spec

A command that creates a detailed plan for a software feature by researching it, analyzing its requirements, and checking its quality.

In plain words
What is it for?
Starting feature specifications, collecting answers to required questions, tracking progress, and completing or pausing the specification workflow.
Why use it?
It gives a feature a documented shape before implementation and keeps the main conversation lighter by handling the work separately.

Command 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 commands/marcusgoll/spec-flow/spec
Clone the repo
git clone --depth 1 https://github.com/marcusgoll/Spec-Flow

Made for: Claude Code.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,869 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 $0.00015 $0.05869
Opus 5 $0.00008 $0.02934
Sonnet 5 $0.00003 $0.01174
Haiku 4.5 $0.00002 $0.00587

Measured 2d ago against content hash 65e7c0742f01, 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 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.

.claude/commands/phases/spec.md · 831 lines

How it starts

The opening of the file, as written. The whole thing — 831 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/spec — Feature Specification Generator (Thin Wrapper)

v11.0 Architecture: This command is now a thin wrapper that spawns the isolated spec-phase-agent via Task(). All specification logic runs in an isolated context with question batching for user interaction.

Active Feature: !ls -td specs/[0-9]*-* 2>/dev/null | head -1 || echo "none"

Interaction State: !cat specs/*/interaction-state.yaml 2>/dev/null | head -10 || echo "none"

Architecture (v11.0 - Full Phase Isolation):

/spec command (this file)
    │
    ▼
┌──────────────────────────────────────────────────────┐
│ 1. Detect feature directory                          │
│ 2. Initialize interaction-state.yaml if needed       │
│ 3. Check for pending answers from previous session   │
│ 4. Spawn Task(spec-phase-agent)                      │
│ 5. Handle agent result:                              │
│    - needs_input → AskUserQuestion → re-spawn        │
│    - completed → update state.yaml                   │
│    - failed → log error, pause workflow              │
└──────────────────────────────────────────────────────┘

Benefits:

  • Main context stays lightweight (no spec details in memory)
  • Unlimited specification complexity
  • Resumable at any point
  • Observable Q&A history in interaction-state.yaml

Workflow position: spec → clarify? → plan → tasks → implement → optimize → ship

Step 0: Ultrathink Checkpoint — Think Different

Philosophy: "Is this solving the real problem or a symptom?"

Before generating any specification, pause to question assumptions.

Display thinking prompt:

┌─────────────────────────────────────────────────────────────┐
│ 💭 ULTRATHINK CHECKPOINT: Think Different                   │
├─────────────────────────────────────────────────────────────┤
│ Before specifying, consider:                                │
│                                                             │
│ • Is this the REAL problem or just a symptom?               │
│ • What assumptions are we making about users?               │
│ • What would the simplest solution look like?               │
│ • Is this a feature, or a symptom of a missing feature?     │
└─────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 831 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. 2d ago First seen · 831 lines · 15 tokens per session scan A 65e7c0742f01

Subscribe to this mod's changes

spec is a command published in the GitHub repository marcusgoll/Spec-Flow (91 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 5,869 once invoked, about $0.0001 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.