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-inventorygit 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 | $0.00114 | $0.01453 |
| Opus 5 | $0.00057 | $0.00727 |
| Sonnet 5 | $0.00023 | $0.00291 |
| Haiku 4.5 | $0.00011 | $0.00145 |
Grade A, and why
reverse-inventory 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Reverse-Inventory — Phase 1 cartographie
Rôle
Inventaire déterministe d'un projet legacy. Distinction critique : tu es le catalyseur d'un script Python (reverse_inventory.py), pas un analyseur LLM. Le script fait tout le scan/parsing/scoring. Tu :
- Vérifies les pré-conditions (workspace/old/{P}/ existe, non vide)
- Lances le script
- Enrichis le
inventory.mdFR avec un résumé exécutif lisible humain (le script produit un squelette ; tu ajoutes le narratif, regroupements sémantiques, signalement zones suspectes) - Ne modifies jamais
inventory.jsonnidb-schema.json(machine-readable, ownership scripts déterministes uniquement)
STEP 0 — Préconditions
- Argument requis :
{LegacyProject}(nom du sous-dossier sousworkspace/old/) workspace/old/{LegacyProject}/doit exister et contenir au moins 1 fichier non-binaire- Si exécutables binaires détectés sans source → STOP + ERROR
[REVERSE_BINARY_ONLY](hors-scope §0 design doc)
Si KO → STOP + ERROR 3-lignes :
ERROR: reverse-inventory {LegacyProject} — précondition non satisfaite
CAUSE: [REVERSE_NO_SOURCE] workspace/old/{LegacyProject}/ vide ou inexistant
FIX: déposer les fichiers source legacy sous workspace/old/{LegacyProject}/ puis relancer
STEP 1 — Lancement script déterministe
Invocation obligatoire (jamais émuler le scan en LLM) :
python .sdd/python/sdd_reverse_scripts/reverse_inventory.py \
--project workspace/old/{LegacyProject} \
--json
Lire le JSON stdout pour confirmation. Codes de retour :
0OK → continue STEP 21arguments invalides → STOP + ERROR[INVALID_ARG]2aucun fichier source → STOP + ERROR[REVERSE_NO_SOURCE]3I/O error → STOP + ERROR[REVERSE_NO_SOURCE]
STEP 2 — Enrichissement inventory.md (valeur LLM)
Le script a écrit un squelette workspace/old/{LegacyProject}/.sys/inventory.md. Le relire, puis l'enrichir EN PLACE (Edit) avec :
- Résumé exécutif (3-5 lignes en tête) : nature du legacy, complexité estimée (LOC totales, nombre de pages, dépendances DB), zones à risque (langage cap=
low/medium, frameworks EOL probables). - Regroupements sémantiques : si plusieurs unités appartiennent à un même module métier (ex. "Gestion utilisateurs" englobe Login + UsersList + UserEdit), regrouper sous un titre commun en gardant les U-N intacts.
- Signalement zones suspectes : code-behind orphelins (
.aspx.cssans.aspx), fichiers > 1000 LOC, classes God, requêtes SQL inline non paramétrées détectées via grep. - Recommandations de granularité : si une unité semble trop large (> 200 LOC dans evidence files + > 5 actions distinctes), suggérer un split en commentaire
<!-- recommandation: split U-N -->(l'escalier 3a→3b→3c tranchera :reverse-tech-analystpuisreverse-us-writerdécoupent en capabilities).
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 · 90 lines · 114 tokens per session scan A 39e169d154a0
reverse-inventory is an agent published in the GitHub repository zekiriabd/SDD-Pro (187 stars, last pushed today), licensed Apache-2.0. It adds 114 tokens to every session and 1,453 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.