discuss

discuss is a skill for Claude Code from PouLJenny/trundle. It costs 290 tokens per session (4,873 once invoked), scanned A, original, Apache-2.0.

A discussion mode that lets several command-line AI agents take turns considering a question while you join the conversation. It coordinates the exchange and keeps a record of what each participant says.

In plain words
What is it for?
Use it to discuss requirements, weigh multiple designs, ask named agents for their views, and explore a problem through a structured multi-agent conversation.
Why use it?
It helps when one answer is not enough and you want different agents to challenge, compare, or cross-check possible approaches.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_SKILL_DIR} variable. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the trundle plugin — 1 skill shipped together

Good fit Use it to discuss requirements, weigh multiple designs, ask named agents for their views, and explore a problem through a structured multi-agent conversation.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add PouLJenny/trundle
Claude Code
/plugin install trundle

Made for: Claude Code.

Or install trundle, the plugin that ships this one along with the rest of its 1 skill.

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.

agentmods badge for discuss

README.md
[![agentmods](https://agentmods.dev/badge/skills/pouljenny/trundle/discuss/github.svg)](https://agentmods.dev/skills/pouljenny/trundle/discuss)
Your own site
<a href="https://agentmods.dev/skills/pouljenny/trundle/discuss"><img src="https://agentmods.dev/badge/skills/pouljenny/trundle/discuss/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for discuss

Your own site · 80×15
<a href="https://agentmods.dev/skills/pouljenny/trundle/discuss"><img src="https://agentmods.dev/badge/skills/pouljenny/trundle/discuss.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 290 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,873 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00290 $0.04873
Opus 5 $0.00145 $0.02436
Sonnet 5 $0.00058 $0.00975
Haiku 4.5 $0.00029 $0.00487

Measured 10d ago against content hash e2ab33418d96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

discuss 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 10d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/discover.sh, scripts/install.sh, scripts/invoke.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/discuss/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

trundle discuss

把当前对话变成 host(正在读本文件的你)+ 其他 CLI agent 的回合制群聊。用户是参与方,不是审批人。产出物是讨论过程本身,不是最后那份文档。

本文件是:只管进入/退出、机械执行和渲染。每轮「谁发言、喂什么、怎么收尾」的裁量由 moderator(一个独立的 CLI agent,见 protocol/moderator.md)产出计划,我照计划执行。我自己的发言在计划的 host_say 划定的边界内展开——那是指引不是讲稿,话由我自己说:我是讨论的当事方,不是传声筒。

路径约定:下文 <SKILL> 指本文件所在目录(Claude Code 软链安装下是 ${CLAUDE_SKILL_DIR},plugin 安装下是 ${CLAUDE_PLUGIN_ROOT}/skills/discuss;其他 host 没有这些变量,就是你读到本文件的实际目录),<SCRIPTS><SKILL>/scripts主 host 是 Claude Code(行为已验证);其他 host 先读 references/hosts.md 的机制映射与支持状态。

铁律

  1. 用户是参与方,不是审批人。 不向用户「提交」结论等批准,而是向用户提问
  2. 默认一轮只有我说话。 拉人是例外——这条裁量由 moderator 执行,但它同时是我在降级模式下的行为底线。
  3. 辅助 agent 全程只读。 API 参与者天然满足(它够不到文件系统),其余四个 CLI: codex 走 --sandbox read-only,gemini 走 --approval-mode plan,claude 走工具白名单 --allowedTools Read,Glob,Grep,dsh 走 DSH_PERMISSION_MODE=read-only(它没有只读 flag,只读靠环境变量,而且它的默认值是可写的——脚本强制覆盖用户环境,不随环境变量放宽)。永不给写权限。moderator 自己也是子进程,同样只读。
  4. 产出物是讨论过程。 除非用户明确要,结尾不生成规格文档、不写"最终方案"。
  5. 子进程无状态。 每次调用把需要的上下文完整塞进 prompt——它不记得上一轮。moderator 也一样:它每轮从 transcript 重建判断。

一个回合(壳的机械循环)

用户发言后:

  1. 组装本轮输入,写进临时文件,五段(格式见 protocol/moderator.md 的「输入」): 【名册】本轮实际阵容(「这轮别带 X」在这里生效)/【共识状态头】/【讨论记录】/【主持人立场】我对议题当前的立场或内心状态,如实写,包括没把握的部分/【用户本轮消息】原话
  2. 跑 moderator:python3 <SCRIPTS>/moderate.py --input <文件>必须允许它跑满 600s——它的总预算是 590s(含一次重试),要让它先于 host 的命令超时开枪(Claude Code:Bash 工具 timeout 显式设 600000,默认 120s 会误杀;其他 host 见 references/hosts.md)。
  3. 照计划执行:输出里 ===EXEC=== 给出的 invoke.sh 命令原样执行(同样 timeout 600000);「本轮无外部调用」则跳过。===WARN=== 里的 soft 违规如实转告用户,不隐瞒。
  4. 渲染所有发言(见「渲染」),然后我在 host_say 的边界内发言。
  5. 收尾closing:user_question → 以那个问题结束回合;fact_verdict我当轮就去查/去跑,结果以 [事实裁定] <结论>(host 实测,第 N 轮) 追加进 transcript 并告知用户——把事实问题推给用户是失职;none → 不追问。
  6. 记账:按 transcript_delta.append 追加 transcript(direction_change 非空则先插 ── 方向变更:X → Y(用户,第 N 轮)──),打状态行。

回合内不中途问"要不要继续"。moderate.py 退出码非 0 → 走「降级模式」。

降级模式

moderator 缺席时(moderate.py 退出码非 0:没装任何可用 CLI、超预算、两次都产不出合法计划),明说一行,例如:moderator 缺席(codex 未安装)· 本轮由我自行主持,然后我自己读 <SKILL>/protocol/moderator.md,按同一套裁量规则在脑内产出本轮计划,再照常走机械循环的 3-6 步

Read the full file on GitHub · 174 lines

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.

  1. 10d ago First seen · 174 lines · 290 tokens per session scan A e2ab33418d96

Subscribe to this mod's changes

discuss is a skill published in the GitHub repository PouLJenny/trundle (2 stars, last pushed 19d ago), licensed Apache-2.0. It adds 290 tokens to every session and 4,873 once invoked, about $0.0014 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.

Related

Other skills, from other repositories

agent-harness-fault-injection

Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.

sickn33/agentic-awesome-skills · 34 tokens

oma-scholar

Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…

first-fluke/oh-my-agent · 73 tokens

oma-hwp

Convert HWP / HWPX / HWPML files to Markdown using kordoc. Extracts text, headings, tables, lists, images, footnotes, and hyperlinks. Use for Korean word processor files (Hangul), government documents, and AI-ready data preparation.

first-fluke/oh-my-agent · 59 tokens

compare-harnesses

Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.

ruvnet/metaharness · 66 tokens

engineering-mission-playbook

Use when planning or replanning engineering missions that create, change, port, migrate, integrate, or preserve durable codebase behavior across UI, API, CLI, background jobs, data/migrations, libraries, or operator workflows. Defines investigation, scope inventory, coherent VAL- contracts, evidence floors…

Intelligent-Internet/zenith · 96 tokens

ads-launch

Draft or explicitly apply a paid-ad campaign launch through Claude Ads capability-gated adapters. Use for campaign creation, launch plans, publishing ads, activating campaigns, uploading creative, or requests to push a campaign live.

AgriciDaniel/claude-ads · 45 tokens