consilium SKILL.md skillA
consilium from arcanada-one/datarim is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add arcanada-one/datarim/consilium@git:20261004.9edafd3Pins git:20261004.9edafd3 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- arcanada-one/datarim
- Path
skills/consilium/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261004.9edafd3, committed Oct 4, 2026
- First version recorded
- Oct 4, 2026
- Size
- 10,815 bytes
- Repository stars
- 16
- License
- MIT
Assemble a panel of Datarim agents for multi-perspective analysis of decisions. Use for /dr-design stage (L3-4) or critical decisions in /dr-plan.
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
**Delegated language context:** Resolve replies/artifacts through `${DATARIM_RUNTIME:?}/skills/datarim-system/language-preferences.md` before dispatch. Pass both validated tags explicitly in the child prompt and via `DATARIM_REPLY_LANG` / `DATARIM_ARTIFACT_LANG` for child processes. Machine-only protocols retain their exact syntax.
# Consilium — Multi-Agent Panel Discussions
## What is Consilium
Consilium is a structured council of Datarim agents debating a decision. Instead of a single perspective, the agent simulates multiple specialized viewpoints — architect, security analyst, SRE, strategist — to surface conflicts, blind spots, and tradeoffs before committing to a path.
Use Consilium for:
- Architecture decisions with lasting impact
- Trade-off analysis where no obvious "right answer" exists
- Production readiness assessments
- New feature evaluation at L3-4 complexity
**Do NOT use Consilium for:** L1-2 tasks, simple bug fixes, or questions with clear answers. Over-consilium wastes time.
---
## Pipeline
```
SCOPE → ASSEMBLE → ANALYZE → DEBATE → CONVERGE → DELIVER
```
---
## Step 1: SCOPE
Define the question clearly before assembling the panel.
**Required:**
…Read the whole file at its exact version.
How to install
mdr add arcanada-one/datarim/consilium@sha256:e345ddff0cbaf10eThe line at the top of this page pins the label git:20261004.9edafd3, 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_k5a63gxazqlrpfhs)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Oct 4, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261004.9edafd3 latest | 2026-10-04 | 9edafd3 | 10,815 B | A | view · diff |
| git:20261004.8dfccd1 | 2026-10-04 | 8dfccd1 | 10,479 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 (10815 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
arcanada-one/datarim · 16 stars · license MIT · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_k5a63gxazqlrpfhs GET https://markdownregistry.com/api/v1/resolve?ref=arcanada-one/datarim/consilium GET https://markdownregistry.com/api/v1/blob/e345ddff0cbaf10ea7e3641f1d35347df9726b13bed0696e859206e8e2901019
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.