claude-piv-skeleton: Command for Claude Code

.claude/commands/validation/learn.md

learn is a command for Claude Code from plipowczan/claude-piv-skeleton. It costs 12 tokens per session (1,477 once invoked), scanned A, original, MIT.

A command that reviews past code-review results to find repeated problems and possible improvements.

In plain words
What is it for?
Use it to analyze all reviews, the latest few reviews, or one selected review file.
Why use it?
It turns individual review comments into patterns that can improve rules, checks, and development guidance.

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/learn.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 learn

README.md
[![agentmods](https://agentmods.dev/badge/commands/plipowczan/claude-piv-skeleton/learn.svg)](https://agentmods.dev/commands/plipowczan/claude-piv-skeleton/learn)
Your own site
<a href="https://agentmods.dev/commands/plipowczan/claude-piv-skeleton/learn"><img src="https://agentmods.dev/badge/commands/plipowczan/claude-piv-skeleton/learn.svg" alt="Measured on agentmods" height="20"></a>
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 1,477 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 $0.00012 $0.01477
Opus 5 $0.00006 $0.00739
Sonnet 5 $0.00002 $0.00295
Haiku 4.5 $0.00001 $0.00148

Measured 7d ago against content hash ebfc45086635, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

learn 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 7d 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/learn.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learning Analysis: Extract Insights from Code Reviews

Purpose

Analyze code review artifacts to:

  1. Extract structured data from review outputs (issues, patterns, recommendations)
  2. Identify recurring patterns across multiple reviews
  3. Generate improvement suggestions for rules, validation, and skills
  4. Update learning metrics to track progress over time

Prerequisites

  • At least one code review artifact exists in .claude/agents/reviews/
  • Code review artifacts follow standard format (from /piv-speckit:code-review)

Arguments

Argument Description Example
--last=N Analyze last N reviews (default: all) --last=5
--review=path Analyze specific review --review=.claude/agents/reviews/code-review-feature-x.md

Process

Step 1: Discover Review Artifacts

# Find all review artifacts
ls -la .claude/agents/reviews/*.md

List all available reviews and their dates.

Step 2: Read and Parse Each Review

For each review artifact, extract:

From ## Issues Found section:

  • Issue severity (Critical/High/Medium/Low)
  • Issue title and description
  • File and line number (if provided)
  • Suggested fix (if provided)

From ## Detailed Analysis section:

  • Category (Logic Errors, Security, Performance, Code Quality)
  • Pass/Fail status
  • Specific findings

From ## Positive Findings section:

  • Good patterns that worked
  • Practices to encourage

From ## Recommendations section:

  • Suggested improvements
  • Future enhancements

From ## Project Standards Compliance section:

  • Which rules were followed
  • Which rules were violated

Metadata:

  • PIV Quality Score
  • Date
  • Feature name

Step 3: Identify Patterns

Recurring Issues:

  • Group issues by category and type
  • Count occurrences across reviews
  • Flag issues appearing in 2+ reviews as "recurring"

Anti-Patterns:

  • Identify code patterns that repeatedly cause issues
  • Document with examples from reviews

Read the full file on GitHub · 231 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. 7d ago First seen · 231 lines · 12 tokens per session scan A ebfc45086635

Subscribe to this mod's changes

learn is a command published in the GitHub repository plipowczan/claude-piv-skeleton (4 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 1,477 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 2026-08-31.