backlog-plan

A read-only planning tool for backlogs in Azure DevOps, GitHub, and Jira. It reads tracker data and saves plans for a later step that applies changes.

In plain words
What is it for?
Use it to find candidate work, enrich assigned items, triage issues, plan a sprint or milestone, and resume an interrupted planning workflow.
Why use it?
You may need to analyze or prepare backlog work without changing the shared tracker yet. This separates planning from execution and prevents accidental edits.

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/microsoft/hve-core/backlog-plan
Any agent
npx skills add microsoft/hve-core --skill backlog-plan
Clone the repo
git clone --depth 1 https://github.com/microsoft/hve-core

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,727 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 $0.00037 $0.01727
Opus 5 $0.00018 $0.00864
Sonnet 5 $0.00007 $0.00345
Haiku 4.5 $0.00004 $0.00173

Measured 2d ago against content hash 2a0db007564c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backlog-plan 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.

.github/skills/project-planning/backlog-plan/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backlog Plan

Read-only backlog planning for Azure DevOps, GitHub, and Jira. This command resolves the backing tracker at runtime, selects a planning mode, and executes it through the shared conventions and reference structure of the backlog-management skill. It produces planning files that a separate execution pass acts on.

This command never mutates a tracker. It creates, updates, and reads files under the platform tracking root, and it reads from the tracker. Every create, update, transition, link, close, and comment belongs to backlog-execute.

When to Use

Use this command to plan backlog work on any supported platform:

  • Discover candidate work from a user request, a set of documents, or a search.
  • Retrieve the work assigned to you and enrich it into an implementation-ready handoff.
  • Triage existing items and recommend field, label, priority, or status changes.
  • Plan a sprint, iteration, or milestone against coverage, capacity, dependencies, and gaps.
  • Resume an interrupted planning workflow from its durable artifacts.

Use backlog-execute instead when the intent is to apply changes to a tracker. Use functional-planner instead when the input is a PRD and the output is a work-item hierarchy.

Required Flow

Step 1: Resolve the platform

Run the Platform Resolution section of the backlog-management skill before any planning work. Carry its resolved platform and readiness verdict forward. When resolution is ambiguous, resolve it there rather than assuming a tracker here.

Every mode below is read-only, so a platform inferred from preflight success may proceed without the confirmation a mutating workflow requires.

Step 2: Select the planning mode

Classify the request into exactly one mode. When the argument names a mode, use it. Otherwise infer from these signals, and when two modes remain plausible, state both with a brief rationale and ask.

Mode Signals Protocol
discover discover, find, search, extract, gaps, roadmap, backlog brief, from a document Discovery workflow in the workflows reference
my-work my items, assigned to me, my queue, what am I working on Stage 1 of the task-planning reference
task-plan task planning, prepare for implementation, hand off to research Stage 2 of the task-planning reference
triage triage, classify, categorize, prioritize, duplicates, untriaged Triage workflow in the workflows reference plus the platform's Triage Delta
sprint sprint, iteration, milestone, release, capacity, velocity, coverage The sprint-planning reference plus the platform's Sprint Planning Delta
resume resume, continue, next step, suggest, where was I Resumption below

Read the full file on GitHub · 111 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. 2d ago First seen · 111 lines · 37 tokens per session scan A 2a0db007564c

Subscribe to this mod's changes

backlog-plan is a skill published in the GitHub repository microsoft/hve-core (1,411 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,727 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 2026-08-30.