sage-pull-request

sage-pull-request is a command for coding agents from gustavobarbosab/sage. It costs 0 tokens per session (438 once invoked), scanned A, original, MIT.

A prompt that creates a ready-to-paste pull-request title and description from a project specification, behavior notes, and generated code. A pull request is a proposal to merge code changes into a shared repository.

In plain words
What is it for?
Use it to create a pr.md file with an imperative title, change summary, acceptance-criteria checklist, out-of-scope notes, and test coverage.
Why use it?
It turns project requirements and implementation details into a consistent review document, including decisions, testing, and items left out.

Command

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

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-pull-request

README.md
[![agentmods](https://agentmods.dev/badge/commands/gustavobarbosab/sage/sage-pull-request.svg)](https://agentmods.dev/commands/gustavobarbosab/sage/sage-pull-request)
Your own site
<a href="https://agentmods.dev/commands/gustavobarbosab/sage/sage-pull-request"><img src="https://agentmods.dev/badge/commands/gustavobarbosab/sage/sage-pull-request.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 438 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 $0.00438
Opus 5 $0.00000 $0.00219
Sonnet 5 $0.00000 $0.00088
Haiku 4.5 $0.00000 $0.00044

Measured 4d ago against content hash 5f0b36dc8edb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sage-pull-request 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 4d 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-pull-request.md · 70 lines

What it actually says

/sage-pull-request

Use this prompt to generate pr.md — a ready-to-paste PR title and description with embedded ADR-style decisions.


Prompt

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

Read:
- spec.md
- behavior.md
- The final generated code
- doc.md (if it exists)

Generate a pr.md with this structure:

## <Short PR title — one line, imperative voice>

<2-3 sentence summary of what this PR implements and why>

### Changes
Bullet list of the concrete code changes (new classes, modified files, key behaviors implemented).

### Decisions (ADR-style)
For each open question resolved during the SAGE workflow:
- <The decision made>
  → <The reasoning behind it>

### Acceptance criteria covered
Reference the items from spec.md that this PR satisfies (use a checklist).

### Out of scope
Briefly mention what this PR deliberately does NOT include and why
(e.g. follow-up tickets, deferred decisions).

### Testing
Brief description of test coverage — which scenarios from behavior.md are covered, what was tested manually, what's left for QA.

---

The title should be imperative voice ("Implement login screen" not "Implemented login screen") and under 72 characters.

Do not include implementation details that belong in code review comments — keep this focused on intent, scope, and decisions.

How to open the PR

After pr.md is generated, you can open the PR directly with the GitHub CLI:

gh pr create \
  --title "$(head -n1 pr.md | sed 's/^## //')" \
  --body "$(tail -n +2 pr.md)"

Or just copy-paste into the GitHub web UI.


Tips

  • The "Decisions" section is gold for reviewers — they see WHY you made the choices you made without having to ask
  • Keep the title imperative and concise — git log becomes much more useful
  • If the PR is large, consider splitting it before opening — pr.md will tell you if too many decisions are bundled
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. 4d ago First seen · 70 lines · 0 tokens per session scan A 5f0b36dc8edb

Subscribe to this mod's changes

sage-pull-request 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 438 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.