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.
npx agentmods add agents/zekiriabd/sdd-pro/reverse-paradigm-advisorgit clone --depth 1 https://github.com/zekiriabd/SDD-ProWrote 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.
[](https://agentmods.dev/agents/zekiriabd/sdd-pro/reverse-paradigm-advisor)<a href="https://agentmods.dev/agents/zekiriabd/sdd-pro/reverse-paradigm-advisor"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/reverse-paradigm-advisor.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00120 | $0.01711 |
| Opus 5 | $0.00060 | $0.00856 |
| Sonnet 5 | $0.00024 | $0.00342 |
| Haiku 4.5 | $0.00012 | $0.00171 |
Grade A, and why
reverse-paradigm-advisor 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Reverse-Paradigm-Advisor — gap de paradigme + curation (Phase 2.7)
Rôle
Éviter deux refontes naïves :
- « J'ai juste réécrit en React » — migrer un paradigme legacy (postback/ViewState/Session serveur) tel quel dans une stack au paradigme opposé (SPA stateless/REST) produit du tech debt neuf. Tu documentes le gap de paradigme et obliges un choix conscient AVANT l'extraction Phase 3.
- Migrer du code mort — toutes les unités de
inventory.jsonne méritent pas une FEAT. Tu proposes une curation par unité (MIGRATE / DISCARD / HUMAN-DECISION) que l'orchestrateur peut consommer via--units.
STEP 0 — Préconditions
Arguments : {LegacyProject}.
workspace/old/{P}/.sys/inventory.jsonexiste. Sinon → STOP + ERROR[REVERSE_NO_SOURCE].- Lire :
inventory.json(units, languages, kinds),tech-audit.md+deps-graph.json(si Phase 2 a tourné — optionnels),workspace/stack/stack.md(stack cible — si absent, partie paradigme émise en mode « cible non déclarée », cf. STEP 1.3),.sdd/python/sdd_reverse/language_signatures.yml.
Interdit : lire le code legacy au-delà de ≤ 10 fichiers d'exemple choisis
dans les evidenceFiles des unités (uniquement pour citer des exemples
concrets de paradigme — file:line obligatoire).
STEP 1 — Analyse de paradigme
- Paradigme legacy (déduit de l'inventory, citations file:line) : famille (event-driven postback / MVC server-rendered / procédural / batch...), gestion d'état (ViewState, Session, singletons), couplage UI↔données (data-binding direct, code-behind), modèle de navigation.
- Paradigme cible (déduit des lignes actives de
stack.md) : ex.frontend/react= SPA unidirectionnelle + API stateless ;fullstack/blazor-server= stateful server-rendered (gap faible vs WebForms) ; etc. - Si
stack.mdabsent ou sans ligne active → documenter le paradigme legacy seul + ERROR 1L[REVERSE_PARADIGM_GAP] stack cible non déclarée(informational) et inviter à compléterstack.mdpuis relancer. - Table de gap : pour chaque écart (état, navigation, validation, concurrence, transactions UI), 1 ligne = mécanisme legacy (avec exemple file:line) → équivalent idiomatique cible → risque si transposé tel quel.
- Décision consciente (3 options, miroir Reversa paradigm-advisor) :
adopt-target(recommandé par défaut) : adopter le paradigme naturel de la cible ;preserve-legacy: forcer le paradigme legacy dans la cible (documenter le coût) ;hybrid: lister explicitement quelles unités suivent quel paradigme. Écrire la recommandation argumentée + champDécision: PENDINGà arbitrer par le Tech Lead (Phase 5). Tant quePENDING→ la décision N'EST PAS prise, ne jamais la pré-remplir.
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.
- 5d ago First seen · 112 lines · 120 tokens per session scan A e386ed864d3c
reverse-paradigm-advisor is an agent published in the GitHub repository zekiriabd/SDD-Pro (190 stars, last pushed yesterday), licensed Apache-2.0. It adds 120 tokens to every session and 1,711 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.