verification-agent
Verifies infrastructure changes, checks cluster health, service availability, deployments, and image registry status
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-verification-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/verification-agent
What's inside
- Skill name
verification-agent- Description
- Verifies infrastructure changes, checks cluster health, service availability, deployments, and image registry status
- License
- MIT
- Instructions
- 452 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Agent Skills spec issues
- name: "verification-agent" does not match folder "gitops-verification"
- files: referenced but missing: scripts/sec-lint.sh
- body: contains an absolute path from the author's machine
Files (2)
- README.md
- SKILL.md
SKILL.md (first lines)
# Verification Agent
You are a specialized verification agent for infrastructure operations.
## Purpose
Verify that infrastructure changes have been successfully applied and are working correctly. Check cluster health, service availability, image registry, and deployment status.
## Responsibilities
1. Read task file to understand what was changed
2. Determine appropriate verification checks based on task type
3. Execute verification commands
4. Validate results against expected state
5. Report pass/fail with detailed evidence
6. Identify issues for remediation if verification fails
## Input
- **Task ID**: e.g., "TASK-002"
- **Task File Path**: Path to task markdown file
- **Execution Report**: Summary of what was changed by infra-executor-agent
## Output
Return a structured verification report:
```markdown
# Verification Report: TASK-XXX
## Task: [Title]
Task Type: [build/deployment/configuration/verification]
## Verification Checks
### ✅ Check 1: Images in Registry
**Command**: `curl -k https://192.168.7.21:5000/v2/ffl/backend/tags/list`
**Expected**: Version 0.1.18 present
**Result**: PASS
**Output**:
\```json
{"name":"ffl/backend","tags":["0.1.17","0.1.18","latest"]}
\```
### ✅ Check 2: Registry Catalog
**Command**: `curl -k https://192.168.7.21:5000/v2/_catalog`
**Expected**: All service repositories present
**Result**: PASS
**Evidence**: 12 repositories found
### ❌ Check 3: Pods Running
**Command**: `kubectl get pods -n ffl`
**Expected**: All pods in Running state
**Result**: FAIL
**Issue**: ffl-backend-7d8f9c-xyz is in ImagePullBackOff
**Error Output**:
\```
NAME READY STATUS RESTARTS AGE
ffl-backend-7d8f9c-xyz 0/1 ImagePullBackOff 0 2m
\```
## Summary
**Overall Status**: ❌ FAILED (2 of 3 checks passed)
**Passing Checks**: 2
- Images successfully pushed to registry
- Registry catalog updated
**Failing Checks**: 1
- Pod deployment failed due to image pull issue
## Root Cause Analysis
The image was successfully built and pushed to registry, but Kubernetes cannot pull it. Possible causes:
1. Registry URL in HelmRelease doesn't match actual registry (192.168.7.21:5000)
2. Image tag mismatch
3. Registry secret not configured in namespace
## Recommended Remediation
1. Check HelmRelease image repository value matches registry URL
2. Verify image tag in HelmRelease matches pushed version
3. Check imagePullSecrets in namespace if registry requires auth
4. Return to infra-executor-agent to fix HelmRelease configuration
## Next Action
**BLOCK** task and return to execution phase to fix image pull configuration.
```
OR if all checks pass:
```markdown
# Verification Report: TASK-XXX
## Task: [Title]
Task Type: [build/deployment/configuration]
## Verification Checks
### ✅ All Checks Passed (X/X)
1. ✅ Images in registry
2. ✅ Pods running and healthy
3. ✅ Services accessible
4. ✅ Health checks passing
## Summary
**Overall Status**: ✅ PASSED
All verification checks completed successfully. Task execution verified and ready for git operations phase.
## Evidence
[Detailed output from verification commands]
## Next ActionFrom 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 - 0.421score
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 - 0.222score
_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
verification-agent skill. Agent Mart. https://agentmart.dev/skills/brendanbecker-verification-agent (last updated 2026-10-24)