peer-conversation

peer-conversation is a skill for Claude Code from TserenTserenov/FMT-exocortex-template. It costs 118 tokens per session (18,911 once invoked), scanned A, original, MIT.

A structured, multi-turn discussion between the main coding agent and one or more other AI assistants about a task.

In plain words
What is it for?
Use it for architecture choices, reviews, diagnoses, or other tasks where comparing AI opinions is useful. It supports discussions with assistants from vendors such as Kimi, Codex, Hermes, and Claude.
Why use it?
It gives a task several independent viewpoints and records the discussion until the assistants reach agreement or need escalation. After agreement, it supports deciding whether to record the decision or implement it.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

Good fit Use it for architecture choices, reviews, diagnoses, or other tasks where comparing AI opinions is useful. It supports discussions with assistants from vendors such as Kimi, Codex, Hermes, and Claude.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tserentserenov/fmt-exocortex-template/peer-conversation
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.

Any agent
npx skills add TserenTserenov/FMT-exocortex-template --skill peer-conversation
Clone the repo
git clone --depth 1 https://github.com/TserenTserenov/FMT-exocortex-template

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.

agentmods badge for peer-conversation

README.md
[![agentmods](https://agentmods.dev/badge/skills/tserentserenov/fmt-exocortex-template/peer-conversation/github.svg)](https://agentmods.dev/skills/tserentserenov/fmt-exocortex-template/peer-conversation)
Your own site
<a href="https://agentmods.dev/skills/tserentserenov/fmt-exocortex-template/peer-conversation"><img src="https://agentmods.dev/badge/skills/tserentserenov/fmt-exocortex-template/peer-conversation/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 peer-conversation

Your own site · 80×15
<a href="https://agentmods.dev/skills/tserentserenov/fmt-exocortex-template/peer-conversation"><img src="https://agentmods.dev/badge/skills/tserentserenov/fmt-exocortex-template/peer-conversation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 18,911 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Prompt Injection · line 266
    Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
    Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
  • medium analysis-evasion · line 1
    Suspicious Unicode normalization or mixed-script content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
  • medium Agent Snooping · line 42
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00118 $0.18911
Opus 5 $0.00059 $0.09456
Sonnet 5 $0.00024 $0.03782
Haiku 4.5 $0.00012 $0.01891

Measured 5d ago against content hash b2ecfb9da95c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

peer-conversation 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 5d 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.

.claude/skills/peer-conversation/SKILL.md · 1,153 lines

How it starts

The opening of the file, as written. The whole thing — 1,153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Peer Conversation (DP.SC.154)

Задача: $ARGUMENTS

Архитектура: я (Claude) = писатель всегда (Skill tool доступен только мне в этой сессии). Напарник(и) — параметр --peer (default kimi), список из одного или нескольких зарегистрированных вендоров (§0в). При 2+ напарниках (N>2 участников целиком) — расширение WP-509, см. §0в и §3р. Каждый напарник вызывается через свой <vendor>-peer-adapter.sh напрямую — Bash tool, stdin pipe. Контракт одинаковый у всех: stdin = промпт, stdout = реплика, exit 0-5 (см. §0в). Напарнику запрещено писать файлы своими инструментами внутри SESSION_DIR — только stdout (гонка file-write vs stdout-capture портит журнал, найдено WP-509 2026-07-30). list_peer_statuses (Local Gateway) — координация файлов, не проверка доступности напарника CLI. Gateway offline ≠ напарник недоступен.


When to use

Многотуровый диалог писателя (Claude) с одним или несколькими напарниками (любой набор зарегистрированных вендоров — Kimi, Codex, Hermes, второй Claude-инстанс headless) по задаче пилота (DP.SC.154). При одном напарнике — turn-loop (пара реплик). При двух и более напарниках — round-loop (WP-509): каждый раунд высказывается каждый участник, с явной role-discovery фазой (раунды 0–2), валидацией реплик по 4 критериям, лимитом повторных вызовов и классификацией результата agreed|partial|escalated|not-agreed. Обнаруживает CONSENSUS/ESCALATE, после консенсуса — Decision Gate (зафиксировать vs реализовать → ревью → проверить → задеплоить), синтезирует report.md через Agent tool.

Scope boundary — не подменяет решения, зарезервированные за пилотом (найдено 2026-07-07)

Peer-сессия пригодна для: технических решений, дизайна, code review, поиска компромисса между подходами, подготовки кандидатов к решению. НЕ пригодна для решений, которые процесс явно закрепляет за человеком (например, R15 Валидатор в /apply-captures — accept/reject/defer кандидатов знания; R1 Стратег — приоритеты месяца). Согласие двух агентов между собой — не решение пилота, даже единогласное и хорошо обоснованное.

Если задача внутри пир-сессии требует такого решения — писатель обязан остановиться и спросить пилота напрямую в текущем чате (не через turn-файл), прежде чем фиксировать результат. См. .claude/skills/apply-captures/SKILL.md раздел «R15 = живой пилот, не агент» и ${IWE_GOVERNANCE_REPO:-DS-strategy}/inbox/bugs/bug-2026-07-07-r15-decisions-bypassed-pilot.md — прецедент, из-за которого добавлено это ограничение.

Read the full file on GitHub · 1,153 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. 5d ago Changed · +1 lines b2ecfb9da95c
  2. 11d ago First seen · 1,152 lines · 118 tokens per session scan A 24ab785cc635

Subscribe to this mod's changes

peer-conversation is a skill published in the GitHub repository TserenTserenov/FMT-exocortex-template (51 stars, last pushed today), licensed MIT. It adds 118 tokens to every session and 18,911 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

team-management-debugging

Systematic debugging — a four-phase root-cause methodology, boundary instrumentation for multi-component systems, the 3-fix escalation rule, and a verification gate to run before claiming anything is fixed. Use on any test failure, production bug, build failure, performance regression, or integration glitch, and…

TeamManagementPlugin/claude-plugin · 95 tokens

team-management-receiving-feedback

How to receive code review as technical evaluation rather than social performance — verify claims against the codebase before implementing, push back with evidence, and drop the performative agreement. Use when responding to a human reviewer, a PR comment, or another AI reviewer, and when deciding whether a suggestion…

TeamManagementPlugin/claude-plugin · 97 tokens

team-management-tdd-discipline

Test-driven development discipline — when TDD applies, when forcing it is wrong, and the RED-GREEN-REFACTOR loop with an explicit "watch it fail" step. Use when writing or reviewing tests, fixing a bug, changing behaviour, or deciding whether a change needs a test at all. Triggers on bug fixes, new validation or…

TeamManagementPlugin/claude-plugin · 96 tokens

data-profiling

Use BEFORE dispatching any subagent that needs to understand the dataset. Generates a high-density, PII-free data profile in Markdown so subagents receive structured context instead of raw data.

zpower426/datapowers · 42 tokens

leakage-guard

Use whenever building features for time-series or any temporal dataset. Enforces strict temporal integrity: no future data in features, no post-event information, correct CV strategy.

zpower426/datapowers · 39 tokens

verification-before-delivery

Use when any analysis, model, or report is claimed to be complete. Runs mandatory artifact integrity, statistical evidence, and reproducibility checks before any delivery.

zpower426/datapowers · 36 tokens