kimi-peer-writer

kimi-peer-writer is a skill for Claude Code from TserenTserenov/FMT-exocortex-template. It costs 84 tokens per session (11,536 once invoked), scanned A, original, MIT.

A peer-work session in which Kimi writes and Claude acts as a second participant. It supports repeated turns, escalation, review, checking, and a decision about whether to record or implement a result.

In plain words
What is it for?
Use it for technical decisions, design discussions, code reviews, trade-off analysis, and preparing options for a final decision. Do not use it for decisions explicitly assigned to a human or a separate validator.
Why use it?
It gives technical work a structured second opinion and keeps review and verification in the conversation. Agreement between the two agents does not replace decisions reserved for a human or another designated role.

Skill for Claude Code

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

Good fit Use it for technical decisions, design discussions, code reviews, trade-off analysis, and preparing options for a final decision. Do not use it for decisions explicitly assigned to a human or a separate validator.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tserentserenov/fmt-exocortex-template/kimi-peer-writer"><img src="https://agentmods.dev/badge/skills/tserentserenov/fmt-exocortex-template/kimi-peer-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,536 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 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: 5 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 Supply Chain · line 436
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
  • high Supply Chain · line 436
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
  • 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.
  • medium Agent Snooping · line 57
    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 $0.00084 $0.11536
Opus 5 $0.00042 $0.05768
Sonnet 5 $0.00017 $0.02307
Haiku 4.5 $0.00008 $0.01154

Measured 6d ago against content hash 062556dc1fff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

kimi-peer-writer scanned grade A with 2 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Если /verify не подходит (например, CLI-only без UI) — напиши и запусти точечный smoke (pytest fixture / curl call / минимальный python script).

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

result = subprocess.run(
.claude/skills/kimi-peer-writer/SKILL.md · 924 lines

How it starts

The opening of the file, as written. The whole thing — 924 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kimi Peer Writer (DP.SC.154)

Задача: $ARGUMENTS

Архитектура: я (Kimi) = писатель, Claude = напарник. Claude вызывается через claude-peer-adapter.sh напрямую — Bash tool, stdin pipe. list_peer_statuses (Local Gateway) — координация файлов, не проверка доступности Claude CLI. Gateway offline ≠ Claude недоступен.


When to use

Peer-сессия DP.SC.154 где Kimi = писатель, Claude = напарник. Запускается простой фразой. Включает ОРЗ Opening и Closing, turn-loop, эскалации, Decision Gate (зафиксировать vs реализовать → ревью → проверить → задеплоить), отложенную финализацию и верификацию.

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.

Шаг 0. Режим

Определить режим из $ARGUMENTS:

  • --list → прочитать ${IWE_GOVERNANCE_REPO:-DS-strategy}/sessions/00-index.md, вывести таблицу. Стоп.
  • --interrupt <id> → перейти к Шагу 5 (interrupt-режим). Стоп после.
  • --finalize <id> → перейти к Шагу 6 (finalize-режим). Стоп после.
  • Иначе → новая сессия, продолжать к Шагу 0б.

Шаг 0а. Preflight Gate (WP-484 Ф33 item Г, обязательно ДО любых других действий)

Read the full file on GitHub · 924 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. 6d ago Changed · +1 lines 062556dc1fff
  2. 11d ago First seen · 923 lines · 84 tokens per session scan A 346be37334a2

Subscribe to this mod's changes

kimi-peer-writer is a skill published in the GitHub repository TserenTserenov/FMT-exocortex-template (51 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 11,536 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). 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