mine-plan-review

mine-plan-review is a skill for Claude Code from 6ixGODD/mine. It costs 100 tokens per session (6,965 once invoked), scanned A, original, MIT.

A strict MINE review workflow for checking whether an implemented software plan actually meets its requirements. It compares the code with repository rules, architecture decisions, the plan, commits, runtime behavior, and verification evidence.

In plain words
What is it for?
Use it to review a completed plan, test its real behavior, inspect downstream contracts, and decide whether the plan can be accepted.
Why use it?
It provides an independent acceptance check and looks for missing or unsupported claims instead of assuming the implementation is correct.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md.

Part of the mine-is-not-everyones plugin — 5 skills, 1 MCP server shipped together

Good fit Use it to review a completed plan, test its real behavior, inspect downstream contracts, and decide whether the plan can be accepted.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/6ixgodd/mine/mine-plan-review
View source ↗ 6ixGODD/mine
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 6ixGODD/mine --skill mine-plan-review
Clone the repo
git clone --depth 1 https://github.com/6ixGODD/mine

Made for: Claude Code.

Or install mine-is-not-everyones, the plugin that ships this one along with the rest of its 5 skills, 1 MCP server.

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 mine-plan-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/6ixgodd/mine/mine-plan-review.svg)](https://agentmods.dev/skills/6ixgodd/mine/mine-plan-review)
Your own site
<a href="https://agentmods.dev/skills/6ixgodd/mine/mine-plan-review"><img src="https://agentmods.dev/badge/skills/6ixgodd/mine/mine-plan-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,965 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00100 $0.06965
Opus 5 $0.00050 $0.03483
Sonnet 5 $0.00020 $0.01393
Haiku 4.5 $0.00010 $0.00696

Measured 4d ago against content hash c2dbd44a4e20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mine-plan-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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (references/scan-plan-refs.sh), 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.

plugins/mine/skills/mine-plan-review/SKILL.md · 373 lines

How it starts

The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MINE Plan Review

MINE Is Not Everyone's. Act as an independent acceptance reviewer, not as the implementing agent's advocate. Try to falsify the implementation's claims. Accept only when the plan's actual contract is demonstrated end to end.

Integration: MCP tools and CLI fallback

mine-plan-review queries and transitions plan state through two paths, in this order of preference:

  1. MCP tools (preferred) - when the current Agent runtime exposes the MINE MCP server (mine mcp serve), call the typed MCP tools. They return the same DTOs as the JSON CLI and never touch the execution-graph files.
  2. JSON CLI (deterministic fallback) - when MCP is unavailable, call mine --format json commands. Never parse human output.

Never invent an MCP tool, CLI command, flag, JSON field, or lifecycle transition that the current binary does not expose. Never edit docs/plan/execution-graph.toml or docs/plan/execution-graph.md directly.

The accepted MCP tools mine-plan-review may use:

  • mine_graph_status (no arguments) - read the current revision.
  • mine_plan_show (id) - read the target node, its predecessors, and status.
  • mine_plan_accept (id, review) - transition IMPLEMENTED -> ACCEPTED and record the review report path.
  • mine_plan_reject (id, reason, review_report, compensating_plan) - evidence-bound transition from IMPLEMENTED or an objectively infeasible IN_PROGRESS Plan to REJECTED.
  • mine_plan_withdraw (id, reason) - owner-authorized retirement of an unstarted (DRAFT/BLOCKED/READY) registration into terminal WITHDRAWN (ADR-0012). Withdrawn nodes are retired: they never block workspace closure and are never revived.
  • mine_graph_validate (no arguments) - validate the graph after transitions.
  • mine_design_validate (no arguments) - confirm design references.

Operations mine-plan-review needs that are intentionally CLI-only (no MCP tool exposes them, because they rewire downstream dependencies outside the single-node accept/reject path):

Read the full file on GitHub · 373 lines

Files

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.

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. 4d ago Changed · +6 lines c2dbd44a4e20
  2. 8d ago First seen · 367 lines · 100 tokens per session scan A fd6e8861c681

Subscribe to this mod's changes

mine-plan-review is a skill published in the GitHub repository 6ixGODD/mine (17 stars, last pushed 3d ago), licensed MIT. It adds 100 tokens to every session and 6,965 once invoked, about $0.0005 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 2026-08-30.