ワンクリックで
issue-start
Claim a HoP GitHub issue, create an isolated worktree from main, and prepare a scoped execution brief before implementation.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Claim a HoP GitHub issue, create an isolated worktree from main, and prepare a scoped execution brief before implementation.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Pipeline simplificado: documento fonte → extração de conhecimento → padrões reutilizáveis → classificação contra repositório → canonical docs. Focado em gerar docs canônicos a partir de um único documento (currículo, análise, transcript). NÃO gera skills, exercícios ou integração profunda de currículo — apenas canonical docs + atualização de tags/aliases + system-of-record. Dispara com: 'canonicalize this document', 'extract canonical from', 'doc to canonical', 'create canonical docs from', 'documento para canonical', 'extrair canônicos de'.
Implementa uma camada de selecao de contexto model-agnostic e vendor-independent. Define um formato padronizado de contexto que qualquer modelo pode consumir, um Context Router que resolve queries de qualquer agente contra o grafo relacional e storage em tiers, e Vendor Adapters que traduzem o formato agnostico para o formato nativo de cada modelo. Transforma contexto no ativo mais duravel da organizacao — portavel entre modelos, sessoes, e provedores. Dispara com: 'neutral selection', 'model-agnostic context', 'vendor-independent context', 'context format standard', 'context router', 'multi-model context', 'portable context', 'cross-model context', 'camada neutra', 'contexto agnostico', 'formato de contexto', 'vendor adapter', 'neutral context layer', 'context portability', 'model migration context'.
Torna o retrieval de contexto budget-aware: cada candidato a retrieval e ranqueado por razao valor/custo antes de ser injetado no contexto. Implementa um Information Value Predictor que estima reducao de incerteza por candidato, um Token Cost Estimator que computa custo em tokens, e um Utility Feedback Loop que aprende com uso real — quais itens recuperados foram efetivamente referenciados pelo modelo. Previne o memory feedback loop onde o sistema construido para resolver o problema de memoria se torna o motor da degradacao. Contrapoe diretamente o Link 4 (inert memory feedback) do Agent Degradation Loop. Dispara com: 'selection-budgeted retrieval', 'budgeted retrieval', 'retrieval budget', 'cost-benefit retrieval', 'information value predictor', 'utility feedback retrieval', 'retrieval ranking', 'orcamento de retrieval', 'busca budgetada', 'recuperacao com orcamento', 'value-cost retrieval', 'retrieval utility feedback'.
Implementa armazenamento de contexto em tres tiers (hot/warm/cold) com promocao e democao baseadas em relevancia. Mantem o conjunto de trabalho ativo deliberadamente pequeno na hot tier (cache in-memory), move contexto recentemente relevante para warm tier (NVMe, baixa latencia), e arquiva historico completo na cold tier (object storage, alta latencia). O Tier Orchestrator executa transicoes baseadas em scores de relevancia e prefetch preditivo antes de cada passo de raciocinio. Previne context rot (cada token acumulado degrada qualidade do passo seguinte) e separa preocupacao de armazenamento de preocupacao de selecao. Dispara com: 'tiered context', 'tier storage', 'context tiers', 'hot warm cold', 'tiered storage', 'context promotion', 'context demotion', 'tier orchestrator', 'promocao de contexto', 'democao de contexto', 'armazenamento em tiers', 'tiered context storage', 'context tier management'.
Operacionaliza um curriculo de autonomia para agentes: controla a proporcao entre rollouts supervisionados (professor/humano) e rollouts auto-gerados (agente) com um parametro lambda, gates de prontidao por classe de tarefa, e uma progressao explicita observe→assist→own. Aplica importance sampling para corrigir a distribuicao mista. Previne cold-start collapse (rollouts puros do agente antes de aprender recuperacao) e autonomy stagnation (agente nunca pratica recuperacao autonoma). Usar ao implantar um novo agente em producao, ao fazer transition de fluxo manual para agentico, ao calibrar o grau de supervisao de um agente existente, ou quando o agente apresenta comportamento fragil em cenarios nao-supervisionados. Dispara com: 'autonomy curriculum', 'curriculo de autonomia', 'lambda schedule', 'teacher mixing', 'rollout sampling', 'autonomy dial', 'autonomy progression', 'observe assist own', 'readiness gate', 'student rollout', 'teacher-student mix', 'gradual autonomy', 'agente semi-supervisionado', 'autonom
Separa o sinal de melhoria do agente em dois componentes independentes: magnitude (o quanto o modelo acredita que uma mudanca importa, extraida de self-distillation delta, log-ratio, atencao, ou confianca interna) e direcao (para onde a mudanca deve ir, determinada por verificador externo, testes, ou revisao humana). Combina magnitude × direcao em um plano de correcao ponderado: gaste esforco de correcao onde o agente tem conviccao FORTE e o verificador confirma a direcao; reduza ou escale quando a direcao e incerta. Previne information leakage (agente aprende a imitar formato sem substancia) e overconfidence collapse (self-distillation puro sem verificacao externa). Usar ao projetar loops de melhoria de agente, ao implementar self-distillation com verificacao, ao calibrar feedback de producao, ou quando o agente produz outputs com formato correto mas conteudo errado. Dispara com: 'magnitude direction', 'verifier split', 'trust but verify', 'confidence direction', 'correction weight', 'self-distillation verif
| name | issue-start |
| description | Claim a HoP GitHub issue, create an isolated worktree from main, and prepare a scoped execution brief before implementation. |
| license | MIT |
| compatibility | opencode |
| metadata | {"audience":"all-agents","workflow":"github","priority":"high"} |
I handle the safe setup phase for HoP issue work: confirm the issue, claim it, create an isolated branch/worktree from main, read the project context, and produce a scoped execution brief before implementation begins.
