Agent Council Nudge logo

Agent Council Nudge

Community
yogirk
agent-council-nudge

Ambient awareness for Agent Council. Detects moments where convening a multi-model council would genuinely help and suggests the right command. Never interrupts. Never nags. Just a quiet tip at the right moment.

Overview

Publisheryogirk
Repositoryagent-council
Skill nameagent-council-nudge
Stars
92
Forks
22
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by yogirk on GitHub. Read the source before you install it.

Installation

Install the Agent Council Nudge AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/yogirk/agent-council/tree/main/skills/claude-code/agent-council-nudge
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/yogirk/agent-council.git /tmp/agent-council
mkdir -p .claude/skills
cp -r /tmp/agent-council/skills/claude-code/agent-council-nudge .claude/skills/agent-council-nudge
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Agent Council Nudge in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Agent Council Nudge on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Agent Council Nudge is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Preamble

bash
# Read proactive config from ~/.council/config.json
_COUNCIL_PROACTIVE="true"
if [ -f "$HOME/.council/config.json" ]; then
  _CP=$(cat "$HOME/.council/config.json" 2>/dev/null | grep -o '"proactive"[[:space:]]*:[[:space:]]*[a-z]*' | grep -o 'true\|false')
  [ -n "$_CP" ] && _COUNCIL_PROACTIVE="$_CP"
fi
echo "COUNCIL_PROACTIVE: $_COUNCIL_PROACTIVE"

# Check for stale sessions (>7 days, no outcome recorded)
_STALE_SESSION="none"
_STALE_DAYS=""
if [ -d "$HOME/.council" ]; then
  for _meta in $(find "$HOME/.council" -name "meta.json" -mtime +7 2>/dev/null | head -5); do
    if ! grep -q '"outcome"' "$_meta" 2>/dev/null; then
      _STALE_SESSION=$(basename "$(dirname "$_meta")")
      _STALE_DAYS=$(( ( $(date +%s) - $(date -r "$_meta" +%s) ) / 86400 ))
      break
    fi
  done
fi
echo "STALE_SESSION: $_STALE_SESSION"
[ "$_STALE_SESSION" != "none" ] && echo "STALE_DAYS: $_STALE_DAYS"

# Session nudge counter (max 2 per session)
_NUDGE_FILE="/tmp/council-nudges-$$"
_NUDGE_COUNT=$(cat "$_NUDGE_FILE" 2>/dev/null || echo "0")
echo "NUDGE_COUNT: $_NUDGE_COUNT"

Nudge Behavior

If COUNCIL_PROACTIVE is "false": do nothing. Do not suggest any council commands. The user opted out.

If COUNCIL_PROACTIVE is "true" AND NUDGE_COUNT is less than 2:

You may suggest council commands at natural pause points in the conversation. The suggestion goes AFTER your full response, as a single quiet line. Never as a question. Never as the main content. Never mid-thought.

When to suggest /council

If the user's message matches ANY of these patterns:

  • Explicit comparison: "should we use X or Y", "X vs Y", "which approach"
  • Trade-off language: "trade-off", "pros and cons", "compare options"
  • Architecture decisions: "how should we structure", "what pattern", "which database"
  • Decision paralysis: "I'm not sure", "I'm torn", "what do you think about" + technical topic
  • Multiple competing options being weighed

Suggest: Tip: Looks like a decision with trade-offs. /council gets 3 independent AI perspectives on this.

Do NOT suggest /council for:

  • Simple factual questions ("what does this function do?")
  • Bug fixes with a clear solution
  • Code generation requests ("write a function that...")
  • Questions you can answer confidently without diverse perspectives

When to suggest /council-revisit

If the user's message matches ANY of these:

  • References a past decision: "remember when we chose", "we decided to use X"
  • Reconsideration language: "should we reconsider", "rethink", "revisit", "was that the right call"
  • Discussing code that was the subject of a past council (if you happen to know)

Suggest: Tip: You may have a past council session on this topic. /council-list to check, then /council-revisit to compare with fresh eyes.

When to suggest /council-outcome

If STALE_SESSION is not "none":

  • After the user mentions shipping, deploying, merging, or completing work
  • At natural retrospective moments ("that went well", "we should have done X")
  • When discussing results of a past decision

Suggest: Tip: Council session {STALE_SESSION} is {STALE_DAYS} days old with no outcome recorded. /council-outcome {STALE_SESSION} "what happened" to track how the decision played out.

After nudging

Increment the counter so you don't exceed 2 per session:

bash
echo "$(( _NUDGE_COUNT + 1 ))" > /tmp/council-nudges-$$

Hard rules

  • Max 2 nudges per session. After 2, stop entirely. No exceptions.
  • Never nudge for /council-list or /council-replay. Users discover these naturally.
  • Never nudge twice for the same command type in one session.
  • If the user says "stop suggesting", "don't nudge me", or shows any irritation: stop for the rest of the session. Do not apologize profusely, just stop.
  • Never make the nudge a question. It's a statement. "Tip: ..." not "Would you like to...?"
  • Never nudge when the user is in the middle of a task. Wait for a natural completion point.

Frequently asked questions

What does the Agent Council Nudge AI skill do?

Ambient awareness for Agent Council. Detects moments where convening a multi-model council would genuinely help and suggests the right command. Never interrupts. Never nags. Just a quiet tip at the right moment.

Why use Agent Council Nudge on TypingMind?

Because you install it once and use it with any model. Agent Council Nudge is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Agent Council Nudge in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yogirk/agent-council/tree/main/skills/claude-code/agent-council-nudge. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Agent Council Nudge?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Agent Council Nudge?

As many as you like. As long as a model supports skills, you can use Agent Council Nudge with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Agent Council Nudge AI skill free?

Yes. It is published on GitHub by yogirk under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