devplan

A planning skill that turns a plain-language software idea into a structured implementation prompt. It first gathers project context from files such as CLAUDE.md and README.md when they exist.

In plain words
What is it for?
Creating a JSON result with a plan key and a detailed prompt covering the project's constraints, background, and implementation work.
Why use it?
A coding agent needs project rules and architecture details to produce a useful plan. Collecting that context reduces assumptions and makes the plan easier to execute.

Skill for Claude CodeCodex

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/sergiovision/devserver/devplan
Any agent
npx skills add sergiovision/DevServer --skill devplan
Clone the repo
git clone --depth 1 https://github.com/sergiovision/DevServer

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,056 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.

ModelPer sessionOnce invoked
Fable 5 $0.00032 $0.01056
Opus 5 $0.00016 $0.00528
Sonnet 5 $0.00006 $0.00211
Haiku 4.5 $0.00003 $0.00106

Measured yesterday against content hash 9c4bee14a8e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devplan 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 yesterday.

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.

.claude/skills/devplan/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DevPlan - Generate Implementation Plan JSON

You are a professional software architect. You receive input in $ARGUMENTS in the format:

<project_name> <idea or feature description>

The first word is the project name. Everything after it is the idea/feature description.

Enter plan mode.

Your job: produce a professional, structured implementation plan that a coding agent can understand and execute properly — not the code itself.

Gathering Project Context

Before generating the plan, you MUST gather project-specific constraints:

  1. CLAUDE.md — Read the project's CLAUDE.md file (if it exists) to learn the tech stack, conventions, directory layout, and rules. This is your primary source of constraints.
  2. README.md — Read the project's README.md (if it exists) for additional architecture and setup context.
  3. Memory — Check your memory for any stored knowledge about this project (user preferences, past feedback, project conventions).

Use whatever you find to populate the Constraints and Background sections of the prompt. If none of these sources exist, generate the plan based solely on the user's description and state assumptions.

Do NOT explore the repo beyond these files. The executing agent has full repo access — your job is to write a clear, actionable plan. Save tokens.

Return only a single JSON object (no markdown fences, no explanation).

Output Schema

{
  "plan_key": "<string>",
  "prompt": "<string>"
}

Field Rules

plan_key

  • UPPERCASE hyphenated slug, PLAN-AREA-SHORT-SLUG format, max 64 chars.
  • Must start with PLAN-.
  • Examples: PLAN-API-ADD-WEBHOOKS, PLAN-UI-TASK-FILTERS, PLAN-WORKER-RETRY-LOGIC.

prompt

A professional, self-contained implementation prompt. It must include ALL of the following sections as a single string (use \n for line breaks):

  1. Role & Context — Open with: "You are a professional software engineer working on {project_name}." Follow with a one-line summary of the project's purpose and tech stack (sourced from CLAUDE.md/README). State: "You have full knowledge of the project structure, codebase conventions, and architecture."

Read the full file on GitHub · 94 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. yesterday First seen · 94 lines · 32 tokens per session scan A 9c4bee14a8e8

Subscribe to this mod's changes

devplan is a skill published in the GitHub repository sergiovision/DevServer (1 stars, last pushed 9d ago), licensed MIT. It adds 32 tokens to every session and 1,056 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

wiki-write

Add or update wiki content — autonomous ingest from URL, file, or text; autonomous update of existing pages. Auto-creates .wiki/ on first use. Use when: 'save to wiki', 'remember this', 'note this', 'store this', 'add to knowledge base', 'save findings', 'save research', 'save idea', 'write to wiki', 'ingest', 'add…

Oshayr/LLM-Wiki · 90 tokens

wiki-serve

Start the wiki web server — browsable Wikipedia-style UI with live research, split-pane editor, AI assist, and themes. Manual trigger only: /wiki-serve, 'start wiki server', 'browse the wiki'.

Oshayr/LLM-Wiki · 48 tokens

wiki-maintain

Wiki maintenance — lint broken links, merge near-duplicates, upgrade confidence, flag stale pages via freshness tiers, gap analysis, concept synthesis. Use on: 'wiki maintenance', 'wiki cleanup', 'fix wiki', 'wiki health', 'check wiki', 'consolidate wiki'.

Oshayr/LLM-Wiki · 61 tokens

wiki-read

Search and query the wiki — get cited answers, with automatic research when knowledge is missing. Three depth modes. Use when: 'check wiki', 'what do we know about', 'look up', 'find in wiki', 'search wiki', 'search for', 'find information about', 'do we have notes on', 'wiki context', 'existing knowledge'…

Oshayr/LLM-Wiki · 102 tokens

wiki-view

Wiki dashboard — browse pages, view stats, knowledge graph, export. Use on: 'wiki dashboard', 'wiki stats', 'show wiki', 'wiki pages', 'list wiki', 'wiki graph', 'export wiki', 'wiki overview'.

Oshayr/LLM-Wiki · 52 tokens

paper-illustration

Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.

wanshuiyin/Auto-claude-code-research-in-sleep · 67 tokens