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.
curl -O https://raw.githubusercontent.com/zekiriabd/SDD-Pro/main/.claude/commands/sdd-reverse-questions.mdgit 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-questions)<a href="https://agentmods.dev/commands/zekiriabd/sdd-pro/sdd-reverse-questions"><img src="https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/sdd-reverse-questions.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 5.1 | $0.00127 | $0.01413 |
| Opus 5 | $0.00063 | $0.00707 |
| Sonnet 5 | $0.00025 | $0.00283 |
| Haiku 4.5 | $0.00013 | $0.00141 |
Grade A, and why
sdd-reverse-questions 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 8d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdd-reverse-questions {LegacyProject} [--ingest] [--interactive] [--json]
Rôle
Fermer la boucle Tech Lead ↔ reverse : les gaps détectés par les reviewers
(aujourd'hui informationnels et dispersés dans .sys/modules/*/) deviennent
des questions structurées (Q-N, impact, evidence) dans un fichier unique ;
les réponses humaines sont ré-injectées dans les FEATs avec traçabilité
(<!-- human-validated: Q-N -->) — c'est la voie officielle pour faire monter
un item medium/low en high (unique exception au cap D1, tracée).
Args
| Arg | Type | Description |
|---|---|---|
{LegacyProject} |
requis | Sous-dossier workspace/old/ |
--ingest |
flag | Ré-injecte les blocs Réponse: remplis au lieu de générer |
--interactive |
flag | Clôture la boucle en un run (C3) : génère questions.md, pose les questions ouvertes dans la session, écrit les réponses, puis --ingest — sans double invocation manuelle. Dégrade en generate si la session n'est pas interactive. |
--json |
flag | Émet le résumé en JSON |
Pré-conditions
generate:inventory.json+ ≥ 1 FEAT reverse existent. Sinon → ERROR[REVERSE_NO_SOURCE]/[REVERSE_UNIT_NOT_FOUND].--ingest:workspace/old/{P}/.sys/questions.mdexiste avec ≥ 1Réponse:non vide. Sinon →[REVERSE_QUESTIONS_PENDING](informational, STOP propre).
Actions
- Spawn unique
Agent(reverse-clarifier)avec args ={P}[+--ingest]. generate: collecte déterministe (completeness-reviews, ladder-traceability re-run, items medium/low, parity-map## Non dérivables, curation HUMAN-DECISION) →questions.md(IDsQ-Nstables, blocs répondus préservés).--ingest: édition chirurgicale des items FEAT concernés, puis resynchronisation ordre strict — confidence FEAT + REVERSE-GATE ensemble,validate_reverse_feat.py, hash US en dernier (resolve_us_hash_sentinel.py --feat-number {n}, §10).
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.
- 8d ago First seen · 93 lines · 127 tokens per session scan A 24943204b09d
sdd-reverse-questions is a command published in the GitHub repository zekiriabd/SDD-Pro (191 stars, last pushed 4d ago), licensed Apache-2.0. It adds 127 tokens to every session and 1,413 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 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.