd3f, 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_7egba4i6ldwimmfd.svg)](https://markdownregistry.com/a/art_7egba4i6ldwimmfd)

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

Versions

The registry has recorded 1 version of this file, committed on Jul 9, 2026.

versioncommittedcommitsizeaudit
git:20260709.887cd3f latest2026-07-09 887cd3f 3,924 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 (3924 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

cercano-ai/cercano · 11 stars · license Apache-2.0 · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7egba4i6ldwimmfd
GET https://markdownregistry.com/api/v1/resolve?ref=cercano-ai/cercano/design-decisions
GET https://markdownregistry.com/api/v1/blob/c617ee7167ade0ec946b8a867a738684f5953397d13af1fd198cb30be21772d3

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 cercano-ai/cercano

cercano-classify SKILL.md skill
cercano-ai/cercano · .agents/skills/cercano-classify/SKILL.md · Classify or triage text using the configured model route via Cercano. Returns a category, confidence level, and brief…
git:20261023.295d5be · audit A · 11 stars
cercano-config SKILL.md skill
cercano-ai/cercano · .agents/skills/cercano-config/SKILL.md · Query or update Cercano's runtime configuration without restarting the server. Use action 'get' to list available local…
git:20261023.295d5be · audit A · 11 stars
cercano-deep-research SKILL.md skill
cercano-ai/cercano · .agents/skills/cercano-deep-research/SKILL.md · Deep multi-source research tool that identifies authoritative sources, systematically searches, analyzes and ranks…
git:20261023.295d5be · audit A · 11 stars
cercano-document SKILL.md skill
cercano-ai/cercano · .agents/skills/cercano-document/SKILL.md · Generate doc comments for exported Go symbols using routed AI and write them directly to the file. Cercano handles the…
git:20261023.295d5be · audit A · 11 stars
cercano-explain SKILL.md skill
cercano-ai/cercano · .agents/skills/cercano-explain/SKILL.md · Explain code or text using the configured model route via Cercano. Returns a clear explanation of what the code does…
git:20261023.295d5be · audit A · 11 stars
cercano-extract SKILL.md skill
cercano-ai/cercano · .agents/skills/cercano-extract/SKILL.md · Extract specific information from text using the configured model route via Cercano. Returns only the relevant sections…
git:20261023.295d5be · audit A · 11 stars
cercano-fetch SKILL.md skill
cercano-ai/cercano · .agents/skills/cercano-fetch/SKILL.md · Fetch a URL and extract readable text content locally. Returns full extracted text (not a summary) — HTML is stripped…
git:20260325.82b3c64 · audit A · 11 stars
cercano-init SKILL.md skill
cercano-ai/cercano · .agents/skills/cercano-init/SKILL.md · Initialize Cercano for a project by scanning the repo and building a context file. Makes all Cercano tools…
git:20261023.295d5be · audit A · 11 stars
cercano-local SKILL.md skill
cercano-ai/cercano · .agents/skills/cercano-local/SKILL.md · Run prompts through Cercano with configured routing. Handles chat-style queries and code generation with validation…
git:20261023.295d5be · audit A · 11 stars
cercano-models SKILL.md skill
cercano-ai/cercano · .agents/skills/cercano-models/SKILL.md · List AI models available on the active local runtime configured in Cercano. Returns model names, sizes, and…
git:20261023.295d5be · audit A · 11 stars
cercano-research SKILL.md skill
cercano-ai/cercano · .agents/skills/cercano-research/SKILL.md · Research a question using DuckDuckGo search and routed AI analysis. Crafts search queries, fetches top results, and…
git:20261023.295d5be · audit A · 11 stars
cercano-stats SKILL.md skill
cercano-ai/cercano · .agents/skills/cercano-stats/SKILL.md · View Cercano usage statistics and cloud token savings. Shows total requests, tokens processed locally, cloud tokens…
git:20260325.82b3c64 · audit A · 11 stars

Every file in cercano-ai/cercano

Other files named design-decisions

design-decisions SKILL.md skill
cercano-ai/cercano · .agents/skills/design-decisions/SKILL.md · Stop and weigh real options before coding a structural decision.
git:20260709.887cd3f · audit A · 11 stars

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