jira-status

Read and move Jira issue statuses from the operator lane, using the Jira credential already granted to the sweep on thor (the credential never leaves that host — the script runs its API calls there over ssh). Verbs: `status <ISSUE>` reads the current status and available transitions; `move <ISSUE> "<target status>"` executes the transition whose name matches. Use when the operator says "flip SCRUM-2", "move the ticket to Pending", "what status is SCRUM-N in", or when arming the sweep's status watermark for a pickup test (move away, wait for a sweep to record it, move back). This is an OPERATOR tool: it acts as the operator's own hand on the board, outside the engine — the system's own board moves go through the jira bridge actor's allowlisted transition verb, never through this.

Ir para a instalação

Repositório: agentculture/culture-nodes
Última atividade na origem: 18 de agosto de 2026 às 20:38
Idioma detectado do SKILL.md: inglês
Estrelas: 3
Forks: 0

Opções de instalação

Por padrão, está selecionado o prompt que primeiro revisa a origem. Você pode mudar para um comando direto ou baixar uma cópia local.

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.

npx skills add https://github.com/agentculture/culture-nodes --skill jira-status

O comando permanece em uma só linha. Role horizontalmente para revisá-lo antes de copiar.

Prefere uma cópia local? Baixe os arquivos disponíveis atualmente no SkillsMP.

Revise os arquivos de origem

Leia o SKILL.md e os arquivos complementares exibidos pelo SkillsMP antes de decidir se vai instalar.

Explorador de arquivos

2 arquivos

SKILL.md

Instruções da origem · Visualização somente leitura

Voltar à pesquisa Voltar à instalação

jira

Comment on, create, and read Jira issues from the operator lane, using the Jira credential already granted to the sweep on thor (the credential never leaves that host — the script runs its API calls there over ssh). Verbs: `show <ISSUE>` reads summary, status and the last five comments with ids and author account ids; `comment <ISSUE> "<text>"` posts a comment and prints its id; `create --project KEY --summary "<text>" [--type Task] [--description "<text>"]` files an issue and prints its key. Everything it writes lands UNDER THE SYSTEM'S JIRA ACCOUNT, so the sweep filters those comments as self-echo by account id (`examples/pr-upkeep/pr_upkeep_jira.py` `jira_comment_is_self_echo`): this is the operator's own hand on the board — for creating proof tickets and reading what the sweep will see — NOT a way to produce a human's fact. The system's own board moves go through the jira bridge actor's allowlisted verbs, never through this. Use when the operator says "comment on SCRUM-5", "open a proof ticket", "what doe

2026-08-29

nodes-operator

Drive a running culture-nodes control plane: inspect runs/ledger/actors, author + validate + publish workflows, and assign real work to registered agent actors (codex-thor, codex-orin) through the normal engine dispatch path. Use when the user says "assign this to codex", "run it through nodes", "create a workflow for X", "what's running", "cancel that run", "check the ledger", or when you want to delegate a scoped task to the production actor fleet instead of doing it in-session. Works for ANY operator with the skill — Claude, the colleague backend, codex sessions, or a human at a shell — plain bash + curl + python3 against the public v1alpha1 HTTP API.

2026-08-29

assign-to-workforce

Fan out a converged devague plan's dependency waves to parallel agents in isolated git worktrees, one agent per task per wave, with TDD-gated merges by the main agent. Human gates: the exported spec, the implementation split plan (task map + per-task agent/model proposal + go/no-go), and the final PR. The devague CLI stays deterministic and non-orchestrating (#20) — it only *describes* the graph via `devague plan waves`; the operator (main agent) performs the fan-out. Use when the user says "assign to workforce", "fan out the plan", "parallel subagents", or after the `spec-to-plan` skill exports a plan. Authored and maintained in agentculture/devague (origin = devague); guildmaster pulls this skill from here and broadcasts it to the AgentCulture mesh — it is NOT vendored from guildmaster like the other skills here.

2026-08-27

Ver todas deste repositório

name	jira-status
description	Read and move Jira issue statuses from the operator lane, using the Jira credential already granted to the sweep on thor (the credential never leaves that host — the script runs its API calls there over ssh). Verbs: `status <ISSUE>` reads the current status and available transitions; `move <ISSUE> "<target status>"` executes the transition whose name matches. Use when the operator says "flip SCRUM-2", "move the ticket to Pending", "what status is SCRUM-N in", or when arming the sweep's status watermark for a pickup test (move away, wait for a sweep to record it, move back). This is an OPERATOR tool: it acts as the operator's own hand on the board, outside the engine — the system's own board moves go through the jira bridge actor's allowlisted transition verb, never through this.
type	command

jira-status — operator-lane Jira status reads and moves

bash .claude/skills/jira-status/scripts/jira-status.sh status SCRUM-2
bash .claude/skills/jira-status/scripts/jira-status.sh move SCRUM-2 "To Do"
bash .claude/skills/jira-status/scripts/jira-status.sh move SCRUM-2 Pending

What it does

status <ISSUE> — prints the issue's current status and the transitions available from it (names are what move matches against).
move <ISSUE> <target> — finds the available transition whose target status name equals <target> (case-insensitive) and executes it. Refuses with the available names when no transition matches — Jira transitions are workflow-dependent, so the error names your real options.

Custody

The Jira credential pair lives in ~/.culture-nodes/runner-secrets.env on thor (granted to the sweep; reuse approved by the operator 2026-08-18). The script sshes to thor and performs the REST calls there; neither the email nor the token ever appears on the local machine, in argv, or in output.

Contrast with the system's own write path: workflow runs move boards through the jira bridge actor (adapters/jira), whose transition_issue verb is bridge-allowlisted to one project prefix and one target transition (decision c19). This skill is the OPERATOR's hand — e.g. arming a pickup test — and deliberately does not widen or bypass that custody: it is the same act as the operator clicking the board, scripted.

Watermark-arming recipe (the reason this exists)

The sweep emits a status fact only when the status it reads differs from the last one it recorded (signal_event_watermarks). To make an issue already sitting in To Do fire a transitioned.to-do fact:

bash .claude/skills/jira-status/scripts/jira-status.sh move SCRUM-2 Pending
# wait until a sweep records Pending (watch signal_event_watermarks or the
# monitor), then:
bash .claude/skills/jira-status/scripts/jira-status.sh move SCRUM-2 "To Do"
# the next sweep emits transitioned.to-do and subscribed workflows fire.

Issues #193 (history-aware sweep) and #194 (failed-trigger re-mint) exist to make this recipe unnecessary; delete this section when they land.

jira-status

Informações da origem

Opções de instalação

Revise os arquivos de origem

Mais deste repositório

Mais deste repositório

jira-status — operator-lane Jira status reads and moves

What it does

Custody

Watermark-arming recipe (the reason this exists)

jira-status — operator-lane Jira status reads and moves

What it does

Custody

Watermark-arming recipe (the reason this exists)