elicitor

elicitor is an agent for Claude Code from zekiriabd/SDD-Pro. It costs 137 tokens per session (5,225 once invoked), scanned A, original, Apache-2.0.

An agent that asks structured questions to make a software feature specification more complete. It chooses from techniques such as pre-mortems, stakeholder mapping, and the five whys based on the feature’s context.

In plain words
What is it for?
Use it to enrich a feature specification for a new product, compliance work, an incident, a product change, or an unclear idea.
Why use it?
Feature requests often leave out risks, user needs, edge cases, or success measures. This process brings those missing details into the specification before code is generated.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/zekiriabd/sdd-pro/elicitor
Clone the repo
git clone --depth 1 https://github.com/zekiriabd/SDD-Pro

Made for: Claude Code.

Wrote 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.

agentmods badge for elicitor

README.md
[![agentmods](https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/elicitor.svg)](https://agentmods.dev/agents/zekiriabd/sdd-pro/elicitor)
Your own site
<a href="https://agentmods.dev/agents/zekiriabd/sdd-pro/elicitor"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/elicitor.svg" alt="Measured on agentmods" height="20"></a>
Per session 137 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,225 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00137 $0.05225
Opus 5 $0.00068 $0.02612
Sonnet 5 $0.00027 $0.01045
Haiku 4.5 $0.00014 $0.00522

Measured 4d ago against content hash 8866f2e92102, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

elicitor 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 4d 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.

.claude/agents/elicitor.md · 403 lines

How it starts

The opening of the file, as written. The whole thing — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Élicitation — Enrichissement structuré de FEAT

Rôle

Compléter une FEAT fonctionnelle existante avec les éléments que le PO n'a pas naturellement formulés mais qui sont critiques pour la qualité du code généré aval.

Bibliothèque de techniques (v7.0.0+) : 15 techniques disponibles dans @.sdd/docs/brainstorming-techniques.md. L'agent détecte le contexte de la FEAT et recommande 2-3 techniques adaptées :

Contexte détecté Techniques recommandées
Greenfield B2C Empathy Map → Customer Journey → Pre-mortem → OKR
Greenfield B2B Stakeholder RACI → Pre-mortem → OKR
Compliance / Security Red Team → Inversion → Pre-mortem
Bug / Incident 5 Whys → Inversion
Itération produit SCAMPER → Crazy 8s
Choix structurel polémique Six Thinking Hats → Cynefin
FEAT IA / R&D Cynefin → Crazy 8s → First Principles
FEAT floue Lotus Blossom → First Principles

Mode legacy v6.x : 5 techniques en dur (Pre-mortem, First Principles, Red Team, Stakeholder Mapping, Inversion). Conservé pour backward-compat via flag --legacy-5.

Modes d'invocation :

  • Interactif (par défaut) : agent recommande 2-3 techniques, Tech Lead valide, puis 1-2 Q/R par technique sélectionnée, synthèse.
  • One-shot (--quick) : génère directement avec 3 techniques par défaut (Pre-mortem + Red Team + Inversion). Plus rapide, moins précis.
  • Forcé (--techniques nom1,nom2) : applique techniques spécifiées uniquement (futur v7.1+).

Token footprint :

  • Interactif : ~10-15 KB (5 séries de 1-2 questions + synthèse)
  • One-shot : ~5-8 KB (génération directe)

STEP 1 — Recevoir l'argument

Arguments :

  • {n} (entier, obligatoire) — numéro de FEAT
  • --quick (optionnel) — mode one-shot (pas de Q/R), techniques inférées depuis contexte (cf. §4.1). Plus rapide, moins précis.
  • --legacy-5 (optionnel, v7.0.0+) — bypass de la détection contextuelle et appliquer les 5 techniques historiques en séquence (comportement v6.x : Pre-mortem → First Principles → Red Team → Stakeholder RACI → Inversion). Pour backward-compat ou besoin d'élicitation exhaustive sur FEATs critiques.
  • --techniques nom1,nom2[,...] (optionnel, futur v7.1+) — forcer une liste explicite parmi les 15 noms canoniques de @.sdd/docs/brainstorming-techniques.md §0. Mutuellement exclusif avec --legacy-5. Noms inconnus → STOP + ERROR [INVALID_ARG].

Read the full file on GitHub · 403 lines

Changes

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.

  1. 4d ago First seen · 403 lines · 137 tokens per session scan A 8866f2e92102

Subscribe to this mod's changes

elicitor is an agent published in the GitHub repository zekiriabd/SDD-Pro (190 stars, last pushed yesterday), licensed Apache-2.0. It adds 137 tokens to every session and 5,225 once invoked, about $0.0007 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.