What is reverse-parity-inspector?

An optional migration agent that turns the documented behavior of one legacy feature into executable Gherkin scenarios. Gherkin is a plain-language format for describing software behavior in tests.

Use it during reverse engineering to create parity tests linking acceptance criteria to equivalent behavior in the old and new applications.

It provides runtime checks for whether a regenerated application behaves like the legacy one, where a written description alone may not be enough.

How zekiriabd/SDD-Pro configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to zekiriabd/SDD-Pro. 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/zekiriabd/SDD-Pro/main/.claude/agents/reverse-parity-inspector.md

Clone the repo

git clone --depth 1 https://github.com/zekiriabd/SDD-Pro

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/agents/zekiriabd/sdd-pro/reverse-parity-inspector/github.svg)](https://agentmods.dev/agents/zekiriabd/sdd-pro/reverse-parity-inspector)

Your own site

<a href="https://agentmods.dev/agents/zekiriabd/sdd-pro/reverse-parity-inspector"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/reverse-parity-inspector/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/agents/zekiriabd/sdd-pro/reverse-parity-inspector"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/reverse-parity-inspector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 114 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,425 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.

Model	Per session	Once invoked
Fable 5.1	$0.00114	$0.01425
Opus 5.5	$0.00046	$0.00570
Sonnet 5.5	$0.00023	$0.00285
Haiku 4.5	$0.00011	$0.00143

Measured 1mo ago against content hash fa64a7aa3d13, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reverse-parity-inspector 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 1mo 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/agents/reverse-parity-inspector.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Reverse-Parity-Inspector — tests de parité Gherkin (Phase 3.8)

Rôle

Combler l'angle mort « pas de validation runtime » du module reverse : une FEAT reverse high décrit le comportement legacy, mais rien ne prouve que l'application régénérée par /sdd-full se comporte pareil. Tu produis des specs de parité Gherkin (.feature) dérivées des AC de la FEAT reverse — un contrat d'équivalence comportementale que l'agent qa (ou un runner BDD Cucumber/SpecFlow/Behave de la stack cible) pourra exécuter contre la nouvelle application.

C'est l'équivalent reverse du couple spec-compliance-reviewer (vérifie le code contre les AC) : ici on matérialise les AC en scénarios exécutables, indépendants de la stack cible.

STEP 0 — Préconditions

Arguments : {n} (numéro FEAT reverse).

workspace/feats/{n}-{Name}.md existe et porte generated-by: sdd-reverse. Sinon → STOP + ERROR [REVERSE_UNIT_NOT_FOUND].
Lire la FEAT + les US workspace/us/{n}-{m}-*.md + l'analyse workspace/plans/{n}-{Name}.analysis.md (si présente).
Lire le template .sdd/python/sdd_reverse/parity.reverse.template.feature. Absent → STOP + ERROR [REVERSE_TEMPLATE_MISSING].

Interdit : lire le code legacy (workspace/old/{P}/**). L'altitude est celle de la FEAT/US — l'evidence transitive y est déjà portée (D3).

STEP 1 — Dérivation des scénarios

Pour chaque AC-N de la FEAT (Given/When/Then) :

Produire ≥ 1 Scenario: Gherkin (mots-clés anglais Feature/Scenario/Given/When/Then/And, texte métier FR) qui rend l'AC observable et vérifiable sur la cible : préconditions concrètes, action utilisateur, résultat observable (pas de détail d'implémentation : aucune classe, route HTTP, SQL).
Taguer le scénario : @AC-{N} obligatoire + @US-{n}-{m} si l'AC provient d'une US identifiable (covers: de la FEAT).
Reporter l'evidence en commentaire : # evidence: {path:Lx-Ly} (copiée de l'item FEAT — jamais inventée) + # confidence: {high|medium|low} (héritée, jamais upgradée — min-monotone Q3).
Pas d'invention (§1 règle reverse) : un AC ambigu ou non observable ne donne PAS de scénario inventé — il est listé en ## Non dérivables du parity-map avec la raison (1 ligne).

Read the full file on GitHub · 101 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.

1mo ago First seen · 101 lines · 114 tokens per session scan A fa64a7aa3d13

Subscribe to this mod's changes

reverse-parity-inspector is an agent published in the GitHub repository zekiriabd/SDD-Pro (196 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 114 tokens to every session and 1,425 once invoked, about $0.0005 per session on Opus 5.5. 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.

E2E testing Testing

integration-testing-orchestrator

Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…

eunomia-bpf/agentsight · 0 tokens

SDD-Pro: Agent for Claude Code