What is sdd-reverse-parity?

A command that creates Gherkin feature files describing whether a rebuilt application behaves like a legacy one. Gherkin is a plain-text format for executable behavior scenarios, and a FEAT is a numbered reverse-engineering feature specification.

Generating one parity test file per user story, writing a parity map, and validating the files with the project's deterministic validator. It reports findings without blocking the workflow.

It adds runtime behavior checks to reverse-engineering work, which static code extraction alone cannot verify.

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

Your own site

<a href="https://agentmods.dev/commands/zekiriabd/sdd-pro/sdd-reverse-parity"><img src="https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/sdd-reverse-parity.svg" alt="Measured on agentmods" height="20"></a>

Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 795 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	$0.00074	$0.00795
Opus 5	$0.00037	$0.00398
Sonnet 5	$0.00015	$0.00159
Haiku 4.5	$0.00007	$0.00080

Measured 7d ago against content hash 145ddb6d5e02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sdd-reverse-parity 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/sdd-reverse-parity.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdd-reverse-parity {n} [--json]

Rôle

Dériver des AC d'une FEAT reverse des scénarios Gherkin exécutables qui définissent l'équivalence comportementale legacy ↔ application régénérée. Comble l'angle mort « extraction statique, pas de validation runtime » : après /sdd-full, le runner BDD de la stack qa/* peut exécuter ces .feature contre la nouvelle application pour prouver la parité.

Args

Arg	Type	Description
`{n}`	requis	Numéro de la FEAT reverse (`workspace/feats/{n}-{FeatName}.md`)
`--json`	flag	Émet le verdict en JSON

Pré-conditions

workspace/feats/{n}-{FeatName}.md existe et porte generated-by: sdd-reverse. Sinon → ERROR [REVERSE_UNIT_NOT_FOUND].
≥ 1 US workspace/us/{n}-{m}-*.md existe (escalier 3b a tourné).

Actions

Spawn unique Agent(reverse-parity-inspector) avec arg = {n}.

L'agent dérive les scénarios (1 .feature par US, tags @AC-N), écrit parity-map.md, puis valide via :

python .sdd/python/sdd_reverse_scripts/validate_parity_features.py \
    --feat-path workspace/feats/{n}-{FeatName}.md \
    --parity-dir workspace/parity/feat-{n} --json

(max 3 itérations de correction sur [REVERSE_PARITY_INVALID]).

Sortie

workspace/parity/feat-{n}/
├── {m}-{Slug}.feature
└── parity-map.md

Couverture (coverage.verdict, ASCII) : complete | partial — jamais bloquant ([REVERSE_PARITY_COVERAGE_GAP] informational ; les AC non dérivables restent listés, jamais comblés par invention).

Émission chat

[REVERSE] Parité FEAT {n} : {S} scénarios, {K}/{N} AC couverts. (PROGRESS%)

Anti-derive

Une seule FEAT par invocation
No-spawn d'agent autre que reverse-parity-inspector
.feature stack-agnostiques (aucune techno cible nommée — step definitions en aval)
Verdict informational — ne bloque ni Phase 4 ni /sdd-full
Idempotent : relancer écrase feat-{n}/

Read the full file on GitHub · 71 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.

7d ago First seen · 71 lines · 74 tokens per session scan A 145ddb6d5e02

Subscribe to this mod's changes

sdd-reverse-parity is a command published in the GitHub repository zekiriabd/SDD-Pro (191 stars, last pushed 3d ago), licensed Apache-2.0. It adds 74 tokens to every session and 795 once invoked, about $0.0004 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.

Backend and APIs E2E testing Testing

cloudflare-durable-objects:setup

Interactive Durable Objects project initialization. Scaffolds new DO project with proper bindings, migrations, and boilerplate code.

secondsky/claude-skills · 32 tokens

api-runtime-verify

Verify an implemented backend HTTP surface at runtime: per route, record the request actually made, the HTTP status, the response content-type, and the observed body shape, assert each response against the slice's acceptance behavior, classify the findings, and decide a PASS/FAIL/BLOCKED runtime gate. The probe's real…

Mozurok/fhorja.dev · 216 tokens

SDD-Pro: Command for Claude Code