A command that gathers several copywriting personas to discuss a strategic decision and produce a shared recommendation.

Use it to compare options, review a difficult production decision, detect repeated failures, or inspect the history of earlier decisions.

It provides multiple viewpoints when a team is stuck or when one decision needs broader review.

conclave — Command for Claude Code by lckx777

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/lckx777/copy-chief-black

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/lckx777/copy-chief-black/conclave.svg)](https://agentmods.dev/commands/lckx777/copy-chief-black/conclave)

Your own site

<a href="https://agentmods.dev/commands/lckx777/copy-chief-black/conclave"><img src="https://agentmods.dev/badge/commands/lckx777/copy-chief-black/conclave.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 506 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00506
Opus 5	$0.00000	$0.00253
Sonnet 5	$0.00000	$0.00101
Haiku 4.5	$0.00000	$0.00051

Measured 8d ago against content hash 92f6b98d1c81, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

conclave scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

framework/commands/conclave.md · 56 lines

What it actually says

/conclave — Multi-Persona Deliberation

Convoke a Conclave of Copy Squad personas to deliberate on a strategic decision.

Usage

/conclave "MUP Selection" --members atlas,hawk,vox --context "3 MUP candidates for florayla"
/conclave --check-stuck <offer>     # detect if stuck and recommend Conclave
/conclave --history                 # show past Conclave decisions

Steps

Parse arguments:
- Topic: first quoted string or first argument
- Members: --members comma-separated list (atlas, hawk, vox, blade, scout, forge, echo, cipher, helix)
- Context: --context string with relevant data
- If --check-stuck: detect production stuck loops
If --check-stuck:
```
bun run ~/copywriting-ecosystem/scripts/conclave.ts --check-stuck $ARGUMENTS
```
- Scan production/ files for scores below threshold
- If 2+ failures → recommend Conclave with topic and members

If --history:

bun run ~/copywriting-ecosystem/scripts/conclave.ts --history

Normal Conclave flow: a. Validate required members per decision type (ref: ~/.claude/rules/conclave.md) b. Generate structured Conclave prompt:
- Topic + Context
- Each member's perspective (loaded from ~/.claude/agents/{persona}/)
- Position statement template (200 tokens max each) c. Execute Conclave protocol:
- Phase 1: Present topic to all members
- Phase 2: Each persona states position independently
- Phase 3: Cross-examination (max 2 rounds)
- Phase 4: Vote (AGREE/DISAGREE/ABSTAIN)
- Phase 5: Record decision d. If unanimous → activate Devil's Advocate (S35.6) e. Record to .conclave-history.yaml f. If appropriate, follow up with MCP zen consensus for external validation
Display result:
- Decision summary
- Vote breakdown
- Dissenting opinions preserved
- Next action recommendation

Ref: ~/.claude/rules/conclave.md for full protocol Sprint: S35 — Conclave Architecture

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 56 lines · 0 tokens per session scan A 92f6b98d1c81

Subscribe to this mod's changes

conclave is a command published in the GitHub repository lckx777/copy-chief-black (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 506 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Marketing and SEO

conclave

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/conclave — Multi-Persona Deliberation

Usage

Steps

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

converge

implement

analyze