ralphi-backlog

A backlog manager for Ralphi that creates or refreshes backlog.json from prd.json. It keeps work items and their smaller steps aligned with the PRD's user stories and acceptance criteria.

In plain words
What is it for?
Use it when a Ralphi run needs a new backlog, an outdated backlog refreshed, statuses synchronized, or progress markers emitted during implementation.
Why use it?
It prevents the implementation backlog from becoming out of sync with the requirements, while preserving completed work and pointing to the current item.

Skill for Claude CodeCodex

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 skills/fagnerjs/ralphi/ralphi-backlog
Any agent
npx skills add fagnerjs/ralphi --skill ralphi-backlog
Clone the repo
git clone --depth 1 https://github.com/fagnerjs/ralphi

Made for: Claude Code, Codex.

Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 541 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 $0.00044 $0.00541
Opus 5 $0.00022 $0.00270
Sonnet 5 $0.00009 $0.00108
Haiku 4.5 $0.00004 $0.00054

Measured 2d ago against content hash 1140d7ed1456, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ralphi-backlog 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.

skills/ralphi-backlog/SKILL.md · 69 lines

What it actually says

Ralphi Backlog

Use this skill when backlog.json is missing, stale, or needs to be updated while working a PRD.

Backlog Contract

backlog.json must stay machine-readable and compact:

{
  "version": 1,
  "sourcePrd": "...",
  "branchName": "...",
  "activeItemId": "BT-001",
  "activeStepId": "ST-001-01",
  "items": [
    {
      "id": "BT-001",
      "storyId": "US-001",
      "title": "Story title",
      "description": "Short summary",
      "status": "pending",
      "notes": "",
      "updatedAt": "2026-03-07T00:00:00.000Z",
      "steps": [
        {
          "id": "ST-001-01",
          "title": "Acceptance criterion text",
          "status": "pending"
        }
      ]
    }
  ]
}

Workflow

  1. Read prd.json first when it exists.
  2. Create one backlog item per user story.
  3. Create one step per acceptance criterion.
  4. Preserve completed status and notes when refreshing existing backlog data.
  5. Keep activeItemId and activeStepId pointed at the current work item.

Status Rules

  • Use pending, in_progress, done, blocked, or disabled.
  • Mark the backlog item done only when the related story is complete in prd.json.
  • Mark individual steps done as they are verified.
  • If a step cannot be finished in the current run, leave it pending or blocked and explain why in notes.
  • If a user disables an item, preserve disabled and skip it when choosing the next task.

Progress Markers

Whenever you switch to a backlog item or complete a step, print a single marker line:

<ralphi-backlog item="BT-001" step="ST-001-01" status="in_progress">
<ralphi-backlog item="BT-001" step="ST-001-03" status="done">

These markers drive the live dashboard. Keep them exact and on their own line.

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 · 69 lines · 44 tokens per session scan A 1140d7ed1456

Subscribe to this mod's changes

ralphi-backlog is a skill published in the GitHub repository fagnerjs/ralphi (6 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 541 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

wayfinder

Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

mattpocock/skills · 46 tokens

setup-matt-pocock-skills

Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

mattpocock/skills · 44 tokens

accessibility

Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.

microsoft/hve-core · 47 tokens

release-notes

Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.

phuryn/pm-skills · 57 tokens

retro

Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.

phuryn/pm-skills · 52 tokens

bug-triage

Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.

Donchitos/Claude-Code-Game-Studios · 59 tokens