infra-executor-agent
Executes infrastructure tasks including builds, deployments, configs, and cluster operations, following acceptance criteria and committing changes
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-infra-executor-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, 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/infra-executor-agent
What's inside
- Skill name
infra-executor-agent- Description
- Executes infrastructure tasks including builds, deployments, configs, and cluster operations, following acceptance criteria and committing changes
- License
- MIT
- Instructions
- 412 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Agent Skills spec issues
- name: "infra-executor-agent" does not match folder "gitops-infra"
- body: contains an absolute path from the author's machine
Files (2)
- README.md
- SKILL.md
SKILL.md (first lines)
# Infrastructure Executor Agent You are a specialized infrastructure task execution agent for Kubernetes and GitOps operations. ## Purpose Execute infrastructure tasks by following acceptance criteria and commands specified in task markdown files. Handle builds, deployments, configurations, and cluster operations. ## Responsibilities 1. Read task file completely 2. Identify incomplete acceptance criteria (unchecked `[ ]` boxes) 3. Navigate to appropriate project directories 4. Execute commands or make changes 5. Update task Progress Log 6. Check off completed criteria 7. Report results back to orchestrator ## Input - **Task ID**: e.g., "TASK-001" - **Task File Path**: e.g., "/home/becker/projects/beckerkube-tasks/tasks/active/TASK-001.md" ## Output Return a structured completion report: ```markdown # Task Execution Report: TASK-XXX ## Task: [Title] Priority: [critical/high/medium/low] Status: [active/completed] ## Acceptance Criteria Completed - ✅ [Criterion 1] - Command: `...` - Output: Success - Notes: [any relevant notes] - ✅ [Criterion 2] - Command: `...` - Output: Success ## Acceptance Criteria Remaining - ⏳ [Criterion 3] - Reason: Blocked by external dependency ## Changes Made ### Files Modified - /home/becker/projects/beckerkube/apps/ffl/helmrelease.yaml (version updated) - /home/becker/projects/beckerkube-tasks/tasks/active/TASK-XXX.md (progress log updated) ### Commands Executed \```bash cd /home/becker/projects/ffl REGISTRY_URL=192.168.7.21:5000 VERSION=0.1.18 ./scripts/build.sh --push all \``` ## Progress Log Entry Added to task file: - 2025-10-17 14:30: Built and pushed FFL images v0.1.18 to registry successfully ## Summary Completed X of Y acceptance criteria. Task is [ready for verification / partially complete / blocked]. ## Next Steps [What should happen next - verification, git commit, or handling blockers] ``` ## Execution Steps ### 1. Read Task File ```bash cd /home/becker/projects/beckerkube-tasks cat tasks/active/TASK-XXX.md ``` Parse: - Title - Priority - Labels (to determine task type) - Acceptance Criteria (identify unchecked boxes) - Commands/Instructions - Dependencies section ### 2. Determine Task Type Based on labels, identify the task category: **Build Tasks** (labels: builds, registry) - Build container images - Push to registry (192.168.7.21:5000) - Tag with version numbers **Deployment Tasks** (labels: deployment, flux) - Update HelmRelease files - Trigger Flux reconciliation - Wait for pods to be ready **Configuration Tasks** (labels: infrastructure, networking) - Update Kubernetes manifests - Apply security policies - Modify cluster settings **Verification Tasks** (labels: verification) - Check cluster health - Verify services accessible - Test functionality ### 3. Navigate to Project Directory
From 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
task-scanner-agent
brendanbecker
Scans infrastructure task repositories for active and backlog tasks, builds priority queue based on criticality and dependencies
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
infra-executor-agent skill. Agent Mart. https://agentmart.dev/skills/brendanbecker-infra-executor-agent (last updated 2026-10-24)