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.
npx skills add lucasnad27/claude-plugins --skill create-plangit clone --depth 1 https://github.com/lucasnad27/claude-pluginsWrote 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.
[](https://agentmods.dev/skills/lucasnad27/claude-plugins/create-plan)<a href="https://agentmods.dev/skills/lucasnad27/claude-plugins/create-plan"><img src="https://agentmods.dev/badge/skills/lucasnad27/claude-plugins/create-plan/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.
<a href="https://agentmods.dev/skills/lucasnad27/claude-plugins/create-plan"><img src="https://agentmods.dev/badge/skills/lucasnad27/claude-plugins/create-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00015 | $0.02492 |
| Opus 5.5 | $0.00006 | $0.00997 |
| Sonnet 5.5 | $0.00003 | $0.00498 |
| Haiku 4.5 | $0.00002 | $0.00249 |
Grade A, and why
create-plan scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **Prefer slices the agent can verify itself** — things with automated tests, curl-able endpoints, or observable output. Save manual checkpoints for things that genuinely need human eyes (UX feel, visual design, busine How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Plan
You are tasked with creating detailed, vertical implementation plans from an approved design document. The design decisions are already made — your job is to translate them into actionable phases.
Mark the herdr phase
As your very first action, tag this agent's herdr tab so the session navigator shows the workflow phase (safe no-op outside herdr):
bash "$(git rev-parse --show-toplevel)/.claude/scripts/herdr-phase.sh" plan
Initial Response
When this command is invoked:
-
Check if parameters were provided:
- If a design doc path was provided as $ARGUMENTS, read it FULLY
- Also check for and read any referenced research docs or tickets
- Begin the planning process
-
If no parameters provided, respond with:
I'll help you create an implementation plan. Please provide: 1. The design document (from /design-doc) — required 2. Optionally, the research doc or ticket reference Tip: /create-plan .rpi/design-2026-01-05-auth-redesign.mdThen wait for the user's input.
Process
Step 1: Context Gathering
- Read the design document FULLY — this is your primary input
- Read any concrete reference artifact it links — an HTML mockup, a schema diff, example request/response payloads. These are the spec; prefer them over the prose describing them.
- Read any referenced research docs and tickets
- Spawn focused research agents if needed:
- Use codebase-locator to find specific files referenced in the design
- Use codebase-analyzer to understand implementation details needed for planning
- Only research what the design doc doesn't already cover
- Read all files identified by research agents
Step 2: Create Plan Outline
Present a high-level outline of vertical phases before writing the full plan:
Based on the design document, here's my proposed phasing:
Phase 1: [Name] — [What it accomplishes end-to-end]
Testing: [How this phase will be verified]
Phase 2: [Name] — [What it accomplishes end-to-end]
Testing: [How this phase will be verified]
Phase 3: [Name] — [What it accomplishes end-to-end]
Testing: [How this phase will be verified]
Files by phase:
src/
├── routes/dashboard/+page.svelte # P1, P3
├── lib/server/jobs/metrics.ts # P2
└── routes/dashboard/+page.server.ts # P3
Does this phasing make sense? Should I adjust?
What ships with it
1 file 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.
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.
- 25d ago Changed · +8 lines e6772737ca06
- 1mo ago Changed fc5fcbc5f46f
- 1mo ago Changed · +14 lines 4ea20ba1c2b6
- 1mo ago First seen · 189 lines · 15 tokens per session scan A 47d14d4ff9a6
create-plan is a skill published in the GitHub repository lucasnad27/claude-plugins (3 stars, last pushed 22d ago), licensed MIT. It adds 15 tokens to every session and 2,492 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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.
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…
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…