feature-plan

feature-plan is a skill for Claude Code, Codex from mtvrkan/senior-dev-kit. It costs 32 tokens per session (531 once invoked), scanned A, original, MIT.

A planning aid for large, risky, or unclear software changes. It produces a detailed implementation plan and does not edit code.

In plain words
What is it for?
Use it before multi-file features, architecture changes, database, authentication, payment, infrastructure, configuration, or other protected work.
Why use it?
It makes the goal, scope, affected files, interfaces, risks, tests, rollback approach, and unanswered questions explicit before work begins.

Skill for Claude CodeCodex

Part of the senior-dev-kit plugin — 25 skills, 6 commands, 9 agents, 1 hook shipped together

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/mtvrkan/senior-dev-kit/feature-plan
Any agent
npx skills add mtvrkan/senior-dev-kit --skill feature-plan
Clone the repo
git clone --depth 1 https://github.com/mtvrkan/senior-dev-kit

Made for: Claude Code, Codex.

Or install senior-dev-kit, the plugin that ships this one along with the rest of its 25 skills, 6 commands, 9 agents, 1 hook.

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 feature-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/mtvrkan/senior-dev-kit/feature-plan.svg)](https://agentmods.dev/skills/mtvrkan/senior-dev-kit/feature-plan)
Your own site
<a href="https://agentmods.dev/skills/mtvrkan/senior-dev-kit/feature-plan"><img src="https://agentmods.dev/badge/skills/mtvrkan/senior-dev-kit/feature-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 531 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 5.1 $0.00032 $0.00531
Opus 5 $0.00016 $0.00266
Sonnet 5 $0.00006 $0.00106
Haiku 4.5 $0.00003 $0.00053

Measured 5d ago against content hash 79477ad5cf43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

feature-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.

skills/feature-plan/SKILL.md · 30 lines

What it actually says

feature-plan

Produce a detailed, executable plan for multi-file/risky features. No code edits, wait for confirmation. Auto-fires for clear feature work (the request names a thing to build); also fits non-feature risky work (refactors, config/infra, ambiguous "make X better" asks) when invoked directly. Tier 3+ / protected-area work should run under native plan mode (read-only) with this output format. If the feature description lacks a goal or scope, fill OPEN: with the missing questions instead of guessing.

Output format

GOAL: [≤10 words] | NON-GOALS: [excluded] | RISK: low|medium|high|critical — [why]
PROTECTED: [auth|payment|DB|secrets|CI|none] | GUARD: [db-guard|security-guard|devops-guard|none]
AFFECTED: `exact/file` — [modify|create] — [why]
STEPS:
  [P:A] `exact/file` — [fn name+sig | endpoint+DTO | component+props]
  [P:A] `exact/file` — [independent of above]
  [P:B] `exact/file` — [depends on A]
CONTRACT: API→[method path req→res] | UI→[component props state] | DB→[model fields migration]
VERIFY: [exact command] | ROLLBACK: [strategy | n/a] | OPEN: [questions | none]

Rules: read the recorded architecture first (PROJECT-CONTRACTS.md / .claude/codebase-overview.md / project CLAUDE.md) and place every new file inside it; a plan that quietly crosses an existing boundary is where a project's second architecture starts. Adding a module, layer or package → /arch-check before planning, so the plan starts from the real boundary state. grep/glob to confirm paths before listing. Every step specific enough to hand to an engineer. Mark [P:GroupName] on independent steps. Do not start coding.

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. 5d ago First seen · 30 lines · 32 tokens per session scan A 79477ad5cf43

Subscribe to this mod's changes

feature-plan is a skill published in the GitHub repository mtvrkan/senior-dev-kit (5 stars, last pushed 5d ago), licensed MIT. It adds 32 tokens to every session and 531 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

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-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 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