Backlog

---
name: backlog
description: See the backlog, decompose an epic or an idea into items, bring an item to ready and start it - always through the sdlc backlog commands.
when_to_use: The user wants to see or plan the backlog, split an epic or idea into items, refine an item, or start the next one.
argument-hint: "[epic, idea or B<n>]"
license: "PolyForm-Noncommercial-1.0.0 with sdlc Additional Permissions, or sdlc Commercial License (https://github.com/marin-ai-tech/sdlc)"
compatibility: Requires the sdlc CLI (sdlc) from the sdlc package.
allowed-tools: Bash(sdlc *)
metadata:
  author: marin-ai technologies
  version: "1"
  generatedBy: "sdlc 0.23.7"
---

Work with the backlog (`openspec/backlog.md`): the ordered list of planned changes. One item becomes one change.

**Harness contract** (applies to every SDLC workflow)
- `sdlc` is the source of truth for lifecycle state. Read it (`sdlc status --change <id> --json`) instead of inferring the stage from the conversation, and re-read artifacts from disk before using them.
- Gates are human decisions. Never run `sdlc approve`, `sdlc reject`, `sdlc waive` or `sdlc tests unlock`, and never edit `.sdlc.yaml`. When a gate needs a person, stop, name the people from the hint (`next.people` in `sdlc next --json`) rather than the role, and give them the exact command to run in their own terminal.
- An answer in chat is never an approval: gate approvals, `track set`, `backlog move`/`drop` and other human decisions happen only as a command the person runs in their own terminal. Offer the choice, explain the consequences, and give the exact command.
- OpenSpec is the specification subsystem: `sdlc openspec <args>` runs the bundled OpenSpec CLI (`list --specs`, `show`, `validate`, `instructions`). Change folders live in `openspec/changes/<id>/`.
- **Change selection**: use the change named in the input. Otherwise run `sdlc status --json`; with exactly one active change use it, with several ask which one. Announce "Using change: <id>".
- **Language**: talk to the person, and write notes and artifacts, in the person's language; when `locale:` is set in `openspec/sdlc.yaml`, use that language. Keep command names, file names, ids and the template headings as they are (sdlc and OpenSpec parse those headings).
- End every workflow with the next step from `sdlc next --json` (the exact command when a person must act).

**Input**: the user's request (a change id, or a description of the work)

**Rules**
- Never edit `openspec/backlog.md` directly: the hook denies it. Every change goes through `sdlc backlog add`, `sdlc backlog epic add` and `sdlc backlog edit`.
- Order and removal are a person's decision. When an item should move or go, give the person the exact command to run in their own terminal (`sdlc backlog move B<n> --top`, `--before B<m>`, `--epic E<n>`, or `sdlc backlog drop B<n> --note "<reason>"`), explain why, and do not run it yourself.
- An item is ready when it has an outcome, at least one acceptance criterion and every dependency done.

**Steps**

1. **Without input: show the backlog.** Run `sdlc backlog list` and `sdlc backlog next`. Name the next ready item and, for every open item that is not ready, what blocks it: no outcome, no acceptance criteria, or open dependencies (`sdlc backlog list --json` has `missing` and `blockedBy`). Offer to refine one of them or to start the next ready item.
2. **With an epic or an idea: decompose.** Read the code, specs (`sdlc openspec list --specs`) and related explorations first. Propose items small enough for one change each; every item has a title, an outcome, at least one acceptance criterion, and its dependencies on the other items. Show the list and ask the person to confirm it with the AskUserQuestion tool (all, a subset, or revise). Add only the confirmed items: `sdlc backlog epic add "<title>" --goal "<goal>"` when the epic is new, then `sdlc backlog add "<title>" --epic E<n> --outcome "<outcome>" --accept "<criterion>" --depends B<n>` for each item, in the order you proposed.
3. **With an item `B<n>`: bring it to ready.** Read the item (`sdlc backlog list --json`) and ask what is missing. Write the answers with `sdlc backlog edit B<n> --outcome "<outcome>" --accept "<criterion>" --depends B<m>` (`--accept` and `--depends` replace the list; `--add-accept` appends; `--title`, `--kind`, `--risk` change the rest). Then offer to start it: `sdlc backlog start B<n>` creates the change with a draft intent; continue with `/sdlc:intent`.
4. **Priorities.** If the person wants a different order, or an item is no longer needed, give the exact `sdlc backlog move …` or `sdlc backlog drop …` command for them to run.
5. **Finish** with the backlog state after your changes (`sdlc backlog list`) and the next step from `sdlc next --json`.

<!--
Generated by sdlc 0.23.7 (https://github.com/marin-ai-tech/sdlc).
Required Notice: Copyright (c) 2026 marin-ai technologies (https://github.com/marin-ai-tech/sdlc)
License: PolyForm Noncommercial 1.0.0 (https://polyformproject.org/licenses/noncommercial/1.0.0) with the sdlc Additional Permissions, or a commercial license; see https://github.com/marin-ai-tech/sdlc
-->