claude-piv-skeleton: Command for Claude Code

.claude/commands/validation/system-review.md

system-review is a command for Claude Code from plipowczan/claude-piv-skeleton. It costs 7 tokens per session (1,963 once invoked), scanned A, original, MIT.

A process review that compares a written implementation plan with the report of what was actually done. It evaluates the planning and execution process, rather than the code itself.

In plain words
What is it for?
Use it after a feature is implemented to assess plan quality, execution differences, validation effectiveness, and process improvements.
Why use it?
It shows where a plan was incomplete or inaccurate and what caused rework, delays, or weak validation.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths.

This is plipowczan/claude-piv-skeleton's own configuration. It tells Claude Code how to work on claude-piv-skeleton itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-piv-skeleton configures →

Part of the piv-speckit plugin — 6 skills, 16 commands shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to plipowczan/claude-piv-skeleton. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/plipowczan/claude-piv-skeleton/main/.claude/commands/validation/system-review.md
Clone the repo
git clone --depth 1 https://github.com/plipowczan/claude-piv-skeleton

Made for: Claude Code.

Or install piv-speckit, the plugin that ships this one along with the rest of its 6 skills, 16 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 system-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/plipowczan/claude-piv-skeleton/system-review/github.svg)](https://agentmods.dev/commands/plipowczan/claude-piv-skeleton/system-review)
Your own site
<a href="https://agentmods.dev/commands/plipowczan/claude-piv-skeleton/system-review"><img src="https://agentmods.dev/badge/commands/plipowczan/claude-piv-skeleton/system-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 system-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/plipowczan/claude-piv-skeleton/system-review"><img src="https://agentmods.dev/badge/commands/plipowczan/claude-piv-skeleton/system-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,963 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 $0.00007 $0.01963
Opus 5 $0.00003 $0.00981
Sonnet 5 $0.00001 $0.00393
Haiku 4.5 $0.00001 $0.00196

Measured 10d ago against content hash b18fa4a9cbb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

system-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 10d 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.

.claude/commands/validation/system-review.md · 334 lines

How it starts

The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Review: Process Improvement Analysis

Inputs

Plan: $ARGUMENTS_1 (path to plan) Execution Report: $ARGUMENTS_2 (path to execution report)

Example:

/piv:system-review .claude/agents/plans/example-feature-validation.md .claude/agents/execution-reports/example-feature-validation-report.md

Purpose

Analyze the implementation process to identify:

  • Plan quality and completeness
  • Execution efficiency
  • Validation effectiveness
  • Process improvements needed
  • Patterns to document

This is NOT about the code quality (that's code-review). This is about improving the PIV PROCESS.

Analysis Process

1. Compare Plan vs Actual

Read the plan:

  • What was planned?
  • What patterns were documented?
  • What validation commands were specified?

Read the execution report:

  • What was actually implemented?
  • What deviations occurred?
  • What challenges were encountered?
  • What was the plan quality score?

Identify gaps:

  • What was missing from the plan?
  • What was inaccurate in the plan?
  • What caused rework or delays?

2. Analyze Plan Quality

Completeness:

  • Were all necessary files listed?
  • Were all patterns documented?
  • Were all validation commands included?
  • Was context sufficient?

Accuracy:

  • Were code examples correct?
  • Were pattern references accurate?
  • Were file paths correct?
  • Were dependencies documented?

One-Pass Implementation:

  • Did the plan enable one-pass implementation?
  • If not, why not?
  • What was missing?

Score Plan Quality:

  • Context completeness: X/10
  • Accuracy: X/10
  • Implementation readiness: X/10
  • Overall Plan Quality: X/10

3. Analyze Execution Efficiency

Time Tracking:

  • Planning time: X hours
  • Implementation time: X hours
  • Validation time: X hours
  • Total time: X hours

Estimated vs Actual:

  • Estimated: X hours
  • Actual: X hours
  • Variance: X%

Rework Analysis:

  • How much rework was needed?
  • What caused the rework?
  • Could it have been prevented?

Read the full file on GitHub · 334 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. 10d ago First seen · 334 lines · 7 tokens per session scan A b18fa4a9cbb5

Subscribe to this mod's changes

system-review is a command published in the GitHub repository plipowczan/claude-piv-skeleton (4 stars, last pushed 7mo ago), licensed MIT. It adds 7 tokens to every session and 1,963 once invoked, about $0.0000 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.