sage-spec

sage-spec is a command for Claude Code from gustavobarbosab/sage. It costs 0 tokens per session (343 once invoked), scanned A, original, MIT.

A command for creating a structured feature specification in a file named spec.md. The specification describes behavior, inputs, outputs, acceptance checks, and explicit exclusions.

In plain words
What is it for?
Use it to draft specs from a feature request, after checking the project’s .sage/harness.md for its stack and conventions.
Why use it?
It turns a feature idea into a shared plan with testable conditions before implementation begins.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to draft specs from a feature request, after checking the project’s .sage/harness.md for its stack and conventions.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/gustavobarbosab/sage/sage-spec
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.

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 sage-spec

README.md
[![agentmods](https://agentmods.dev/badge/commands/gustavobarbosab/sage/sage-spec.svg)](https://agentmods.dev/commands/gustavobarbosab/sage/sage-spec)
Your own site
<a href="https://agentmods.dev/commands/gustavobarbosab/sage/sage-spec"><img src="https://agentmods.dev/badge/commands/gustavobarbosab/sage/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 343 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00343
Opus 5 $0.00000 $0.00171
Sonnet 5 $0.00000 $0.00069
Haiku 4.5 $0.00000 $0.00034

Measured 7d ago against content hash a22c34b6e146, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sage-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 7d 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.

commands/sage-spec.md · 54 lines

What it actually says

/sage-spec

Use this prompt to create a structured spec.md for a feature.

A good spec is the foundation of SAGE — it's the single source of truth that drives behavior, code, and documentation downstream.


Prompt

You are SAGE, a spec-first AI development assistant.

I need you to help me write a spec.md for a new feature.

Use the harness file at .sage/harness.md (or whatever's in our project knowledge) for stack and convention context.

Generate a spec.md with exactly these sections:

## Feature: <FeatureName>

### What it does
A 1–2 sentence description of the feature's purpose.

### Inputs
List every input parameter with type and short description.

### Outputs
List every output callback, event, or return value with description.

### Acceptance criteria
Bullet list of testable conditions that must be true for the feature to be considered complete.
Be specific. Avoid vague terms like "good UX" or "works correctly".

### Do NOT
Explicit out-of-scope items and forbidden patterns.

---

If the feature description I provide is vague or incomplete, ask clarifying questions BEFORE writing the spec. Do not invent acceptance criteria from thin air.

Here is what I want to build:

<paste your feature description, Jira ticket, or rough idea here>

Tips

  • Be specific in the "Do NOT" section — explicit restrictions reduce back-and-forth in later steps
  • The acceptance criteria become your review checklist later, so make them testable
  • If you don't know an answer, write (TBD) — the AI will surface it as an open question in Step 2
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. 7d ago First seen · 54 lines · 0 tokens per session scan A a22c34b6e146

Subscribe to this mod's changes

sage-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 343 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.