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.
npx agentmods add skills/microsoft/hve-core/backlog-managementnpx skills add microsoft/hve-core --skill backlog-managementgit clone --depth 1 https://github.com/microsoft/hve-coreWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00034 | $0.05143 |
| Opus 5 | $0.00017 | $0.02572 |
| Sonnet 5 | $0.00007 | $0.01029 |
| Haiku 4.5 | $0.00003 | $0.00514 |
Grade C, and why
backlog-management scanned grade C with 1 finding 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 3d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- markdown-table-prettify-ignore-start --> How it starts
The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlog Management
Shared, platform-agnostic conventions for backlog managers across Azure DevOps, GitHub, and Jira. This skill owns the structural core that every platform reuses: how planning files are named and laid out, how planned items are identified, how candidate work is compared to existing work, how autonomy gates mutations, how outbound text is sanitized, and how an interrupted workflow resumes. Each platform contributes only its small delta (the command surface, field vocabulary, reference-ID prefix, and action verbs) through a per-platform reference.
When to Use
Use this skill when running any backlog workflow for a supported platform:
- Discovery — turn user requests, artifacts, or queries into candidate work items.
- Triage — assess existing items, recommend field, label, priority, and status changes, and flag duplicates.
- PRD-to-work-item planning — map a PRD into a validated work-item hierarchy for a separate execution pass.
- Sprint and iteration planning — analyze a delivery window for coverage, capacity, dependencies, and gaps, and recommend grooming candidates.
- Execution — process a reviewed handoff into sequential create, update, transition or move, and comment operations.
Read the platform-agnostic conventions below, then load the reference that matches the active platform for its concrete command surface and vocabulary.
How This Skill Is Organized
- This file — the platform-agnostic core: platform resolution, planning-file lifecycle, directory conventions, planning-type enum, scope normalization, reference-ID scheme, similarity assessment, autonomy tiers, content sanitization, state persistence, and human review triggers.
- references/workflows.md — the platform-agnostic workflow protocols (discovery, triage, execution), the platform binding resolution table, the operation contract, dry-run and error handling, and the shared planning-file templates.
- references/story-quality.md — work-item quality at epic, feature, user story, and task level: title and description conventions, acceptance criteria, definition of done, scope and sizing signals, evidence sourcing, completeness dimensions, and the authoring and refinement coaching loop.
- references/sprint-planning.md — the platform-agnostic sprint and iteration planning protocol: container binding, coverage and capacity analysis, gap and dependency detection, grooming recommendations, and the sprint-plan template.
- references/task-planning.md — assigned-work retrieval and enrichment: identity-scoped retrieval, repository-context gathering, discussion integration, and the implementation handoff record.
- references/ado.md — Azure DevOps platform delta: MCP ADO command surface, namespaced field vocabulary, the
WIreference prefix, action verbs, PRD hierarchy (Epic → Feature → User Story), relationship semantics, and work-item tracking paths. - references/ado-pull-request.md — Azure DevOps pull request creation: work item discovery and linking, reviewer identification from git history, the seven-phase creation protocol, and its planning-file formats.
- references/ado-build-info.md — Azure DevOps build and pipeline information: pipeline tool surface, build location by PR, build ID, or branch, log extraction, and summarization rules.
- references/github.md — GitHub platform delta: MCP GitHub command surface, supported operations, field vocabulary and field matrix, search syntax, issue body and type strategy, label taxonomy, milestone protocol, the
ISreference prefix, action verbs, community-communication guardrails, PRD sub-issue hierarchy, and issue tracking paths. - references/jira.md — Jira platform delta: command surface (delegated to the
jiraskill), field vocabulary, theJIreference prefix, action verbs, PRD hierarchy and field-mapping rules, triage and update decisions, and Jira tracking paths.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 338 lines · 34 tokens per session scan C db85335cb0c4
backlog-management is a skill published in the GitHub repository microsoft/hve-core (1,411 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 5,143 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…