backlog-prioritize

backlog-prioritize is a command for Claude Code from gonzalezpazmonica/savia. It costs 22 tokens per session (1,193 once invoked), scanned A, original, MIT.

A backlog prioritization tool that scores planned work with RICE or WSJF. RICE weighs reach, impact, confidence, and effort; WSJF is a method for ordering work by value and waiting cost against job size.

In plain words
What is it for?
Use it to score unfinished backlog items, compare RICE with WSJF, and give extra weight to strategy alignment or estimated effort.
Why use it?
It replaces informal ordering with a visible calculation based on expected value and effort. It can also consider historical delivery speed and alignment with company goals.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

Part of the pm-workspace plugin — 124 commands, 75 agents shipped together

Good fit Use it to score unfinished backlog items, compare RICE with WSJF, and give extra weight to strategy alignment or estimated effort.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/gonzalezpazmonica/savia/backlog-prioritize
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/gonzalezpazmonica/savia

Made for: Claude Code.

Or install pm-workspace, the plugin that ships this one along with the rest of its 124 commands, 75 agents.

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 backlog-prioritize

README.md
[![agentmods](https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/backlog-prioritize/github.svg)](https://agentmods.dev/commands/gonzalezpazmonica/savia/backlog-prioritize)
Your own site
<a href="https://agentmods.dev/commands/gonzalezpazmonica/savia/backlog-prioritize"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/backlog-prioritize/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for backlog-prioritize

Your own site · 80×15
<a href="https://agentmods.dev/commands/gonzalezpazmonica/savia/backlog-prioritize"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/backlog-prioritize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,193 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 $0.00022 $0.01193
Opus 5 $0.00011 $0.00596
Sonnet 5 $0.00004 $0.00239
Haiku 4.5 $0.00002 $0.00119

Measured 4d ago against content hash 32db9fe3cdd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

backlog-prioritize 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/backlog-prioritize.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/backlog-prioritize

🦉 Savia calcula prioridad objetiva: Reach, Impact, Confidence, Effort (RICE) o Weighted Shortest Job First (WSJF).


Cargar perfil

Grupo: Backlog Intelligence — cargar:

  • CLAUDE.md — proyecto activo
  • projects/{proyecto}/CLAUDE.md — config
  • company/strategy.md — OKRs y alineación estratégica
  • Backlog items desde Azure DevOps
  • Histórico de Story Points (velocity)

Subcomandos

  • /backlog-prioritize — RICE score por defecto
  • /backlog-prioritize --method wsjf — usar WSJF en lugar de RICE
  • /backlog-prioritize --strategy-aligned — ponderar por alineación con OKRs
  • /backlog-prioritize --effort-weighted — ponderar por esfuerzo estimado

Flujo

Paso 1 — Cargar items y datos

Cargar backlog (sin Done) + Story Points + histórico 3 sprints para velocidad media.

Paso 2 — Calcular RICE

RICE = (Reach × Impact × Confidence) / Effort

  • Reach (1-100): usuarios afectados, escala relativa TAM
  • Impact (1-3): 1=minor, 2=medium, 3=major
  • Confidence (0-100%): madurez del spec (Poor=50%, High=100%)
  • Effort (1-20): Story Points históricos

Si PBI sin SP → pedir estimation antes de calcular.

Paso 3 — Calcular WSJF (alternativa)

WSJF = (Business Value + Time Criticality + Risk) / Job Size

  • Todos 1-5 (Business Value, Criticality, Risk Reduction, Job Size)
  • Usar si equipo es SAFe o prefiere scoring cualitativo

Paso 4 — Ponderar por estrategia (opcional)

Si se usa --strategy-aligned:

Score_final = Score_base × (1 + Strategy_weight)

Donde Strategy_weight:
  - Item NO contribuye a OKR → 0.8 (penalizar)
  - Item contribuye a 1 KR → 1.0 (neutro)
  - Item contribuye a 2+ KR → 1.3 (priorizar)

Leer company/strategy.md para vincular items a KRs.

Paso 5 — Presentar ranking ordenado

# Backlog Prioritization — {proyecto}

Método: RICE | Generado: {fecha}
Velocidad media (3 sprints): {SP/sprint}

## Top 20 Items Priorizados

| Rango | PBI ID | Título | Reach | Impact | Conf. | Effort | RICE Score | Estrategia |
|-------|--------|--------|-------|--------|-------|--------|------------|-----------|
| 1 | #2341 | Feature X | 80 | 3 | 90% | 5 SP | 432 | OKR 1.2 + 2.1 |
| 2 | #2338 | Bug critical | 50 | 3 | 100% | 2 SP | 225 | Tech debt |
| ... | ... | ... | ... | ... | ... | ... | ... | ... |

## Items en cola (21-50) — mostrar resumen solo
[Tabla comprimida con rango 21-50]

## Recomendación de capacidad actual

Capacidad sprint: NNN SP
Items para este sprint (score ≥ X): NNN SP
Items para 2-3 sprints próximos: NNN SP

## Insights

- Top 3 items cubren X% del OKR principal
- Y items sin alineación estratégica (considerar deprioritizar)
- Esfuerzo promedio top 10: Z SP/item

---

## Vincular a company/strategy.md

Si existe strategy.md:

```markdown

Read the full file on GitHub · 151 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. 4d ago First seen · 151 lines · 22 tokens per session scan A 32db9fe3cdd1

Subscribe to this mod's changes

backlog-prioritize is a command published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 1,193 once invoked, about $0.0001 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 2026-09-06.