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.
npx agentmods add commands/florini/florians-claude-code-kit/dialogue-convenegit clone --depth 1 https://github.com/FlorinI/Florians-Claude-Code-KitWrote 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.
[](https://agentmods.dev/commands/florini/florians-claude-code-kit/dialogue-convene)<a href="https://agentmods.dev/commands/florini/florians-claude-code-kit/dialogue-convene"><img src="https://agentmods.dev/badge/commands/florini/florians-claude-code-kit/dialogue-convene.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00049 | $0.01499 |
| Opus 5 | $0.00024 | $0.00749 |
| Sonnet 5 | $0.00010 | $0.00300 |
| Haiku 4.5 | $0.00005 | $0.00150 |
Grade A, and why
dialogue-convene 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dialogue-convene — start a two-party written dialogue
Convene a two-party dialogue: this session and one other agent discuss a topic in writing, in a shared append-only file, self-driving to consensus (or a deliberate hand-back to you) with no human relaying messages. The other party can be another Claude Code session or any other agentic tool (Cursor, etc.) — the launch prompt you emit assumes it has none of Claude Code's skills, memory, or conventions and spells out everything it needs.
The rules both parties follow live in the protocol doc; this skill creates the per-use dialogue file, emits the other party's launch prompt, and then plays Party A in this very session.
Protocol doc (canonical rules): ~/.claude/dialogue-protocol.md — resolve ~ via $env:USERPROFILE (Windows) or $HOME. Read it before Step 4; you don't need to copy it.
Step 1 — gather the blanks
From $ARGUMENTS if given, else ask the user (a single AskUserQuestion with free text is fine). Collect:
- TOPIC — what the two parties discuss (one or two sentences).
- PARTIES — two labels. This session is Party A (it opens, Turn 1); the other agent is Party B. Validate: distinct, non-overlapping (neither a substring of the other),
[A-Za-z0-9-]only. RejectCONVENER(reserved). If invalid, ask again. Suggest meaningful names (e.g.PM-Claude/Cursor-Web) overSession-A/Session-Bwhen the user's context implies them. - GOAL / definition of done — default "consensus + a joint summary addressed to the Convener." Accept an override.
- Dialogue file path — where to create it. Default:
<cwd>\<topic-slug>-dialogue.md. Confirm or take a path.
Step 2 — create the dialogue file
Write the file at the chosen path with this header (fill the blanks; nothing after the --- yet):
# <TOPIC> — Dialogue
> Parties: <PARTY-A-LABEL> (opens, Turn 1) ↔ <PARTY-B-LABEL>. Rules: see dialogue-protocol.md.
> Goal: <GOAL>.
---
If the file already exists and is non-empty, stop and warn rather than overwriting — a dialogue may be in progress.
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.
- 6d ago First seen · 61 lines · 49 tokens per session scan A ebe29c59f2a9
dialogue-convene is a command published in the GitHub repository FlorinI/Florians-Claude-Code-Kit (5 stars, last pushed 7d ago), licensed MIT. It adds 49 tokens to every session and 1,499 once invoked, about $0.0002 per session on Opus 5. 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.
Other commands, from other repositories
notification
Use the unified toast notification system for all user-facing notifications in Conduit.
dev
You are continuing development on Conduit, an AI-powered remote connection manager. Follow this workflow precisely.
sounds
List available notification sounds and preview them.
run
显式启动一次隔离的 Windows Computer Use 任务.
notifications-settings
Alias for settings — Configure notification sounds and settings.
cross-platform
Command "cross-platform" from Awesome-Embedded-Learning-Studio/CFDesktop, covering /cross-platform — 跨平台兼容性检查, 触发方式, 支持平台, 检查流程 and step 1: 条件编译检查.