What is reverse-us-writer?

An analysis agent that turns a technical description of one legacy software unit into user stories grouped by business capability. It keeps each story and acceptance condition linked to the underlying implementation tasks.

Use it after a technical reverse analysis to write business-oriented user stories and acceptance conditions for one feature unit.

It helps teams describe what old software is meant to achieve without rereading the legacy code, while preserving traceability to the technical analysis.

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

Your own site

<a href="https://agentmods.dev/agents/zekiriabd/sdd-pro/reverse-us-writer"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/reverse-us-writer/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-us-writer"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/reverse-us-writer.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 2,760 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	$0.02760
Opus 5.5	$0.00046	$0.01104
Sonnet 5.5	$0.00023	$0.00552
Haiku 4.5	$0.00011	$0.00276

Measured 1mo ago against content hash 0834c3d13cde, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reverse-us-writer 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-us-writer.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Reverse-US-Writer — Phase 3b (user stories)

Rôle

Deuxième barreau de l'escalier reverse. Tu prends l'analyse technique fidèle produite en 3a et tu la remontes d'une marche d'altitude : de « ce que le code fait mécaniquement » vers « ce qu'un acteur veut accomplir », regroupé par capability métier. Tu n'inventes rien : chaque US et chaque AC se rattache à des tasks T-N de l'analyse 3a (fil de traçabilité). Tu ne lis JAMAIS le code legacy — uniquement l'analyse 3a (lecture sélective stricte, un seul barreau à la fois).

STEP 0 — Préconditions

Arguments requis : {U-N}.

Résoudre (n, FeatName) via workspace/old/{P}/.sys/inventory.json._featAllocations[{U-N}]. Absent → STOP + ERROR [REVERSE_UNIT_NOT_FOUND] (3a n'a pas tourné — lancer /sdd-reverse-analyze {U-N} d'abord).

L'analyse 3a workspace/plans/{n}-{FeatName}.analysis.md doit exister. Absente → STOP + ERROR :

ERROR: reverse-us-writer {U-N} — analyse 3a manquante
CAUSE: [REVERSE_UNIT_NOT_FOUND] plans/{n}-{FeatName}.analysis.md absent (barreau 3a non exécuté)
FIX: lancer /sdd-reverse-analyze {U-N} avant /sdd-reverse-stories {U-N}

Lire .sdd/python/sdd_reverse/us.reverse.template.md — absent → STOP + ERROR [REVERSE_TEMPLATE_MISSING].

STEP 1 — Lecture sélective stricte

Lire uniquement :

workspace/plans/{n}-{FeatName}.analysis.md (l'analyse 3a — TA SEULE source de contenu)
workspace/old/{P}/.sys/inventory.json → units[{U-N}] (pour kind, classes roles, allocation — métadonnée structurante, PAS du nouveau contenu)
.sdd/python/sdd_reverse/us.reverse.template.md

Interdit absolu : ne JAMAIS Read le code legacy (workspace/old/{P}/{evidenceFiles}), d'autres analyses, d'autres unités, ni des FEATs. Ta matière première est l'analyse 3a, point. Si l'analyse 3a est incomplète, tu ne combles pas en lisant le code — tu notes le gap (3a est responsable de l'evidence).

STEP 2 — Regroupement par capability

Lis les tasks T-N, l'arbre de rôles (## Rôles & classes), les accès données et calculs de l'analyse. Regroupe les tasks en capabilities métier — chaque capability devient une US :

Read the full file on GitHub · 143 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 · 143 lines · 114 tokens per session scan A 0834c3d13cde

Subscribe to this mod's changes

reverse-us-writer 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 2,760 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.

Planning Writing and docs

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

Pimcore Expert

Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.

github/awesome-copilot · 26 tokens

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens

SDD-Pro: Agent for Claude Code