advisor-model SKILL.md skillA

advisor-model from cdeust/zetetic-team-subagents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add cdeust/zetetic-team-subagents/advisor-model@git:20260917.7575105

Pins git:20260917.7575105 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
cdeust/zetetic-team-subagents
Path
plugins/zetetic-loop/skills/advisor-model/SKILL.md
Versions recorded
1
Latest version
git:20260917.7575105, committed Sep 17, 2026
Size
7,623 bytes
Repository stars
8
License
MIT

Consult a separate model at a selected plan, fork, or completion decision while the current model retains execution ownership; use supplied context only, keep the consultation read-only, and never treat advice as a goal check.

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

# Advisor Model

## Purpose

The advisor is a second model consulted at a selected decision point. The current model
remains the executor: it owns the task, edits, commands, goal ledger, and final decision.
Advice is evidence to consider, not an approval gate. The executor may reject it when the
repository, command output, or other supplied evidence contradicts the recommendation.

This skill is standalone. A goal file is useful context when one exists, but it is not
required.

When persisted with a goal, use an optional `## Advisor` section after the budget:

```markdown
## Advisor
enabled: true | false
required: false | true
backend: native | delegated | unavailable
model: host-default | <configured model>
consultations:
- id: <stable id>
  mode: plan-review | decision-fork | completion-check
  status: pending | accepted | rejected | opaque | declined | unavailable
  plan_revision: <revision or null>
  request: <why this consultation was selected>
  evidence_refs: <paths, outputs, or transcript references supplied>
  response: <recorded response or opaque>
  disposition: accepted | rejected | unresolved
  accounting: <host-reported cumulative usage or unavailable>
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add cdeust/zetetic-team-subagents/advisor-model@sha256:1ee8442f54a51275

The line at the top of this page pins the label git:20260917.7575105, 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_l77fq74rz5e4cdis.svg)](https://markdownregistry.com/a/art_l77fq74rz5e4cdis)

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

Versions

The registry has recorded 1 version of this file, committed on Sep 17, 2026.

versioncommittedcommitsizeaudit
git:20260917.7575105 latest2026-09-17 7575105 7,623 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 (7623 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

cdeust/zetetic-team-subagents · 8 stars · license MIT · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_l77fq74rz5e4cdis
GET https://markdownregistry.com/api/v1/resolve?ref=cdeust/zetetic-team-subagents/advisor-model
GET https://markdownregistry.com/api/v1/blob/1ee8442f54a512759f08707dd708da664b57a9ab30cbd0276883924fe6fd1057

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 cdeust/zetetic-team-subagents

AGENTS.md AGENTS.md file
cdeust/zetetic-team-subagents · AGENTS.md
git:20260917.288eff7 · audit A · 8 stars
CLAUDE.md CLAUDE.md file
cdeust/zetetic-team-subagents · CLAUDE.md
git:20260908.ede89b5 · audit A · 8 stars
design SKILL.md skill
cdeust/zetetic-team-subagents · plugins/zetetic-design/skills/design/SKILL.md · UX/UI design and accessibility audit -- name the user, task, and success criterion before any layout decision, enforce…
git:20260906.2f7c802 · audit A · 8 stars
goal SKILL.md skill
cdeust/zetetic-team-subagents · plugins/zetetic-loop/skills/goal/SKILL.md · Compile a long-running objective into a persistent, host-neutral goal contract: one measurable end state, non-goals…
git:20260917.db5f697 · audit A · 8 stars
plan SKILL.md skill
cdeust/zetetic-team-subagents · plugins/zetetic-loop/skills/plan/SKILL.md · Turn an active goal contract into an ordered plan where every step carries its own check, then verify the plan against…
git:20260917.db5f697 · audit A · 8 stars
refine-goal SKILL.md skill
cdeust/zetetic-team-subagents · plugins/zetetic-loop/skills/refine-goal/SKILL.md · After a verify-goal run, turn the ledger into the next iteration: tighten criteria that passed by accident, add the…
git:20260917.db5f697 · audit A · 8 stars
verify-goal SKILL.md skill
cdeust/zetetic-team-subagents · plugins/zetetic-loop/skills/verify-goal/SKILL.md · Run every acceptance criterion of a goal file as an external check, record the command, its exit code and an output…
git:20260917.db5f697 · audit A · 8 stars
evidence-synthesis SKILL.md skill
cdeust/zetetic-team-subagents · plugins/zetetic-reasoning/skills/evidence-synthesis/SKILL.md · Synthesize multiple papers, benchmarks, interviews, reviews, or other sources into a defensible and qualified…
git:20260802.d219d53 · audit A · 8 stars
boundary-design SKILL.md skill
cdeust/zetetic-team-subagents · skills/boundary-design/SKILL.md · Draw the line where it costs least. Use for build-vs-buy calls, "where does this module/team/service boundary belong?"…
git:20261021.4372ea9 · audit A · 8 stars
causal-audit SKILL.md skill
cdeust/zetetic-team-subagents · skills/causal-audit/SKILL.md · Correlation walked in; make it prove causation. Use when someone claims "X causes Y" from observational data, asks "did…
git:20261021.4372ea9 · audit A · 8 stars
decision-bias-check SKILL.md skill
cdeust/zetetic-team-subagents · skills/decision-bias-check/SKILL.md · Audit the decision before it ships. Use for "are we sure about this?", high-stakes choices made on fast intuition…
git:20261021.4372ea9 · audit A · 8 stars
estimation SKILL.md skill
cdeust/zetetic-team-subagents · skills/estimation/SKILL.md · Bound it before you build it. Use when a decision is blocked by "we don't have data", an estimate looks suspiciously…
git:20261021.4372ea9 · audit A · 8 stars

Every file in cdeust/zetetic-team-subagents

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