agentmods.dev

realm-planning

realm-planning is a skill for Claude Code, Codex from blackmo18/realm. It costs 57 tokens per session (1,867 once invoked), scanned A, original, MIT.

A two-stage planning tool for turning a proposed software change into an architecture decision and an implementation plan. It can also produce a shorter scope-and-test plan.

In plain words
What is it for?
Use it for new features, architectural changes, work spanning several modules or services, or plans that need an ADR, a written record of an architecture decision.
Why use it?
It helps resolve unclear design choices and identify affected files and required tests before coding starts.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex; $skill-name invocation.

Part of the realm plugin — 8 skills, 7 agents shipped together

not rated 0repo 2mo ago A scan 57 tokens original MIT

Good fit Use it for new features, architectural changes, work spanning several modules or services, or plans that need an ADR, a written record of an architecture decision.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/blackmo18/realm/realm-planning
View source ↗ blackmo18/realm
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 blackmo18/realm --skill realm-planning
Clone the repo
git clone --depth 1 https://github.com/blackmo18/realm

Made for: Claude Code, Codex.

Or install realm, the plugin that ships this one along with the rest of its 8 skills, 7 agents.

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 realm-planning

README.md
[![agentmods](https://agentmods.dev/badge/skills/blackmo18/realm/realm-planning/github.svg)](https://agentmods.dev/skills/blackmo18/realm/realm-planning)
Your own site
<a href="https://agentmods.dev/skills/blackmo18/realm/realm-planning"><img src="https://agentmods.dev/badge/skills/blackmo18/realm/realm-planning/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 realm-planning

Your own site · 80×15
<a href="https://agentmods.dev/skills/blackmo18/realm/realm-planning"><img src="https://agentmods.dev/badge/skills/blackmo18/realm/realm-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,867 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 $0.00057 $0.01867
Opus 5.5 $0.00023 $0.00747
Sonnet 5.5 $0.00011 $0.00373
Haiku 4.5 $0.00006 $0.00187

Measured 1mo ago against content hash 6ce31517b452, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

realm-planning 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 1mo 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.

skills/realm-planning/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.

realm-planning

Two-phase planning. P1 = high-level + ADR direction. P2 = code-level impl plan.

Host invocation: Claude Code and Gemini use /realm-planning; Codex uses $realm-planning.

Runs inside native plan mode — each phase has its own Enter/Exit cycle, approval is per-phase, not inherited. Boundary + fallback: references/plan-mode-contract.md.

Anchor-scoped: Phase 1 detects run mode (enhancement / anchored-new / greenfield), resolves seed anchors, caps investigator reads. Phase 2 consumes Phase 1 Anchor Set — no re-scan.

Usage

/realm-planning <topic>          # Phase 1
/realm-planning <topic> --phase2 # skip to Phase 2 (plan already approved)
/realm-planning <topic> --lite   # Scope & Test shortcut only — Affected Files + Test Scenarios, no ADR, no full plan

When to Use

  • Feature not yet implemented
  • Architectural direction unclear
  • Spans multiple services/files
  • Need plan ready for coding agent
  • Token-budget constrained, want direction only, will hand-code the implementation yourself, don't need an architecture ADR — use --lite

Communication Style

Caveman mode active. Drop articles, filler, pleasantries, hedging. Fragments OK. Technical terms exact.

Routing

  • Phase 1 → load phase1/PROCEDURE.md
  • Phase 2 → load phase2/PROCEDURE.md
  • Lite → load lite/PROCEDURE.md (--lite flag: Scope & Test Definition only, skips architecture + full plan)
  • Contract → load contract/PROCEDURE.md (Phase 1 Step 7 Contract Delta embed, or explicit write contract trigger below)
  • write adr → load write-adr/PROCEDURE.md (trigger below)

"write contract" — Draft API Contract to Vault

Trigger: user says write contract or draft contract — any time after Phase 1 approval, before Phase 2. Does not depend on write adr (that can come later) — but if ## Contract Delta is present, Phase 2 depends on this: phase2/PROCEDURE.md Step 1 refuses to start until the contract file exists. Ordering enforced: Phase 1 → contract (if applicable) → Phase 2.

Read the full file on GitHub · 132 lines

Files

What ships with it

16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago First seen · 132 lines · 57 tokens per session scan A 6ce31517b452

Subscribe to this mod's changes

realm-planning is a skill published in the GitHub repository blackmo18/realm (0 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 1,867 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-02.

Planning
Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens