starting-a-reverse-eng

starting-a-reverse-eng is a skill for Claude Code, Codex from zekiriabd/SDD-Pro. It costs 108 tokens per session (1,201 once invoked), scanned A, original, Apache-2.0.

A guided workflow for examining a legacy codebase and turning its behavior into documented software requirements. Legacy means an older system that may be difficult to understand or change.

In plain words
What is it for?
Inventorying old projects, documenting their features, and preparing a legacy system for migration or reconstruction.
Why use it?
It gives teams a structured way to map unfamiliar code before migrating or rewriting it, while stopping when the required source code is missing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Inventorying old projects, documenting their features, and preparing a legacy system for migration or reconstruction.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zekiriabd/sdd-pro/starting-a-reverse-eng
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 zekiriabd/SDD-Pro --skill starting-a-reverse-eng
Clone the repo
git clone --depth 1 https://github.com/zekiriabd/SDD-Pro

Made for: Claude Code, Codex.

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 starting-a-reverse-eng

README.md
[![agentmods](https://agentmods.dev/badge/skills/zekiriabd/sdd-pro/starting-a-reverse-eng.svg)](https://agentmods.dev/skills/zekiriabd/sdd-pro/starting-a-reverse-eng)
Your own site
<a href="https://agentmods.dev/skills/zekiriabd/sdd-pro/starting-a-reverse-eng"><img src="https://agentmods.dev/badge/skills/zekiriabd/sdd-pro/starting-a-reverse-eng.svg" alt="Measured on agentmods" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,201 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 pass 7 Sept 2026
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00108 $0.01201
Opus 5 $0.00054 $0.00600
Sonnet 5 $0.00022 $0.00240
Haiku 4.5 $0.00011 $0.00120

Measured 4d ago against content hash 1e2ba8e6d127, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

starting-a-reverse-eng 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.

.sdd/skills/starting-a-reverse-eng/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill — Starting a Reverse Engineering workflow

Quand cette skill se déclenche

Triggers stricts (D5 — conservatisme délibéré pour éviter interception abusive) :

  • « reverse engineering »
  • « convertir l'ancien système »
  • « migrer le legacy »
  • « j'ai un legacy »
  • « workspace/old »
  • « convertir un projet ASPX/Java/PHP/Delphi existant »
  • « extraire les FEATs d'un projet legacy »

Ne PAS déclencher sur :

  • « vieux code », « ancien code » (trop vague)
  • « rewrite this » (peut être refactor SDD_Pro standard)
  • « migrer vers .NET 9 » (c'est une montée de version, pas du reverse)

Routage

Si le trigger matche, route vers le workflow reverse engineering au lieu de laisser l'agent improviser un audit de code ou un rewrite ad-hoc :

  1. Vérifier précondition source (§0 design doc) :
    • Le code source legacy doit être dans workspace/old/{LegacyProject}/
    • Si binaire-only → STOP + escalade Tech Lead (hors-scope V3)
  2. Phase 0 (humain) : confirmer que les fichiers sont déposés
  3. /sdd-reverse-init {LegacyProject} (Phase 0 bootstrap)
  4. /sdd-reverse-inventory {LegacyProject} (Phase 1 cartographie)
  5. Lire workspace/old/{LegacyProject}/.sys/inventory.md pour identifier les unités U-N pertinentes
  6. Pour chaque unité voulue : /sdd-reverse U-N (Phase 3, séquentiel)
  7. Phase 5 (humain) : Tech Lead revue + complétion ## Project Config des FEATs
  8. Pré-/sdd-full : python .sdd/python/sdd_reverse_scripts/check_reverse_feat_for_full.py --feat-path workspace/feats/{n}-*.md
  9. /sdd-full {n} (pipeline SDD_Pro standard — workflow EXISTANT inchangé)

Décisions architecturales verrouillées (D1-D7)

À rappeler au Tech Lead s'il pose des questions :

  • D1 Language-agnostic : détection auto via language_signatures.yml. 9+ langages supportés MVP. Confidence cap par langage dans le YAML, jamais hardcodé.
  • D2 Chunking fin : 1 FEAT = 1 unité fonctionnelle. 1-4 FEATs par page. Grid CRUD = 1 FEAT, modale confirm = 0 FEAT.
  • D3 Tech audit : optionnel, skippable, informational. Hors MVP (V2).
  • D4 Loader séparé : loader.reverse.yml autonome. Aucune édition de loader.yml.
  • D5 Triggers stricts : cette skill ne hijacke pas sur « vieux code » générique.
  • D6 Output français : FEATs, inventory.md, tech-audit.md en FR. Commentaires evidence/confidence en EN.
  • D7 DB schema Phase 1 : extraction basique en Phase 1, source de vérité entities. Si absent → entities dégradées à confidence: medium.

Read the full file on GitHub · 77 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 · 77 lines · 108 tokens per session scan A 1e2ba8e6d127

Subscribe to this mod's changes

starting-a-reverse-eng is a skill published in the GitHub repository zekiriabd/SDD-Pro (191 stars, last pushed 5d ago), licensed Apache-2.0. It adds 108 tokens to every session and 1,201 once invoked, about $0.0005 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 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens