Skip to content

hashgraph-online/awesome-codex-plugins / plugins/alpoxdev/hypercore/skills/hyper-issue

hyper-issue

Verified

Use this skill when the user wants a confirmed finding or a piece of decided work recorded as an implementation-ready issue, wants a fixed batch of open issues selected and grouped into disjoint work lanes, or names issue numbers such as `#1~3` to run as a batch. It investigates only enough to make the issue self-contained, writes the issue in English for a fresh agent with a machine-readable scope block, produces a batch manifest, and hands the lanes to the hyper orchestrator when work should follow. Do not use for implementing the work itself, for general documentation, or for a plan file.

references/batch-manifest.md

View on GitHub
# Batch Manifest

Use this reference before writing `.hyper/issues/<slug>/batch.md`. It owns the manifest format, the lane table, and the handoff line.

## Contents

- Format
- Rules
- Worked example lane split

## Format

```markdown
# Batch: <slug>

- 생성 일시: YYYY-MM-DD HH:MM
- 저장소: <owner/repo>
- 질의: `<the exact query>` | 번호: `<the numbers as written>` -> <expanded list>
- 수집: <rows returned> / 총계 <total> | 페이지 <n>개 | 잘림 없음 (번호 모드: 남김 <k> / 지목 <n>)
- 대상 브랜치: <base branch>
- 레인 상한: <n>
- 차단: <none | the blockers, one per line>

## Issue 목록

| # | 이슈 | 제목 | 분류 | 크기 | 레인 | 순서 | verify |
|---|---|---|---|---|---|---|---|
| 1 | #12 | <title> | bug | s | orders-idempotency | 1 | `bun test src/api/orders.test.ts` |
| 2 | #14 | <title> | task | m | docs-parity | 1 | `bash scripts/check.sh` |

## Lane 표

| Lane | 이슈 순서 | 쓰는 경로 | 근거 |
|---|---|---|---|
| orders-idempotency | #12 | src/api/orders.ts, src/api/orders.test.ts | 1 |
| docs-parity | #14 | skills/**/*.md | 1 |

## 그래프

- 간선: #12 -> #14 (직접 선언 아님, `touches` 겹침 아님, 순서만 선언 순서)
- 순환: <none | the cycle>

## 공백과 차단

- <issue> - `hyper:` 블록 없음, `## Scope`에서 재도출함
- <issue> - `size: l`, 배정 전 분할 필요
- #<n> - 제외: <pull request | closed | not found | read failed>

## 핸드오프

- 배치 명세: `.hyper/issues/<slug>/batch.md`
- 이슈 <n>건, 레인 <m>개, 차단 <k>건
- 다음 단계는 이 파일을 고정 입력으로 읽는다. 목록을 바꾸지 않는다.
- 다음 단계: hyper (넘김, YYYY-MM-DD HH:MM) | 없음 (<--no-run | --from-hyper | 실행 가능한 레인 없음>)
```

## Rules

- The `## Issue 목록` order is the canonical order from selection; never re-sort it after the fact.
- `## Lane 표` lists the union of written paths per lane, so a reader can confirm the lanes are disjoint at a glance.
- A lane with one issue still appears; a lane is not "parallelism", it is a write set.
- `## 그래프` records edges with their origin: declared, overlap-derived, or ordering-only.
- `## 공백과 차단` is never empty unless every issue had a parseable block, no split was needed, and no named number was excluded; write `none` explicitly.
- The handoff line's counts are read off the tables, never estimated.
- `대상 브랜치` records only the branch the user named for delivery. With no named branch it reads `미정 (사용자 지정 없음)`; the batch never invents a base branch, because the plan stage picks its own integration base and the user's delivery words decide the push.

## Worked Example Lane Split

Three issues arrive:

- `#21` writes `src/api/a.ts` and `src/api/a.test.ts`, `size: s`
- `#22` writes `src/api/a.ts`, `depends_on: [21]`
- `#23` writes `docs/api.md`

Result: `#21` and `#22` share a path, so they form one lane in dependency order (`21`, then `22`); `#23` is its own lane. Two lanes, both runnable at once, with no path written by two lanes.

A fourth issue `#24` that writes both `src/api/a.ts` and `docs/api.md` joins the `21`/`22` lane and forces `#23` to wait behind it in a merged lane, because merging the lanes is the only way to keep the write sets disjoint.

## Sources

> Checked 2026-11-07.

| Claim | Source |
|---|---|
| A fixed canonical list, per-lane order, and a manifest the next stage reads unchanged | [kdy1-scripts slop-fix-batch](https://github.com/kdy1/kdy1-scripts) |
| Disjoint write sets as the lane rule, and shared files forcing one lane | [automazeio/ccpm](https://github.com/automazeio/ccpm) |
| Conflict rates between concurrent agent changes as the reason for disjointness | [AI Agent PRs on GitHub](https://arxiv.org/abs/2607.04697) |

### Evidence grade

`LOCAL` - the manifest format and the lane table are this package's design; the freeze rule is adapted from the named prior art.
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 197kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 197kUpdated Claude CodeCodexVerifiedInstall