AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Council

skill-yogirk-agent-council-claude-code · by yogirk

|

No reviews yet
0 installs
50 views
0.0% view→install

Install

$ agentstack add skill-yogirk-agent-council-claude-code

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-yogirk-agent-council-claude-code)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
5mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Council? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Agent Council

Convene a multi-agent council to deliberate on a question. You (Claude) are the chairman. Other CLI agents (Codex, Gemini) provide independent opinions. You synthesize the final verdict.

Usage

The user invokes /council "their question" or /council --with-review "their question".

Step 1: Dispatch the council

Run this bash block. Replace {QUESTION} with the user's actual question text.

COUNCIL_BIN=""; for _d in "$HOME/.claude/skills/agent-council" "$HOME/.agents/skills/agent-council" "$HOME/.gemini/skills/agent-council" "$(git rev-parse --show-toplevel 2>/dev/null)"; do [ -x "$_d/bin/council" ] && COUNCIL_BIN="$_d/bin/council" && break; [ -x "$_d/council" ] && COUNCIL_BIN="$_d/council" && break; done; [ -z "$COUNCIL_BIN" ] && COUNCIL_BIN="$(which council 2>/dev/null || echo "bin/council")"
QUESTION_FILE=$(mktemp /tmp/council-q-XXXXXX)
cat  "$QUESTION_FILE"
{QUESTION}
COUNCIL_EOF
SLUG=$(basename "$(git rev-parse --show-toplevel 2>/dev/null || pwd)")
SESSION_DIR=$($COUNCIL_BIN --question-file "$QUESTION_FILE" --project "$SLUG")
rm -f "$QUESTION_FILE"
echo "SESSION_DIR=$SESSION_DIR"

If the user passed --with-review, add that flag to the council command. If the user passed --quick, add that flag instead.

Step 2: Read the council opinions

After the bash block completes, read the opinion files from the session directory:

  1. Read $SESSION_DIR/meta.json to understand the session structure
  2. Read each file in $SESSION_DIR/stage1/ (opinioncodex.json, opiniongemini.json, etc.)
  3. If --with-review was used, also read files in $SESSION_DIR/stage2/

Step 3: Synthesize as chairman

You are the chairman. You have the full conversation context with the user PLUS the council opinions. Produce the synthesis:

  • Consensus: Where all agents agree
  • Divergence: Where agents disagree. State each position fairly with agent name.
  • Recommendation: Your synthesized answer drawing from the strongest elements.
  • Confidence:
  • If all agree: HIGH — Strong consensus across models.
  • If majority agrees: MEDIUM — Majority view with notable dissent.
  • If fundamental disagreement: LOW — Agents fundamentally disagree.

For each agent, state: Agent name (their confidence): their position. End with: "This is a decision you should make yourself, not delegate to the council."

Step 4: Save synthesis

Write your synthesis to $SESSION_DIR/synthesis.json:

{
  "chairman": "claude",
  "consensus": "...",
  "divergence": "...",
  "recommendation": "...",
  "confidence": "high|medium|low",
  "timestamp": "ISO 8601"
}

Step 5: Regenerate the viewer

After writing synthesis.json, regenerate the viewer so it includes your verdict:

$COUNCIL_BIN regenerate-viewer "$(basename "$SESSION_DIR")" --project "$SLUG"

Step 6: Offer the viewer and next steps

Tell the user:

> Council viewer saved to: $SESSION_DIR/viewer.html — open in browser to explore the full deliberation. > > Next steps: > - Re-evaluate later with current context: /council-revisit {SESSION_ID} > - Record how this decision played out: /council-outcome {SESSION_ID} "what happened" > - Browse past sessions: /council-list

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.