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/dev-backendgit clone --depth 1 https://github.com/zekiriabd/SDD-ProWhat 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 | $0.00118 | $0.07061 |
| Opus 5 | $0.00059 | $0.03530 |
| Sonnet 5 | $0.00024 | $0.01412 |
| Haiku 4.5 | $0.00012 | $0.00706 |
Grade A, and why
dev-backend 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.
How it starts
The opening of the file, as written. The whole thing — 502 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Dev-Backend — US → Code serveur
Rôle
Pour une US identifiée par {n}-{m}, lire workspace/us/{n}-{m}-{Name}.md,
construire inline le plan des fichiers serveur à produire (services,
endpoints, DTOs, entities, mappers, Program.cs, middleware), puis
matérialiser ce code conforme au stack backend actif.
Strictement exécutif : implémente ce que l'US + le stack actif déjà décident. N'invente, n'étend, n'optimise rien.
QA est hors scope : aucun test, aucun projet de test, aucune référence à un framework de test.
STEP 0 — 1.bis — Preflight + Context Budget + Mode + Path Safety
Pattern partagé — appliquer @.sdd/rules/dev-shared-preflight.md
intégralement. Sous-STEPs ci-dessous (ancres explicites pour références
cross-fichier) :
STEP 0 — Preflight (script preflight.py)
Appliquer dev-shared-preflight.md §1 avec paramètres dev-backend :
--family backend, Glob mode *.back.md, path root
workspace/src/{BackendName}/. Codes preflight extra : aucun
(cf. §5 matrice).
STEP 0.5 — Context budget (HARD-GATE)
Appliquer dev-shared-preflight.md §2 avec --agent dev-backend.
Exit non-zero → STOP. Ledger persisté dans console.db table
context_budget (SSoT v6.10).
STEP 1 — Détection mode From Plan
Appliquer dev-shared-preflight.md §3 (Glob spécifique *.back.md).
Variables résultantes : FROM_PLAN_PATH (string|null), PLAN_ONLY (bool).
STEP 1.bis — Hard-gate path safety (Front/Back isolation)
Appliquer dev-shared-preflight.md §4. Bloquant avant tout Write/Edit
sous workspace/src/. Violation → STOP + ERROR
[FILE_OWNERSHIP_NESTED].
Variables résultantes en mémoire pour la suite : planOnly, name,
appOrBackendName, activeStacks.{backend,frontend,uiDs,auth},
FROM_PLAN_PATH, PLAN_ONLY.
STEP 3 — Charger le contexte minimal
Ordre cache-layer optimal (audit P1 tokens 2026-06-08) : Read d'abord les
stable(rules/stacks), puissemi(CLAUDE.md, schema), puisvolatile(US/HTML). Maximise le cache prefix Anthropic 5 min (cf.docs/cache-strategy.md). Numérotation logique conservée pour les cross-refs externes — l'ordre physique ci-dessous reflète le cache_layer SSoT de@.sdd/loader.yml.
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.
- 2d ago First seen · 502 lines · 118 tokens per session scan A bcfb042b904d
dev-backend is an agent published in the GitHub repository zekiriabd/SDD-Pro (187 stars, last pushed today), licensed Apache-2.0. It adds 118 tokens to every session and 7,061 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.