agentmods.dev

plan-build

plan-build is a skill for Claude Code from DorianSchlede/nexus-template. It costs 19 tokens per session (5,393 once invoked), scanned A, original, MIT.

A required starting workflow for creating a Nexus build, including checking onboarding, choosing a build type, and setting up the build.

In plain words
What is it for?
Use it whenever creating a build so the agent can check onboarding, initialize the right structure, and follow the discovery process.
Why use it?
It prevents builds from starting without the needed project setup or, for a first build, without offering the required introduction.

Skill for Claude Code

Written for Claude Code: PreCompact hook event. Also seen: mentions subagents; names the TodoWrite tool.

not rated 8repo 7mo ago A scan 19 tokens original MIT

Good fit Use it whenever creating a build so the agent can check onboarding, initialize the right structure, and follow the discovery process.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dorianschlede/nexus-template/plan-build
View source ↗ DorianSchlede/nexus-template
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 DorianSchlede/nexus-template --skill plan-build
Clone the repo
git clone --depth 1 https://github.com/DorianSchlede/nexus-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 plan-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/dorianschlede/nexus-template/plan-build.svg)](https://agentmods.dev/skills/dorianschlede/nexus-template/plan-build)
Your own site
<a href="https://agentmods.dev/skills/dorianschlede/nexus-template/plan-build"><img src="https://agentmods.dev/badge/skills/dorianschlede/nexus-template/plan-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,393 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 $0.00019 $0.05393
Opus 5 $0.00010 $0.02697
Sonnet 5 $0.00004 $0.01079
Haiku 4.5 $0.00002 $0.00539

Measured 7d ago against content hash 156fa147791a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

plan-build 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 7d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/create-build.py, scripts/init_build.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

00-system/skills/builds/plan-build/SKILL.md · 714 lines

How it starts

The opening of the file, as written. The whole thing — 714 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Onboarding Awareness (CHECK BEFORE STARTING)

Before creating a build, AI MUST check user-config.yaml for incomplete onboarding:

Pre-Flight Check (MANDATORY)

# Check learning_tracker.completed in user-config.yaml
learn_builds: false  → SUGGEST 'learn builds' skill FIRST

If learn_builds: false AND this is user's FIRST build:

Before creating your first build, would you like a quick 8-minute tutorial
on how Nexus builds work? It covers:
- When to use builds vs skills (avoid common mistakes)
- Build structure and lifecycle
- How to track progress effectively

Say 'learn builds' to start the tutorial, or 'skip' to create directly.

If user says 'skip': Proceed with build creation but add this note at the end:

Tip: Run 'learn builds' later if you want to understand the build system deeply.

If learn_builds: true: Proceed normally without suggestion.

MANDATORY ROUTER PATTERN

plan-build is the ONLY entry point for all build creation.

WORKFLOW SEQUENCE (DO NOT SKIP STEPS)

  1. TYPE DETECTION → Semantic match from _type.yaml descriptions
  2. BUILD SETUP → Run init_build.py with detected type
  3. DISCOVERY → 3-phase flow (inline) OR skill-based 3a. Discovery Questions → Understand what user wants to build 3b. Active Research → AI explores based on answers 3c. Informed Follow-ups → Questions + optional follow-up research ↳ Loop to 3b if new areas discovered (max 2 loops)
  4. MENTAL MODELS → MANDATORY - Run AFTER discovery
  5. RE-DISCOVERY → If mental models reveal gaps (max 2 rounds)
  6. FINALIZATION → Fill 03-plan.md, fill 04-steps.md

CRITICAL CHECKPOINTS:

  • After Phase 3: plan.md MUST have success criteria + risks (from mental models)
  • After Phase 6: plan.md MUST be filled (not template), steps.md MUST have concrete tasks

Critical Rules

Read the full file on GitHub · 714 lines

Files

What ships with it

51 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. 7d ago First seen · 714 lines · 19 tokens per session scan A 156fa147791a

Subscribe to this mod's changes

plan-build is a skill published in the GitHub repository DorianSchlede/nexus-template (8 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 5,393 once invoked, about $0.0001 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 2026-08-31.

Planning
Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 tokens

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

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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens