niuyunda/agent-wave
/SKILL.md
# agvv ## 1) Role Boundary `agvv` is deterministic orchestration infrastructure, not a coding-quality judge. It is responsible for: - task/run state files under `.agvv/` - daemon-driven auto runs - worktree/process lifecycle - Git-backed completion checkpoints The orchestrator agent is responsible for planning, retry policy, and merge decisions. ## 2) Authoritative CLI Surface Top-level commands: - `agvv daemon` - `agvv projects` - `agvv tasks` - `agvv feedback` Not available as top-lev
tools
Updated Apr 8, 2026
$ install --global
skillsauthnpx skillsauth add niuyunda/agent-wave agent-waveInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 8, 2026, 2:10 AM10.6s22 files scanned
SKILL.md
agvv
1) Role Boundary
agvv is deterministic orchestration infrastructure, not a coding-quality judge.
It is responsible for:
- task/run state files under
.agvv/ - daemon-driven auto runs
- worktree/process lifecycle
- Git-backed completion checkpoints
The orchestrator agent is responsible for planning, retry policy, and merge decisions.
2) Authoritative CLI Surface
Top-level commands:
agvv daemonagvv projectsagvv tasksagvv feedback
Not available as top-level commands:
runssessionscheckpointsstatus
Use projects and tasks for state inspection.
3) Operational Query Commands
Projects:
agvv projectsagvv projects listagvv projects show <repo_path>agvv projects remove <repo_path>
Tasks:
agvv tasks [--project <repo_path>]agvv tasks list [--project <repo_path>]agvv tasks show <task_name> [--project <repo_path>]agvv tasks add --project <repo_path> --file <task_md> [--create-project] [--agent <name>]agvv tasks merge <task_name> [--project <repo_path>]
Daemon:
agvv daemon startagvv daemon statusagvv daemon stop
Feedback:
agvv feedback --title <text> [--body <text>] [--type bug|feature|refactor] [--issue]
4) tasks add Side Effects
tasks add does all of the following:
- ensures project repo/layout (
.agvv/config.json, hooks directory, task/archive folders) - auto-registers project in
~/.agvv/projects.json - creates task and
runs/directory - forces
auto_manage: true - sets queued feedback fields in task front matter
- auto-starts daemon unless
AGVV_SKIP_DAEMON_AUTOSTARTis truthy
Agent selection for daemon auto-runs:
task.mdfieldagent(or--agentoverride)- project config
default_agent - fallback
claude
5) Task Contract
Required task.md front matter:
name
Validation rules:
namemust match[A-Za-z0-9._-]+- duplicate names are rejected across active tasks and archive
- invalid incoming
statusis rejected
All extra front matter keys are preserved.
6) Runtime and Completion Semantics
- Every successful run must create a new checkpoint commit versus run
base_commit. reviewruns must also write a non-empty report file atreport_path.- Implement/repair runs can auto-commit pending work via
agent_runnerafter a zero exit code. - Auto-managed task: completed run -> task
done. - Non-auto-managed task: completed run -> task
pending. - Merge conflict sets task
blocked.
7) Minimal Orchestration Loop
agvv tasks add --project /repo/app --file /tmp/fix-login.md --agent codex
agvv projects show /repo/app
agvv tasks show fix-login --project /repo/app
agvv tasks merge fix-login --project /repo/app
Run discipline:
- inspect
tasks showbefore merge - avoid merge when task status is
failedorblocked - pass
--projectwhen task name might not be globally unique
8) Issue Capture
When behavior is incorrect, file reproducible evidence in:
docs/issues/docs/issues/ISSUE_TEMPLATE.md
Related Skills
openclaw/taskflow
tools
VerifiedTrustedCommunity
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.
357,764SKILL.mdUpdated Apr 10, 2026
openclaw/extensions/lobster
tools
VerifiedTrustedCommunity
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
357,764SKILL.mdUpdated Apr 10, 2026
steipete/extensions/lobster
tools
VerifiedTrustedCommunity
# Lobster Lobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation ## When to use Lobster | User intent | Use Lobster? | | ------------------------------------------------------ | --------------------------
357,588SKILL.mdUpdated Apr 13, 2026
steipete/xurl
tools
VerifiedTrustedCommunity
A CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.
356,423SKILL.mdUpdated Apr 13, 2026