Load this skill when:
Follow these steps in order. Do not write implementation code until setup is complete.
If the user gave an issue URL, extract the number. If they said "issue 42", use 42.
gh issue view <N> --json number,title,body,assignees,labels,state
If the issue is missing or closed, stop and report.
gh issue view <N> --json assignees,labels --jq '{assignees: [.assignees[].login], labels: [.labels[].name]}'
If agent:working exists or the issue is already assigned, stop and ask whether to proceed anyway. Do not steal active work silently.
gh label create "agent:working" --color "FFA500" --description "Agent session actively working on this issue" 2>/dev/null || true
gh issue edit <N> --add-assignee "@me" --add-label "agent:working"
gh issue comment <N> --body "Agent session started - $(date -u +%Y-%m-%dT%H:%M:%SZ)"
HoP issue branches use the observed convention:
issue/<N>-<slug>
Examples:
issue/123-fix-tenant-artifact-pathsissue/124-dashboard-health-panel-regressionissue/125-crossroad-logger-parityUse a short lowercase slug from the issue title. Keep it readable; do not encode implementation details.
BRANCH="issue/<N>-<slug>"
WORKTREE=".worktrees/<N>-<slug>"
echo "Branch: $BRANCH"
echo "Worktree: $WORKTREE"
git fetch origin main
git worktree add -b "$BRANCH" "$WORKTREE" origin/main
echo "Worktree ready at: $WORKTREE"
echo "Branch: $BRANCH"
If the worktree or branch already exists, stop and inspect instead of deleting automatically. Only remove existing branches/worktrees with explicit user approval or when you created them in this session.
In the worktree, read the relevant context before implementation:
AGENTS.mddocs/system-of-record.mdagents/manifest.yamlREADME.mddocs/canonical/, docs/decisions/, docs/guides/, and docs/evidence/DESIGN.md for dashboard/UI work.github/PULL_REQUEST_TEMPLATE.mddocs/guides/crossroad-change-policy.md if crossroad files may be touchedAlso inspect adjacent code and tests for the specific surface:
scripts/src/lib/, src/config/, src/clients/, src/persistence/src/runner/, src/evaluator/, src/reporter/, src/orchestration/packages/dashboard/tests/Create a brief before implementation. Use a concise inline template. Save it only if the issue is non-trivial or the user wants an artifact. Prefer docs/analysis/ for non-normative working notes unless the repo has an approved briefs directory.
Brief template:
# Execution Brief - Issue #N: <title>
## Objective
<One sentence.>
## Success Criteria
- <Concrete, verifiable outcome>
## In Scope
- <Files/modules/behaviors included>
## Out of Scope
- <Explicit non-goals>
## Candidate Files
- <Likely files to modify>
## Sensitive Surfaces
- Tenant paths: <yes/no + details>
- Crossroad files: <yes/no + details>
- Env vars: <yes/no + details>
- Dashboard design: <yes/no + DESIGN.md relevance>
- Docs/ADR impact: <yes/no + docs>
## Implementation Strategy
<Steps and existing pattern to follow.>
## Validation Plan
- <npm script or manual QA command>
For trivial single-file fixes, a brief in the chat is enough.
Report:
Issue #N claimed.
Branch: issue/<N>-<slug>
Worktree: .worktrees/<N>-<slug>
Execution brief:
<brief summary>
Approve the brief to proceed, or request changes.
When implementation is complete, load the issue-review skill.
Run /compact after setup and before implementation on non-trivial issues. The setup phase creates noisy context; implementation should start from the brief and relevant files.
main.issue/<N>-<slug> branch names..runtime/ or artifacts/ without considering HOP_TENANT_ID tenant isolation.gh issue edit N --add-assignee "@me" --add-label "agent:working"
gh issue comment N --body "Agent session started - $(date -u +%Y-%m-%dT%H:%M:%SZ)"
git fetch origin main
git worktree add -b "issue/N-short-slug" ".worktrees/N-short-slug" origin/main