A post-implementation check that compares an executed development plan with its success criteria and produces a validation report.

Use it after implementation to run the plan's checks against the working tree and audit the resulting changes.

It reveals missing steps, deviations, or unresolved issues before a feature is considered complete.

validate — Skill for Claude Code by juicesharp

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 juicesharp/rpiv-mono --skill validate

Clone the repo

git clone --depth 1 https://github.com/juicesharp/rpiv-mono

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/validate/github.svg)](https://agentmods.dev/skills/juicesharp/rpiv-mono/validate)

Your own site

<a href="https://agentmods.dev/skills/juicesharp/rpiv-mono/validate"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/validate/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/juicesharp/rpiv-mono/validate"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/validate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,822 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 warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 204
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00064	$0.04822
Opus 5	$0.00032	$0.02411
Sonnet 5	$0.00013	$0.00964
Haiku 4.5	$0.00006	$0.00482

Measured today against content hash c1a85c5078d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

validate 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 today.

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.

packages/rpiv-pi/skills/validate/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validate

You are tasked with validating that an implementation plan was correctly executed, verifying all success criteria and identifying any deviations or issues.

Input

User input (raw): $ARGUMENTS

Expected shape: an optional plan path (usually under .rpiv/artifacts/plans/), optionally followed by --goal <path> (the user's original brief, captured verbatim at run start), --baseline <path> (the run-start snapshot of paths that were ALREADY dirty before the run touched anything — a JSON file with a paths array), --scope <path> (the workflow scope floor's verdict JSON — { verdict, findings: [{ detail, where }] } — recording writes outside the plan's declared write-set for you to adjudicate), and/or --acceptance <path> (the goal-derived acceptance inventory — items: frontmatter, ids a1…, each with a runnable evidence command or a manual procedure — frozen before planning; you EXECUTE it in Step 2.10). Peel the --goal, --baseline, --scope, and --acceptance flags first; what remains is the plan path. Only if the user input above is empty, or no plan path remains after peeling, branch on the recent-plans list in the Metadata block.

Metadata

node "${SKILL_DIR}/../_shared/now.mjs"
echo
node "${SKILL_DIR}/../_shared/git-context.mjs"
echo
echo "### recent (read only in case of empty user input)"
echo "recent plans:"
node "${SKILL_DIR}/../_shared/list-recent.mjs" .rpiv/artifacts/plans 10

Steps

Step 1: Input Handling and Context Discovery

When invoked:

Determine context — fresh or existing conversation?
- If existing: review what was implemented in this session, then proceed to Step 2.
- If fresh: continue with the substeps below.
Locate the plan:
- If plan path provided, use it.
- Otherwise, branch on the recent plans: listing in the Metadata block:
  - Empty — no plans under .rpiv/artifacts/plans/; ask the user for a path in prose.
  - Exactly one entry — confirm with ask_user_question: "Validate this plan?" with options "Validate <filename> (Recommended)" and "Pick a different path".
  - Two or more entries — present the top 4 filenames as ask_user_question options. The tool automatically appends a Type something. free-text row; do not list it manually.

Read the full file on GitHub · 249 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.

templates/validation.md 2.4 KB

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.

today Changed · +14 lines c1a85c5078d3
9d ago First seen · 235 lines · 64 tokens per session scan A 096f27c2a476

Subscribe to this mod's changes

validate is a skill published in the GitHub repository juicesharp/rpiv-mono (765 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 4,822 once invoked, about $0.0003 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

validate