parity-check

parity-check is an agent for coding agents from helderberto/agent-skills. It costs 38 tokens per session (729 once invoked), scanned A, original, MIT.

A migration auditor that compares a legacy codebase with its replacement to find missing or changed behavior. It checks branches, interactions, derived values, safeguards, error paths, translations, and child components.

In plain words
What is it for?
Use it to compare specific features such as a profile form or checkout flow, classify gaps as missing, partial, or different, and report where they occur.
Why use it?
It catches functionality that can be lost or altered when software is moved to a new implementation.

Agent

Part of the hb plugin — 40 skills, 6 agents shipped together

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 agents/helderberto/agent-skills/parity-check
Clone the repo
git clone --depth 1 https://github.com/helderberto/agent-skills

Or install hb, the plugin that ships this one along with the rest of its 40 skills, 6 agents.

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 parity-check

README.md
[![agentmods](https://agentmods.dev/badge/agents/helderberto/agent-skills/parity-check.svg)](https://agentmods.dev/agents/helderberto/agent-skills/parity-check)
Your own site
<a href="https://agentmods.dev/agents/helderberto/agent-skills/parity-check"><img src="https://agentmods.dev/badge/agents/helderberto/agent-skills/parity-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 729 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 $0.00038 $0.00729
Opus 5 $0.00019 $0.00365
Sonnet 5 $0.00008 $0.00146
Haiku 4.5 $0.00004 $0.00073

Measured 4d ago against content hash 3bb6ef746f03, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

parity-check 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.

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.

agents/parity-check.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Require: source path, target path, scope (e.g. "user profile form", "checkout flow"). Ask if missing.

Method

1. Map source behaviors

Grep for scope keywords, then Read each file. Extract every discrete behavior — don't skim:

  • Branches: every if/else, ternary, switch case, template conditional — each branch is a separate behavior
  • Event handlers: user interactions, lifecycle hooks, subscriptions
  • Derived state: computed values, transformations, formatting (dates, URLs, labels)
  • Guards: null/undefined checks, empty states, fallback values, default branches
  • Error paths: try/catch, .catch(), error states, error messages
  • I18n: every user-visible string (copy exact text)
  • Child components: what's invoked and what props/data flows down

2. Map target behaviors

Same as above for the target path. Note file:line for each behavior found.

3. Diff and report

Compare source → target. Classify each gap:

  • MISSING: exists in source, absent in target
  • PARTIAL: exists but incomplete (e.g. missing an else branch, fewer switch cases)
  • DIFFERS: exists in both but logic diverges

Skip items where target has a comment explaining intentional omission.

Report format

## Parity Audit: [Scope]

Source: [framework] — [path] ([N] files)
Target: [framework] — [path] ([N] files)

### Gaps

| # | Category | Description | Source ref | Target ref | Status |
|---|----------|-------------|-----------|------------|--------|
| 1 | behavior | [what's missing] | file:line | file:line or — | MISSING/PARTIAL/DIFFERS |

Categories: behavior, edge-case, error-handling, i18n, test, subcomponent

### Summary
- **Gaps**: X missing, Y partial, Z differs
- **Risk**: HIGH / MEDIUM / LOW
- **Priority fixes**: [ordered list]

Rules

  • Read-only. Never modify files.
  • Source is truth. Must exist in target unless intentionally omitted (with comment).
  • Exact strings for i18n. Copy literal text, don't paraphrase.
  • Broad scope? Summary table first, offer to deep-dive per item.

Read the full file on GitHub · 82 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. 4d ago First seen · 82 lines · 38 tokens per session scan A 3bb6ef746f03

Subscribe to this mod's changes

parity-check is an agent published in the GitHub repository helderberto/agent-skills (14 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 729 once invoked, about $0.0002 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.