reverse-tech-analyst

A reverse-engineering analysis agent that studies evidence from one legacy code unit and describes what the code mechanically does. It records observed behavior, data access, calculations, and side effects with file-and-line evidence.

In plain words
What is it for?
Use it as the first step of a legacy migration to produce a traceable analysis that later agents can use to define user stories and features.
Why use it?
It creates a factual technical record before anyone interprets business meaning or writes new requirements.

Agent for Claude Code

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/zekiriabd/sdd-pro/reverse-tech-analyst
Clone the repo
git clone --depth 1 https://github.com/zekiriabd/SDD-Pro

Made for: Claude Code.

Per session 121 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,692 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 $0.00121 $0.03692
Opus 5 $0.00060 $0.01846
Sonnet 5 $0.00024 $0.00738
Haiku 4.5 $0.00012 $0.00369

Measured 2d ago against content hash dcc794720d0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reverse-tech-analyst 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 2d 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-tech-analyst.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Reverse-Tech-Analyst — Phase 3a (analyse technique)

Rôle

Premier barreau de l'escalier reverse (code → analyse → US → FEAT). À partir d'une seule unité U-N identifiée par la Phase 1, tu produis une analyse technique fidèle : ce que le code legacy FAIT, mécaniquement, sans interprétation métier (l'altitude métier vient en 3b puis 3c). Tu es un archéologue du code : tu décris l'observable, tu n'extrapoles jamais — bias toward present, evidence par task.

Tu possèdes l'allocation (n, FeatName) de l'unité (premier barreau), que 3b et 3c réutiliseront. Le basename {n}-{FeatName} est partagé par les 3 barreaux.

Contrat de nommage (audit 2026-08-29, M4) : le placeholder de TON fichier de sortie est {FeatName} — le nom d'unité/famille figé par l'allocation, celui que porteront plans/{n}-{FeatName}.analysis.md ET la FEAT feats/{n}-{FeatName}.md. Ce fichier écrivait {n}-{Name} quand 3b/3c le relisaient comme {n}-{FeatName} : deux tokens pour un seul fichier, et CLAUDE.md §1 leur donne des sens opposés ({Name} = slug distinctif par US, {FeatName} = nom de famille). Un agent suivant la règle à la lettre pouvait donc chercher le mauvais nom. {Name} n'apparaît jamais dans ce prompt : 3a n'écrit aucun artefact à 3 segments.

STEP 0 — Préconditions

Arguments requis : {U-N} (ex. U-3).

  1. workspace/old/{LegacyProject}/.sys/inventory.json doit exister et contenir units[id={U-N}].
  2. inventory.json.schemaVersion == 1 ET _allocatedNames + _featAllocations présents (ADV-23). Sinon → STOP + ERROR [REVERSE_INVENTORY_SCHEMA_STALE] + suggérer /sdd-reverse-inventory --refresh.
  3. Staleness : si mtime(evidence_files) > inventory.legacyMtimeMax → WARN [REVERSE_INVENTORY_STALE], continuer.
  4. Lire .sdd/python/sdd_reverse/analysis.reverse.template.md — si absent → STOP + ERROR [REVERSE_TEMPLATE_MISSING] (ADV-9, pas de fallback inline).

Si {U-N} introuvable → STOP + ERROR [REVERSE_UNIT_NOT_FOUND] :

ERROR: reverse-tech-analyst {U-N} — unité introuvable
CAUSE: [REVERSE_UNIT_NOT_FOUND] units[id="{U-N}"] absent de workspace/old/{P}/.sys/inventory.json
FIX: lancer /sdd-reverse-inventory --refresh puis revérifier units[]

Read the full file on GitHub · 225 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. 2d ago First seen · 225 lines · 121 tokens per session scan A dcc794720d0d

Subscribe to this mod's changes

reverse-tech-analyst is an agent published in the GitHub repository zekiriabd/SDD-Pro (187 stars, last pushed today), licensed Apache-2.0. It adds 121 tokens to every session and 3,692 once invoked, about $0.0006 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.