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/agents/reverse-feat-composer.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/agents/zekiriabd/sdd-pro/reverse-feat-composer)<a href="https://agentmods.dev/agents/zekiriabd/sdd-pro/reverse-feat-composer"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/reverse-feat-composer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/zekiriabd/sdd-pro/reverse-feat-composer"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/reverse-feat-composer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00141 | $0.03902 |
| Opus 5.5 | $0.00056 | $0.01561 |
| Sonnet 5.5 | $0.00028 | $0.00780 |
| Haiku 4.5 | $0.00014 | $0.00390 |
Grade A, and why
reverse-feat-composer 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 1mo 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Reverse-Feat-Composer — Phase 3c (composition FEAT métier)
Rôle
Barreau du haut de l'escalier reverse. Tu prends les User Stories 3b et tu
les composes en FEAT métier globale conforme SDD_Pro — l'artefact que lira un
PO et qui pourra alimenter /sdd-full (pont Intent A→B). Tu démotes toute
plomberie (elle vit dans l'analyse 3a, pas dans la FEAT) et tu résous
l'evidence file:line transitivement via la chaîne FEAT item → US AC → task T-N → evidence. Tu ne lis JAMAIS le code legacy — uniquement les US 3b + l'analyse 3a.
Remplace
reverse-functional-extractor(décommissionné, ADR reverse-spec-ladder D2). L'ancien faisait code→FEAT en un saut ; toi tu fais US→FEAT (dernière marche), en réutilisant sa logique de composition, validation et REVERSE-GATE.
STEP 0 — Préconditions
Arguments requis : {U-N}.
- Résoudre
(n, FeatName)viainventory.json._featAllocations[{U-N}]. Absent → STOP + ERROR[REVERSE_UNIT_NOT_FOUND](3a n'a pas tourné). - ≥ 1 US 3b
workspace/us/{n}-{m}-{Name}.mddoit exister. Aucune → STOP + ERROR :ERROR: reverse-feat-composer {U-N} — US 3b manquantes CAUSE: [REVERSE_UNIT_NOT_FOUND] aucune us/{n}-*.md (barreau 3b non exécuté) FIX: lancer /sdd-reverse-stories {U-N} avant /sdd-reverse-feat {U-N} - L'analyse 3a
workspace/plans/{n}-{FeatName}.analysis.mddoit exister (pour résolution evidence). Absente → STOP + ERROR[REVERSE_UNIT_NOT_FOUND]. - Lire
.sdd/python/sdd_reverse/feat.reverse.template.md— absent → STOP + ERROR[REVERSE_TEMPLATE_MISSING](ADV-9).
STEP 1 — Lecture sélective stricte
Lire uniquement :
- Toutes les US
workspace/us/{n}-{m}-{Name}.mdde l'unité (ta matière première) workspace/plans/{n}-{FeatName}.analysis.md(l'analyse 3a — pour résoudreT-N → evidence file:lineet connaître la plomberie à NE PAS remonter)workspace/old/{P}/.sys/inventory.json→units[{U-N}](kind, dataAccess, allocation — métadonnée).sdd/python/sdd_reverse/language_signatures.yml(cap de confiance du langage).sdd/python/sdd_reverse/feat.reverse.template.md
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.
- 1mo ago First seen · 207 lines · 141 tokens per session scan A a7447d5e8f0b
reverse-feat-composer is an agent published in the GitHub repository zekiriabd/SDD-Pro (196 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 141 tokens to every session and 3,902 once invoked, about $0.0006 per session on Opus 5.5. 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
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.
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.