sage-update

sage-update is a command for Claude Code from gustavobarbosab/sage. It costs 0 tokens per session (384 once invoked), scanned A, original, MIT.

A prompt for requesting precise changes to AI-generated code. It ties each requested change to a rule in spec.md or behavior.md, which describe the intended requirements and behavior.

In plain words
What is it for?
Use it when reviewing generated code and asking for targeted fixes, such as adding a missing test scenario or replacing an overly detailed error message.
Why use it?
It reduces vague feedback and helps keep generated code aligned with the written requirements. It also asks the agent to flag changes that would conflict with those requirements.

Command for Claude Code

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

Good fit Use it when reviewing generated code and asking for targeted fixes, such as adding a missing test scenario or replacing an overly detailed error message.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/gustavobarbosab/sage/sage-update.svg)](https://agentmods.dev/commands/gustavobarbosab/sage/sage-update)
Your own site
<a href="https://agentmods.dev/commands/gustavobarbosab/sage/sage-update"><img src="https://agentmods.dev/badge/commands/gustavobarbosab/sage/sage-update.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 384 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 $0.00384
Opus 5 $0.00000 $0.00192
Sonnet 5 $0.00000 $0.00077
Haiku 4.5 $0.00000 $0.00038

Measured 7d ago against content hash f92f5dc77c0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sage-update 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-update.md · 54 lines

What it actually says

/sage-update

Use this prompt to request changes to generated code with precise, spec-anchored feedback.

The goal: keep iteration tight by tying every change request to a specific item in spec.md or behavior.md, not vague impressions.


Prompt

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

I'm requesting changes to the code you generated.

Read the current state of:
- spec.md
- behavior.md
- the file(s) I'm referencing

Apply these specific changes:

1. <Change request 1 — reference the spec item or scenario it relates to>
2. <Change request 2 — same format>
3. <...>

Rules:
- Do not introduce changes I didn't request
- Do not deviate from the harness
- If a change would violate spec.md or behavior.md, flag it before applying
- Return only the modified files in the same FILE: format as before

Examples of good feedback

"Scenario Double submit during loading is missing the assertion that no duplicate auth request is made — please add it.""Spec item 'Generic error message on auth failure' is violated — the current code surfaces the exception message. Replace with a generic string resource.""The harness says navigation must be via lambda callbacks, but LoginViewModel is calling NavController directly. Move navigation out of the ViewModel."

Examples of weak feedback

❌ "This doesn't look right." ❌ "Make it cleaner." ❌ "Add some error handling."


Tips

  • Open spec.md and behavior.md side by side with the generated code — find the mismatch, name it precisely
  • If you find yourself wanting to give vague feedback, the issue is probably that the spec or behavior is too vague — fix that first
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 f92f5dc77c0b

Subscribe to this mod's changes

sage-update 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 384 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.