sage

sage is a command for Claude Code from gustavobarbosab/sage. It costs 122 tokens per session (955 once invoked), scanned A, original, MIT.

A command-based workflow for planning software with written specifications, behavior examples, and generated code. SDD means specification-driven development, BDD means describing software through expected behavior, and a project harness is the files and rules that guide work on a codebase.

In plain words
What is it for?
Use it to create or update specs, turn them into behavior scenarios and code, initialize or review project guidance, and export pull-request descriptions and documentation.
Why use it?
It keeps requirements and expected behavior clear before code is written, reducing misunderstandings and making later updates easier to trace.

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/sage
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

README.md
[![agentmods](https://agentmods.dev/badge/commands/gustavobarbosab/sage/sage.svg)](https://agentmods.dev/commands/gustavobarbosab/sage/sage)
Your own site
<a href="https://agentmods.dev/commands/gustavobarbosab/sage/sage"><img src="https://agentmods.dev/badge/commands/gustavobarbosab/sage/sage.svg" alt="Measured on agentmods" height="20"></a>
Per session 122 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 955 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 $0.00122 $0.00955
Opus 5 $0.00061 $0.00477
Sonnet 5 $0.00024 $0.00191
Haiku 4.5 $0.00012 $0.00096

Measured 5d ago against content hash 35e3b3e975ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sage 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 5d 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.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SAGE

Spec · Assert · Generate · Export

A spec-first workflow that combines SDD, BDD, and Harness Engineering to front-load thinking and back-load generation.

spec.md  →  behavior.md  →  code       →  pr.md + doc.md
 (you)      (you + AI)      (you + AI)     (AI + you)

Commands

The user interacts with SAGE using /sage <command> [argument].

Command Argument Reference file
/sage spec <description> Feature description, ticket text, or idea references/spec.md
/sage behavior (none — reads spec.md) references/behavior.md
/sage code (none — reads spec.md + behavior.md) references/code.md
/sage update <feedback> Precise feedback tied to spec or behavior references/update.md
/sage pr (none — reads full context) references/pr.md
/sage doc (none — reads full context) references/doc.md
/sage harness init (none — interactive wizard) references/harness-init.md
/sage harness generate (none — reads codebase files) references/harness-generate.md
/sage harness review (none — reads harness.md) references/harness-review.md

How to handle each command

When the user types a /sage command:

  1. Identify the sub-command from the table above
  2. Read the corresponding reference file — it contains the full prompt and instructions for that step
  3. Extract the inline argument if provided (e.g. /sage spec "Login screen with email and password" → argument is "Login screen with email and password")
  4. Execute the step following the reference file instructions

If the user types /sage with no sub-command, show the command table above and ask which step they want to run.


Prerequisite — the harness

Before running any SAGE step, check if .sage/harness.md (or CLAUDE.md, .cursorrules, or project knowledge) exists.

  • If it exists — load it as context for all steps
  • If it doesn't exist — remind the user once: "No harness found. Run /sage harness init or /sage harness generate to set one up. I'll proceed without it for now." Then continue.

Read the full file on GitHub · 84 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. 5d ago First seen · 84 lines · 122 tokens per session scan A 35e3b3e975ea

Subscribe to this mod's changes

sage is a command published in the GitHub repository gustavobarbosab/sage (2 stars, last pushed 2mo ago), licensed MIT. It adds 122 tokens to every session and 955 once invoked, about $0.0006 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.