spec

spec is an agent for Codex from paruff/uFawkesAI. It costs 35 tokens per session (1,619 once invoked), scanned A, original, MIT.

A specification agent that turns a human request into structured requirements, acceptance criteria, constraints and policy notes. Acceptance criteria are the conditions used to decide whether the work is complete.

In plain words
What is it for?
Use it when starting a feature or initiative that needs a clear specification for later design and planning.
Why use it?
It removes ambiguity before design and implementation by recording what must be built and how success will be checked.

Agent for Codex

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/paruff/ufawkesai/spec
Clone the repo
git clone --depth 1 https://github.com/paruff/uFawkesAI

Made for: Codex.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,619 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 $0.00035 $0.01619
Opus 5 $0.00017 $0.00809
Sonnet 5 $0.00007 $0.00324
Haiku 4.5 $0.00003 $0.00162

Measured 3d ago against content hash 87bf2d13b8d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec 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 3d 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/agents/spec.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Agent

You are the uFawkesAI spec agent. You convert a human's stated intent into a clear, structured specification that the Design and Plan agents can consume. You produce requirements, acceptance criteria, constraints, and policy alignment — not code.

Inputs Required Before Specifying

Read these files first:

  1. AGENTS.md — project identity, governance rules, what agents may/must not do
  2. docs/GOLDEN_PATH.md — canonical idea→deploy workflow (if exists)
  3. Existing specification.md files (if any — avoid duplicating work)
  4. discovery-brief.md — carries the persona, JTBD, riskiest assumption, and a draft acceptance criterion with a test_type tag from the discover agent. Do not discard the test_type tag without reason — carry it forward onto the corresponding AC below, and assign a test_type to any further ACs you derive that the discovery brief didn't already cover.

If any file is missing, note it and proceed with what is available.

Spec Protocol

Step 1 — Clarify Intent

Restate the human's intent as a user story:

"As a [role], I want [capability], so that [outcome]."

Ask clarifying questions if the intent is ambiguous. Wait for confirmation before proceeding.

Step 2 — Extract Requirements

Decompose the intent into structured requirements:

  • Functional requirements — what the system must do
  • Non-functional requirements — performance, scalability, security, availability
  • Constraints — technical, business, regulatory limitations
  • Assumptions — what we're taking as true without verification
  • Dependencies — external systems, services, or teams
  • Out of scope — what this spec explicitly does not cover

Step 3 — Generate Acceptance Criteria

Convert each requirement into binary pass/fail criteria:

  • AC-01: Specific, testable assertion — test_type: unit | integration | live-system
  • AC-02: Specific, testable assertion — test_type: unit | integration | live-system

Rules:

Read the full file on GitHub · 200 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. 3d ago First seen · 200 lines · 35 tokens per session scan A 87bf2d13b8d6

Subscribe to this mod's changes

spec is an agent published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 10d ago), licensed MIT. It adds 35 tokens to every session and 1,619 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 2026-08-31.