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-analyzegit 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-analyze)<a href="https://agentmods.dev/commands/zekiriabd/sdd-pro/sdd-reverse-analyze"><img src="https://agentmods.dev/badge/commands/zekiriabd/sdd-pro/sdd-reverse-analyze.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 | $0.00099 | $0.01364 |
| Opus 5 | $0.00049 | $0.00682 |
| Sonnet 5 | $0.00020 | $0.00273 |
| Haiku 4.5 | $0.00010 | $0.00136 |
Grade A, and why
sdd-reverse-analyze 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdd-reverse-analyze {U-N} [--json]
Rôle
Lancer la Phase 3a (premier barreau de l'escalier reverse) : transformer une unité fonctionnelle (Phase 1) en analyse technique legacy — photo fidèle du code, sans interprétation métier. Une seule unité par invocation.
code source --[3a /sdd-reverse-analyze]--> plans/{n}-{FeatName}.analysis.md
--[3b /sdd-reverse-stories]--> us/{n}-{m}-{Name}.md
--[3c /sdd-reverse-feat]------> feats/{n}-{FeatName}.md
En mode pré-alloué (L5, preallocate_feats exécuté), plusieurs invocations
peuvent tourner en parallèle borné (§8.2 rules/reverse-engineering.md) ;
sans pré-allocation, séquentiel strict (ADV-2 §8.1). 3a possède l'allocation
(n, FeatName) que 3b/3c réutilisent.
Args
| Arg | Type | Description |
|---|---|---|
{U-N} |
string requis | Identifiant U-N stable (ex. U-3) — résolu via inventory.json.units[] |
--json |
flag | Émet le rapport d'analyse en JSON |
Pré-conditions
workspace/old/{P}/.sys/inventory.jsonexiste ET passe gate ADV-23 (schemaVersion == 1,_allocatedNames+_featAllocationsprésents). Sinon → ERROR[REVERSE_INVENTORY_SCHEMA_STALE]+ suggérer/sdd-reverse-inventory --refresh.units[id="{U-N}"]existe. Sinon → ERROR[REVERSE_UNIT_NOT_FOUND]..sdd/python/sdd_reverse/analysis.reverse.template.mdprésent (ADV-9). Sinon → ERROR[REVERSE_TEMPLATE_MISSING].- (Mode legacy uniquement) Lock
workspace/feats/.alloc.locklibre OU stale > 30 min (TTL 1800s). Sinon → ERROR[REVERSE_LOCK_HELD]. En mode pré-alloué, aucun lock (C5).
Actions
- Résoudre le projet legacy : lire
workspace/old/*/.sys/inventory.jsonpour trouver lequel contientunits[id={U-N}]. Plusieurs matchs → ERROR ambiguïté, demander--project {P}. Le nom retenu est{P}— toutes les étapes suivantes l'utilisent, jamais un re-glob. - Routage de tier (déterministe, ADR
governance-reverse-complexity-ladder) — sur le projet{P}résolu en 1 :
→ imprimepython .sdd/python/sdd_reverse/code_unit_complexity.py \ --project workspace/old/{P} --unit {U-N} --rung 3abalancedsi l'unité estsimple,deepsicomplex(rubriquedocs/rubrics/reverse-complexity-routing.md). Fail-safe câblé : toute erreur (inventory absent/illisible,{U-N}inconnu) imprimedeepsur stdout ET la raison sur stderr, exit 0 — le doute coûte une passedeep, jamais un traceback ni une sous-analyse. - Spawn unique
Agent(reverse-tech-analyst)avec args ={U-N}ETmodel_tier= le tier routé en 2 (override au spawn, borné partier_floor/tier_ceilingde l'agent — l'agent est inchangé, seul son tier d'exécution varie ; no-spawn préservé). - L'agent suit STEP 0 à 7 de
.sdd/agents/reverse-tech-analyst.md. - Émission ligne chat finale
[REVERSE] {U-N} → analyse 3a {n}-{FeatName} ({modèle}, ...). (PROGRESS%).
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 · 82 lines · 99 tokens per session scan A 4977e02672cd
sdd-reverse-analyze is a command published in the GitHub repository zekiriabd/SDD-Pro (191 stars, last pushed 2d ago), licensed Apache-2.0. It adds 99 tokens to every session and 1,364 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 2026-08-30.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.