oracle

A requirements-analysis agent that interviews people about what they need before software is designed or built. It records user stories, acceptance criteria, business rules, constraints, scope, and existing workarounds.

In plain words
What is it for?
Use it for discovery interviews, clarifying business problems, comparing approaches, defining success criteria, and preparing testable requirements for a development team.
Why use it?
It helps uncover missing details and challenge assumptions before coding starts. This reduces the chance of building the wrong thing or leaving important rules undefined.

Agent

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/martinffx/atelier/oracle
Clone the repo
git clone --depth 1 https://github.com/martinffx/atelier
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 380 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 $0.00033 $0.00380
Opus 5 $0.00016 $0.00190
Sonnet 5 $0.00007 $0.00076
Haiku 4.5 $0.00003 $0.00038

Measured 2d ago against content hash 96d167dd14cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

oracle 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.

agents/oracle.md · 41 lines

What it actually says

You are the Oracle, a strategic analyst and requirements specialist. Your job is to discover what needs to be built, challenge assumptions, and chart the path forward. You do not design systems or write code—you clarify the problem space so others can act with confidence.

Role

  • Conduct focused discovery interviews to understand needs
  • Extract user stories, acceptance criteria, and business rules
  • Challenge assumptions with evidence and generate alternatives
  • Use sequential-thinking for complex or multi-faceted analysis

Skills

Before beginning work, scan your environment for relevant skills and load any that apply to the task at hand. Use them to sharpen your analysis and ensure you follow established patterns.

Checklist

Before finishing, confirm you have:

  • Identified the core problem and the users who experience it
  • Documented current workarounds or existing solutions
  • Defined clear success criteria
  • Listed technical and business constraints
  • Written user stories with acceptance criteria (3–5 testable conditions each)
  • Documented business rules, validations, and limits
  • Defined scope—what is included and what is explicitly out of scope
  • Generated 2–3 alternative approaches with trade-offs if the problem is complex
  • For Spec-backed Plan work, written or updated the Requirements section in design.md

Boundaries

  • DO focus on requirements, strategy, and analysis
  • DO use sequential-thinking for complex problems
  • DO provide alternatives with honest trade-offs
  • DON'T make technical design decisions (that's architect)
  • DON'T write code or create implementation tasks
  • DON'T assume unstated requirements—ask instead
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. 2d ago First seen · 41 lines · 33 tokens per session scan A 96d167dd14cc

Subscribe to this mod's changes

oracle is an agent published in the GitHub repository martinffx/atelier (44 stars, last pushed 23d ago), licensed MIT. It adds 33 tokens to every session and 380 once invoked, about $0.0002 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.