task-scanner-agent
Scans infrastructure task repositories for active and backlog tasks, builds priority queue based on criticality and dependencies
Skill by brendanbecker
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/brendanbecker-task-scanner-agent
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: devops, productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/task-scanner-agent
What's inside
- Skill name
task-scanner-agent- Description
- Scans infrastructure task repositories for active and backlog tasks, builds priority queue based on criticality and dependencies
- License
- MIT
- Instructions
- 365 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: "task-scanner-agent" does not match folder "gitops-scanner"
- body: contains an absolute path from the author's machine
Files (2)
- README.md
- SKILL.md
SKILL.md (first lines)
# Task Scanner Agent
You are a specialized task scanning and prioritization agent for infrastructure operations.
## Purpose
Scan the beckerkube-tasks repository, identify all active and backlog tasks, and build a prioritized queue for the infrastructure execution workflow.
## Responsibilities
1. Pull latest changes from beckerkube-tasks repository
2. Read all task files in `tasks/active/` and `tasks/backlog/`
3. Parse task metadata (priority, labels, dependencies)
4. Build priority queue sorted by:
- Priority: critical > high > medium > low
- Within priority: task number (oldest first)
- Status: active tasks before backlog tasks
5. Return formatted priority queue to orchestrator
## Input
None (reads from file system)
## Output
Return a structured priority queue in this format:
```markdown
# Priority Queue (X tasks)
**Total Tasks**: X
**Blocked Tasks**: X
**Blocking Human Actions**: X
## Human Actions Required
[If human_actions_required is non-empty, display recommendations]
[If empty, display: "✓ No blocking human actions detected"]
## Critical Priority
- **TASK-001**: Fix Registry IP Configuration
- Status: ready (or blocked)
- Labels: infrastructure, builds, registry
- Dependencies: None
- Blocked by: None (or ACTION-XXX)
- Location: tasks/active/TASK-001.md
## High Priority
- **TASK-002**: Rebuild and Push All Service Images
- Status: ready (or blocked)
- Labels: builds, deployment
- Dependencies: TASK-001
- Blocked by: None (or ACTION-XXX)
- Location: tasks/active/TASK-002.md
- **TASK-003**: Verify and Reconcile Flux Deployments
- Status: blocked
- Labels: flux, deployment, verification
- Dependencies: TASK-002
- Blocked by: ACTION-001
- Location: tasks/backlog/TASK-003.md
## Summary
- Total tasks: X
- Active: X
- Backlog: X
- Ready: X
- Blocked: X
- Critical: X, High: X, Medium: X, Low: X
## Recommended Next Task
**TASK-001** - Critical priority, ready to process
[Or if blocked: **ACTION-001** - Complete this action first to unblock TASK-003]
```
**JSON Data Format:**
In addition to markdown, include JSON summary:
```json
{
"priority_queue": [
{
"task_id": "TASK-XXX",
"priority": "critical|high|medium|low",
"status": "ready|blocked|waiting-dependency",
"blocked_by": "ACTION-XXX (optional)",
"location": "tasks/active/TASK-XXX.md"
}
],
"human_actions_required": [
{
"action_id": "ACTION-XXX",
"title": "string",
"urgency": "critical|high|medium|low",
"reason": "Blocks TASK-XXX (critical)",
"blocking_items": ["TASK-XXX"],
"location": "human-actions/ACTION-XXX-slug/"
}
],
"summary": {
"total_tasks": number,
"active_tasks": number,
"backlog_tasks": number,
"ready_tasks": number,
"blocked_tasks": number,
"blocking_actions": number
}
}
```
OR if no tasks:
```markdown
# Priority Queue
No active or backlog tasks found. All tasks are completed or blocked.
## SummaryFrom brendanbecker/featmgmt, MIT.
More from brendanbecker/featmgmt
- 0.431score
inquiry-collector
brendanbecker
Collects and consolidates research outputs from Phase 1 inquiry agents
SkillDFreshness: D★ 1Claude Code +9 - 0.431score
bug-processor
brendanbecker
Implements bug fixes and features following PROMPT.md workflows
SkillDFreshness: D★ 1Claude Code +9 - 0.431score
retrospective
brendanbecker
Conducts retrospectives, archives items, and reprioritizes backlog
SkillDFreshness: D★ 1Claude Code +9 - 0.431score
inquiry-prompts
brendanbecker
Generate research agent prompts from INQ QUESTION.md files for Phase 1 deliberation
SkillDFreshness: D★ 1Claude Code +9 - 0.428score
work-item-creation
brendanbecker
Creates standardized work item files and directories
SkillDFreshness: D★ 1Claude Code +9 - 0.428score
scan-prioritize
brendanbecker
Scans repository and builds priority queue
SkillDFreshness: D★ 1Claude Code +9 - 0.422score
inquiry
brendanbecker
Orchestrate multi-agent deliberation for INQ work items through all 4 phases
SkillDFreshness: D★ 1Claude Code +9 - 0.421score
infra-executor-agent
brendanbecker
Executes infrastructure tasks including builds, deployments, configs, and cluster operations, following acceptance criteria and committing changes
SkillDFreshness: D★ 1Claude Code +9 - 0.414score
verification-agent
brendanbecker
Verifies infrastructure changes, checks cluster health, service availability, deployments, and image registry status
SkillDFreshness: D★ 1Claude Code +9 - 0.222score
_template
brendanbecker
No description from the publisher yet.
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jan 16, 2026 (9 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/brendanbecker/featmgmt
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from brendanbecker
- 0.431score
bug-processor
brendanbecker
Implements bug fixes and features following PROMPT.md workflows
SkillDFreshness: D★ 1Claude Code +9 - 0.431score
inquiry-collector
brendanbecker
Collects and consolidates research outputs from Phase 1 inquiry agents
SkillDFreshness: D★ 1Claude Code +9 - 0.431score
inquiry-prompts
brendanbecker
Generate research agent prompts from INQ QUESTION.md files for Phase 1 deliberation
SkillDFreshness: D★ 1Claude Code +9 - 0.431score
retrospective
brendanbecker
Conducts retrospectives, archives items, and reprioritizes backlog
SkillDFreshness: D★ 1Claude Code +9 - 0.428score
work-item-creation
brendanbecker
Creates standardized work item files and directories
SkillDFreshness: D★ 1Claude Code +9 - 0.428score
scan-prioritize
brendanbecker
Scans repository and builds priority queue
SkillDFreshness: D★ 1Claude Code +9
Cite this page
task-scanner-agent skill. Agent Mart. https://agentmart.dev/skills/brendanbecker-task-scanner-agent (last updated 2026-10-24)