behavior

A command that turns a product specification into a behavior document, first listing unclear requirements and unanswered questions.

In plain words
What is it for?
Reviewing a spec.md file, recording ambiguities and edge cases, and generating behavior.md after the open questions are resolved.
Why use it?
It prevents test cases from being based on assumptions when the specification leaves behavior undefined.

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

Made for: Claude Code.

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 563 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 $0.00563
Opus 5 $0.00000 $0.00282
Sonnet 5 $0.00000 $0.00113
Haiku 4.5 $0.00000 $0.00056

Measured 2d ago against content hash 922bb24fc38e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

behavior 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.

skill/claude-code/.claude/commands/sage/behavior.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sage behavior

Generates behavior.md from spec.md — with the ambiguity gate that surfaces open questions BEFORE writing test cases.

Note: When triggered via /sage spec, this step runs automatically after spec.md is generated. Use /sage behavior directly only when you already have a spec.md and want to regenerate behavior.md independently.

Instructions

Read spec.md and the harness. Then generate behavior.md in exactly this structure:


Section 1 — Open Questions (REQUIRED, always first)

Analyze spec.md and list every ambiguity, missing detail, or behavioral decision not explicitly covered. Format:

## Open Questions
- [ ] <Question about an ambiguous behavior>
- [ ] <Question about a missing edge case>
- [ ] <Question about a conflicting constraint>

Surface anything where:

  • The spec is silent on expected behavior
  • Two interpretations are equally valid
  • An edge case isn't explicitly covered
  • A constraint conflicts with another

If there are genuinely no ambiguities: - No open questions.

DO NOT skip this section under any circumstances.


Section 2 — Test Cases (BLOCKED until questions resolved)

If open questions exist:

## Test Cases
> ⚠️ Pending resolution of open questions above. Do not finalize.

STOP HERE. Wait for the user to resolve questions.

If NO open questions: generate full test cases immediately (see below).


Resolving open questions

The user will either:

  • Answer questions inline in chat
  • Mark each [ ] as [x] with the answer in behavior.md
  • Update spec.md to remove the ambiguity

When all questions are resolved, finalize test cases.


Finalizing test cases

Group scenarios under: Happy path, Validation, Edge cases, Error handling.

For each scenario provide TWO versions:

**Scenario: <Short descriptive title>**
Short → <one-line condensed form: condition + action + outcome>
Full:
- Given <precondition>
- When <action>
- Then <expected outcome>
- And <additional assertion if needed>

Read the full file on GitHub · 94 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 · 94 lines · 0 tokens per session scan A 922bb24fc38e

Subscribe to this mod's changes

behavior 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 563 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.