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 commands/zekiriabd/sdd-pro/sdd-reverse-fullgit 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/commands/zekiriabd/sdd-pro/sdd-reverse-full)<a href="https://agentmods.dev/commands/zekiriabd/sdd-pro/sdd-reverse-full"><img src="https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/sdd-reverse-full.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 | $0.00156 | $0.04999 |
| Opus 5 | $0.00078 | $0.02499 |
| Sonnet 5 | $0.00031 | $0.01000 |
| Haiku 4.5 | $0.00016 | $0.00500 |
Grade A, and why
sdd-reverse-full 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdd-reverse-full {LegacyProject} [--minimal] [--skip-audit] [--skip-paradigm] [--skip-synth] [--with-parity] [--skip-ui] [--skip-review] [--skip-questions] [--interactive] [--skip-status] [--synth-level essentiel|complet|detaille] [--units U-1,U-2,...] [--max-parallel N] [--no-cache] [--sequential] [--json]
Rôle
Pipeline complet de reverse engineering Phase 0→5 sur un projet legacy. Séquence des commandes sans spawn d'agent direct — chaque commande appelée spawn son propre agent identifiable (séparation responsabilités).
Refonte 2026-06-13 (décision Tech Lead) — quasi-tout par défaut, SAUF parité. Avant cette date,
--with-paradigm/--with-parity/--with-questions/--with-synthétaient tous opt-in. Désormais audit + paradigm + synth + review + UI + questions + status s'exécutent par défaut (opt-out--skip-*ou--minimal). Exception : la parité (Phase 3.8) reste opt-in via--with-parity(décision Tech Lead 2026-06-13 — non désirée par défaut, et ses.featurevont dansworkspace/parity/, JAMAIS dansqa/qui est réservé aux tests). Les anciens flags--with-paradigm|synth|questionsrestent acceptés en alias no-op (rétro-compat) ;--with-parityest, lui, fonctionnel.
Audit 2026-06-09/10 : --skip-crosscut retiré (C3 — le crosscut Librairies + Database est OBLIGATOIRE, jamais skippable). --allow-low retiré (C9 — voie officielle :
check_reverse_feat_for_full.py --allow-reverse-lowcôté /sdd-full).
Args
| Arg | Type | Défaut | Description |
|---|---|---|---|
{LegacyProject} |
requis | — | Sous-dossier workspace/old/ |
--minimal |
flag | off | Mode lean : équivaut à --skip-paradigm --skip-synth --skip-questions. Garde le cœur (init+inventory+audit+extraction+crosscut+review+UI+status). Pour un run rapide / itératif |
--skip-audit |
flag | off (phase active) | Saute Phase 2 (tech audit) — perd l'enrichissement DB schema |
--skip-paradigm |
flag | off (phase active) | Saute Phase 2.7 (gap paradigme + curation MIGRATE/DISCARD/HUMAN-DECISION) |
--skip-synth |
flag | off (phase active) | Saute Phase 3.7 (synthèse système : C4 + ERD + soul.md, déterministe) |
--with-parity |
flag | off | Opt-in (décision Tech Lead 2026-06-13 — parité exclue par défaut) : active Phase 3.8 (specs Gherkin de parité comportementale → workspace/parity/, jamais dans qa/) |
--skip-ui |
flag | off (phase active) | Saute Phase 4 (génération des interfaces / mockups HTML) |
--skip-review |
flag | off (phase active) | Saute Phase 3.6 (revue de complétude back, reverse-completeness-reviewer) |
--skip-questions |
flag | off (phase active) | Saute Phase 3.9 (génération questions.md — boucle de validation humaine) |
--interactive |
flag | off | Ferme la boucle humaine dans le run (C3) : à Phase 3.9, pose les questions ouvertes en session + ingère les réponses, au lieu de s'arrêter sur questions.md. Sans effet en batch/CI (dégrade en génération seule) |
--skip-status |
flag | off (phase active) | Saute le diagnostic final /sdd-reverse-status |
--synth-level |
essentiel|complet|detaille |
complet |
Niveau de synthèse passé à /sdd-reverse-synth (ignoré si --skip-synth) |
--units U-N,U-M |
flag | toutes | Limite l'extraction (Phase 3 + 4 + parité) à un sous-ensemble d'unités |
--max-parallel N |
flag | 3 | Borne de parallélisme Phase 3 (range 1-12, aligné ownership.md §5) |
--no-cache |
flag | off | Force la ré-extraction de toutes les unités (ignore extraction-cache.json, L5) |
--sequential |
flag | off | Force la Phase 3 séquentielle (mode legacy ADV-2, désactive le parallélisme) |
--json |
flag | off | Émet le rapport final en JSON |
--with-audit|paradigm|synth|parity|questions |
alias no-op | — | Déprécié : ces phases sont actives par défaut. Acceptés sans effet (rétro-compat) |
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 · 262 lines · 156 tokens per session scan A ac5ccb7bd832
sdd-reverse-full is a command published in the GitHub repository zekiriabd/SDD-Pro (191 stars, last pushed 2d ago), licensed Apache-2.0. It adds 156 tokens to every session and 4,999 once invoked, about $0.0008 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.