A guided method for breaking a large or unclear software task into smaller tasks and a practical order of work. It can also help inspect the project and use other relevant skills during planning.

Use it to plan complex changes, ask important follow-up questions, study the existing codebase, define subtasks, and prepare an implementation plan.

It reduces uncertainty before implementation by clarifying requirements, project constraints, dependencies, and how success will be judged.

koda-plan — Skill for Claude Code and Codex by XCode-NLP: A guided method for breaking a large or unclear…

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.

agentmods

npx agentmods add skills/xcode-nlp/kodaskills/koda-plan

Any agent

npx skills add XCode-NLP/KodaSkills --skill koda-plan

Clone the repo

git clone --depth 1 https://github.com/XCode-NLP/KodaSkills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/xcode-nlp/kodaskills/koda-plan.svg)](https://agentmods.dev/skills/xcode-nlp/kodaskills/koda-plan)

Your own site

<a href="https://agentmods.dev/skills/xcode-nlp/kodaskills/koda-plan"><img src="https://agentmods.dev/badge/skills/xcode-nlp/kodaskills/koda-plan.svg" alt="Measured on agentmods" height="20"></a>

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,620 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00058	$0.01620
Opus 5	$0.00029	$0.00810
Sonnet 5	$0.00012	$0.00324
Haiku 4.5	$0.00006	$0.00162

Measured 5d ago against content hash 67f46b20bf6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

koda-plan 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

planning — 88% identical, 136 lines differ

skills/koda-plan/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Планирование сложных задач

Цель: сформировать подробный пошаговый практичный план действий перед реализацией, чтобы согласовать ожидания и снизить риски.

Когда использовать

Пользователь просит план, стратегию или этапы
Задача крупная, абстрактная, неоднозначная или рискованная
Задача затрагивает разные слои проекта, требует множества согласованных между собой изменений
Требуются уточняющие вопросы

Что делать

1. Анализ входных данных

Проанализируй исходный запрос и текущий контекст.
Если необходимо: сформулируй несколько уточняющих вопросов, уточни ключевые нюансы, конечную цель и критерии оценки результата.
Изучи текущий проект: файловую структуру, архитектуру, паттерны, бизнес-логику, зависимости, связность и др.
При возможности изучи документацию к проекту: это могут быть комментарии в коде, дополнительные файлы и/или документация к фреймворкам и библиотекам.
Определи список доступных навыков и инструментов.
Выдели те участки проекта, которые соотносятся с требованиями пользователя.

2. Планирование

Исходя из анализа, разбей исходную постановку на задачи в соответствии со структурой проекта. Необязательно детализировать до уровня атомарных операций, но каждый последующий шаг должен быть детерминирован и логично следовать из предыдущего.
Для каждого шага определи хотя бы один подходящий навык из доступных. Необязательно, если подходящего навыка нет.
Пересмотри план, проверь наличие необходимых данных, участков кода, навыков, инструментов; сделай заключение о выполнимости текущего плана, в противном случае скорректируй.
Покажи план пользователю как есть и передай ему слово:
- План работ должен иметь следующий формат:
```
1. [ ] **<Описание задачи 1>**
    - Навыки: ...
    - Файлы:
        - <путь1>
        - <путь2>
        - ...
2. [ ] **<Описание задачи 2>**
    - Навыки: ...
    - Файлы:
        - <путь1>
        - <путь2>
        - ...
3. [ ] **<Описание задачи 3>**
    - Навыки: ...
    - Файлы:
        - <путь1>
        - <путь2>
        - ...
...
```
- При отрицательном ответе вернись на этап анализа входных данных и задай уточняющие вопросы.
- При положительном ответе запиши план в файл .koda/plans/<имя-плана>.md в корне проекта. Имя плана зависит от исходной задачи. Например:
  - если нужно исправить ошибку формирования заказа, файл плана следует назвать fix-order-creation.md;
  - если нужно внедрить новый вид уведомлений, тогда new-notification.md.

Read the full file on GitHub · 132 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.

5d ago First seen · 132 lines · 58 tokens per session scan A 67f46b20bf6a

Subscribe to this mod's changes

koda-plan is a skill published in the GitHub repository XCode-NLP/KodaSkills (19 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 1,620 once invoked, about $0.0003 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.

Planning agent-skills ai-agent kodacode skills

claude-md-improver

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…

anthropics/claude-plugins-official · 82 tokens

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

gke-reliability

Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).

google/skills · 73 tokens

gke-workload-security

Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…

google/skills · 181 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens