Internal skill for normalizing mission artifact structure and metadata.
Internal skill for expanding mission goals into runnable tasks.
Internal skill for task-granular mission progress reporting.
Internal skill for recovering mission execution after interruption or failure.
Internal skill for executing a single validate task through mission runtime.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
mission 是一个面向 Claude Code 的本地任务编排插件。
work / validate 任务显示进度/mission:start <prompt>/mission:providers [worker] [validator]resume 不受 workspace 默认值变更影响codex CLI,MISSION_CODEX_VALIDATOR_RUNNER 仅作为 overridedist/kimicodexclaude plugin marketplace add Loner1024/claude-mission-plugin --scope user
claude plugin install mission@local-mission --scope user
claude plugin enable mission@local-mission --scope user
如果当前 Claude Code 会话已经打开,执行:
/reload-plugins
claude plugin marketplace add /absolute/path/to/claude-mission-plugin/.claude-plugin/marketplace.json --scope local
claude plugin install mission@local-mission --scope local
claude plugin enable mission@local-mission --scope local
源码变更后更新本地安装:
claude plugin update mission@local-mission --scope local
/mission:setup
/mission:providers [worker] [validator]
/mission:start <mission-prompt>
/mission:status [mission-id]
/mission:resume <mission-id>
/mission:result [mission-id]
/mission:cancel <mission-id>
canceledvalidate 默认走本机 codex CLI。
MISSION_CODEX_VALIDATOR_RUNNERCODEX_BINARY示例:
export MISSION_CODEX_VALIDATOR_RUNNER=/absolute/path/to/validator-runner.ts
export CODEX_BINARY=/absolute/path/to/codex
如果未设置 MISSION_CODEX_VALIDATOR_RUNNER,插件会检测:
codex login status
只有默认 Codex CLI 或 override runner 至少有一个可用时,validate 任务才会继续执行。
构建:
bun run build
测试:
bun test
类型检查:
bun run typecheck
插件校验:
claude plugin validate .claude-plugin/marketplace.json
claude plugin validate plugins/mission/.claude-plugin/plugin.json
mission is a local mission orchestration plugin for Claude Code.
work tasksvalidate taskswork / validate task at a time/mission:start <prompt>/mission:providers [worker] [validator]codex CLI by default; MISSION_CODEX_VALIDATOR_RUNNER is only an overridedist/kimicodexclaude plugin marketplace add Loner1024/claude-mission-plugin --scope user
claude plugin install mission@local-mission --scope user
claude plugin enable mission@local-mission --scope user
If Claude Code is already running, reload plugins:
/reload-plugins
claude plugin marketplace add /absolute/path/to/claude-mission-plugin/.claude-plugin/marketplace.json --scope local
claude plugin install mission@local-mission --scope local
claude plugin enable mission@local-mission --scope local
Update an existing local install after source changes:
claude plugin update mission@local-mission --scope local
npx claudepluginhub loner1024/claude-mission-plugin --plugin missionUse Kimi from Claude Code to ask questions or delegate tasks.
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
Installer for TÂCHES' Get-Shit-Done workflow system - meta-prompting, context engineering and spec-driven development
Curated Claude Code skills and commands for prompt engineering, MCP servers, subagents, hooks, and productivity workflows
AI-native task management system. Track progress, coordinate multi-agent work, manage hierarchical tasks with dependencies, sprints, acceptance criteria, and a web dashboard.
Implementation of the babysitter technique - continuous orchestration loops for deterministic development. Run Claude in a loop with orchestration steps based on the babysitter-sdk and technique.
Claude Code integration for MCP Task Orchestrator — schema-aware context, note-driven workflow