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 skills add TserenTserenov/FMT-exocortex-template --skill peer-conversationgit clone --depth 1 https://github.com/TserenTserenov/FMT-exocortex-templateWrote 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/skills/tserentserenov/fmt-exocortex-template/peer-conversation)<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.
<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>- NVIDIA SkillSpector warn
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 contentFix: 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.
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 | $0.00118 | $0.18911 |
| Opus 5 | $0.00059 | $0.09456 |
| Sonnet 5 | $0.00024 | $0.03782 |
| Haiku 4.5 | $0.00012 | $0.01891 |
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.
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(defaultkimi), 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.shнапрямую — Bash tool, stdin pipe. Контракт одинаковый у всех: stdin = промпт, stdout = реплика, exit 0-5 (см. §0в). Напарнику запрещено писать файлы своими инструментами внутриSESSION_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.mdраздел «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.
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.
- 5d ago Changed · +1 lines b2ecfb9da95c
- 11d ago First seen · 1,152 lines · 118 tokens per session scan A 24ab785cc635
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.
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…
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…
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…
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.
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.
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.