plan-review

A review workflow that compares a proposed implementation plan with the current codebase. It reads the plan and related source files, checks proposed changes against existing code, and produces a self-contained HTML review.

In plain words
What is it for?
Use it to review plans involving code, public interfaces, configuration, data migrations, tests, or release steps, and to document whether the current project supports the proposed work.
Why use it?
It helps reveal missing files, affected dependencies, incorrect assumptions, absent tests, and risks before implementation starts. A compact quick mode is available when explicitly requested.

Command

▶ NEW Visual Explainer Skill: HTML Plans/Summaries (Claude Code Example) AI Coding Daily · about nicobailon/visual-explainer · on YouTube →
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 commands/nicobailon/visual-explainer/plan-review
Clone the repo
git clone --depth 1 https://github.com/nicobailon/visual-explainer
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 484 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 $0.00012 $0.00484
Opus 5 $0.00006 $0.00242
Sonnet 5 $0.00002 $0.00097
Haiku 4.5 $0.00001 $0.00048

Measured 2d ago against content hash 82273e0c12d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

plugins/visual-explainer/commands/plan-review.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Load the visual-explainer skill and generate a self-contained HTML plan review.

Quick mode

Only use quick mode when $@ contains the literal --quick flag. Remove the flag before resolving the plan input. Complete the same code research and verification below, then read ./quick/README.md and ./quick/schema.json and express the review as a compact spec. In Pi, call visual_explainer with action: "render_quick". In other harnesses, run the local ./quick/render.mjs fallback. If the review does not fit the schema, validation fails, or rendering errors, generate complete HTML and use the normal render flow. Without --quick, preserve full HTML behavior.

Inputs

Use $@ as the plan path or plan text. If no path is given, ask for the plan.

Data gathering before HTML

Read the plan in full. Extract goals, assumptions, proposed files/functions/types, migrations, tests, rollout/release notes, and explicit risks. Read every referenced file, plus importers/dependents that may be affected. Use ripgrep for existing patterns, similar implementations, public API boundaries, config/schema files, and tests.

Source verification

For each proposed change, verify whether referenced files/functions/types exist, whether current behavior matches the plan, what ripple effects are missing, and whether the proposed test coverage fits the current test style. Cite plan sections and file:line evidence.

Required page sections

  1. Plan summary: problem, core idea, scope.
  2. Accuracy verdict: correct, stale, risky, unsupported, missing.
  3. Current architecture: diagram of affected subsystem only.
  4. Proposed architecture: matching visual diff against current state.
  5. Gap/risk matrix: correctness, tests, API, data model, UX, security/privacy, performance, maintainability, release.
  6. File-by-file review: proposed edits, current reality, recommendation.
  7. Better plan: concrete corrections or simplifications.
  8. Decision: approve, revise, or reject with rationale.

Read the full file on GitHub · 38 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. 2d ago First seen · 38 lines · 12 tokens per session scan A 82273e0c12d1

Subscribe to this mod's changes

plan-review is a command published in the GitHub repository nicobailon/visual-explainer (9,621 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 484 once invoked, about $0.0001 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.