y-plan-core-review

y-plan-core-review is a command for Claude Code from yashs33244/the_y_coding_standard. It costs 118 tokens per session (1,626 once invoked), scanned A, original, MIT.

A strategic review step for an active software plan. It checks whether the planned scope is too large, too small, or aimed at the wrong problem.

In plain words
What is it for?
Use it to challenge a plan, assess its likely impact, find weak assumptions, and lock the scope for later design and engineering work.
Why use it?
It helps prevent teams from building more than needed or missing important consequences before implementation starts.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the the-y-coding-standard plugin — 1 skill, 10 commands shipped together

Good fit Use it to challenge a plan, assess its likely impact, find weak assumptions, and lock the scope for later design and engineering work.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add yashs33244/the_y_coding_standard
Claude Code
/plugin install the-y-coding-standard

Made for: Claude Code.

Or install the-y-coding-standard, the plugin that ships this one along with the rest of its 1 skill, 10 commands.

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 y-plan-core-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/yashs33244/the_y_coding_standard/y-plan-core-review/github.svg)](https://agentmods.dev/commands/yashs33244/the_y_coding_standard/y-plan-core-review)
Your own site
<a href="https://agentmods.dev/commands/yashs33244/the_y_coding_standard/y-plan-core-review"><img src="https://agentmods.dev/badge/commands/yashs33244/the_y_coding_standard/y-plan-core-review/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 y-plan-core-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/yashs33244/the_y_coding_standard/y-plan-core-review"><img src="https://agentmods.dev/badge/commands/yashs33244/the_y_coding_standard/y-plan-core-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,626 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 $0.00118 $0.01626
Opus 5 $0.00059 $0.00813
Sonnet 5 $0.00024 $0.00325
Haiku 4.5 $0.00012 $0.00163

Measured 9d ago against content hash 56f3b8dfc1fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

y-plan-core-review 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 9d 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.

commands/y-plan-core-review.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/y-plan-core-review

You are running step 02 of Yash's Sprint Loop: Core Review. This is the "how big could it be?" phase. CEO-mode. You read the active plan from /y-office-hours (or any draft plan) and pressure-test scope. You challenge whether it is overbuilt, underbuilt, or shaped wrong. You write the answer back into the plan so the next step (/y-plan-design-review) starts from a locked scope.

The Sprint Loop is: Office Hours -> Core Review -> Design Review -> Eng Review -> Implement -> Test -> Review -> Ship -> Retro. You are the scope gate. Everything past you is execution.

Pre-flight

  1. List plans/ files matching YYYY-MM-DD-*.md, newest first.
  2. If the user passed a path as an arg, use it. Otherwise:
    • If exactly one plan has Status: draft (office-hours), use it.
    • Else ask the user which file to review. Show top 3 by date.
  3. Read the selected plan end to end before asking anything. Do not skim.
  4. Load ${CLAUDE_PLUGIN_ROOT}/skills/the-y-coding-standard/references/agentic-stack.md for plan format conventions.

Workflow

Run six passes. Each pass updates an internal worksheet. After all six, write the consolidated update to the plan file.

Pass 1: Scope shape

Ask the user (one at a time, not in a flood):

  1. "What is the single sentence that says what shipping this means? Verb plus deliverable."
  2. "Is the goal a feature, a workflow change, a platform piece, or a one-off fix?"
  3. "What is the success metric? How would you know in three weeks this worked?"

If success cannot be stated, that is the first finding. A plan without a measurable win is a hobby.

Pass 2: Overbuilt check

Re-read the recommended shape from the plan. Ask:

  1. "What is the simplest version that delivers the success metric? Strip everything optional."
  2. "If you had two days instead of two weeks, what would you cut?"
  3. "Which part of this is being built because it is interesting, not because it is needed?"

Be blunt. Yash does not want polite review.

Read the full file on GitHub · 158 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. 9d ago First seen · 158 lines · 118 tokens per session scan A 56f3b8dfc1fc

Subscribe to this mod's changes

y-plan-core-review is a command published in the GitHub repository yashs33244/the_y_coding_standard (2 stars, last pushed 3mo ago), licensed MIT. It adds 118 tokens to every session and 1,626 once invoked, about $0.0006 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.