spec

spec is a command for Claude Code from gustavobarbosab/sage. It costs 0 tokens per session (907 once invoked), scanned A, original, MIT.

A guided feature-specification command that asks questions about a proposed feature and creates `spec.md` and `behavior.md` from the answers.

In plain words
What is it for?
Use it to define scope, inputs, outputs, acceptance criteria, restrictions, error states, and edge cases for a feature.
Why use it?
It helps turn an incomplete idea or ticket into a clearer, testable description before coding begins.

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/gustavobarbosab/sage/spec
Clone the repo
git clone --depth 1 https://github.com/gustavobarbosab/sage

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 spec

README.md
[![agentmods](https://agentmods.dev/badge/commands/gustavobarbosab/sage/spec.svg)](https://agentmods.dev/commands/gustavobarbosab/sage/spec)
Your own site
<a href="https://agentmods.dev/commands/gustavobarbosab/sage/spec"><img src="https://agentmods.dev/badge/commands/gustavobarbosab/sage/spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 907 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 $0.00000 $0.00907
Opus 5 $0.00000 $0.00453
Sonnet 5 $0.00000 $0.00181
Haiku 4.5 $0.00000 $0.00091

Measured 3d ago against content hash e92a5c3b4d92, 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.

skill/claude-code/.claude/commands/sage/spec.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sage spec

Generates spec.md + behavior.md through a structured interview — all questions shown upfront, files generated together after answers are collected.

Inline argument

The user may provide an initial description inline:

/sage spec "Login screen with email and password"
/sage spec [paste of Jira ticket content]

If no argument is provided, ask: "What feature do you want to specify?"


Step 1 — Analyze and prepare questions

Read the harness from .sage/harness.md (or CLAUDE.md, .cursorrules, or project knowledge).

Analyze the description and identify everything you need to know to write a complete, unambiguous spec. Do NOT generate the spec yet.

Prepare questions across these categories:

  • Purpose & scope — what the feature does and what it explicitly doesn't do
  • Inputs & outputs — parameters, types, callbacks, events
  • Acceptance criteria — testable conditions for each behavior
  • Restrictions — forbidden patterns, anti-patterns, out-of-scope items
  • Edge cases — boundary conditions, error states, concurrent actions

Step 2 — Present all questions at once

Show all questions in a single message. Format:

I have X questions before writing your spec and behavior files.
Answer them all and I'll generate both at once.

─────────────────────────────────────────
 Question 1 of X
─────────────────────────────────────────
[Category: Purpose & scope]
<Question text>

─────────────────────────────────────────
 Question 2 of X
─────────────────────────────────────────
[Category: Inputs & outputs]
<Question text>

... (all questions)

─────────────────────────────────────────
Reply with your answers (numbered or in order) and I'll generate
spec.md and behavior.md together.
─────────────────────────────────────────

Rules for questions:

  • Only ask what you genuinely can't infer from the description and harness
  • Skip questions whose answers are obvious from context
  • Minimum 3, maximum 10 questions — be thorough but not exhausting
  • Each question must be specific and answerable in 1-2 sentences

Read the full file on GitHub · 153 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 · 153 lines · 0 tokens per session scan A e92a5c3b4d92

Subscribe to this mod's changes

spec is a command published in the GitHub repository gustavobarbosab/sage (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 907 tokens. 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.