arn-assessing
This skill should be used when the user says "assessing", "arness assessing", "assess", "assess codebase", "technical review", "codebase assessment", "find…
This skill should be used when the user says "review infra change", "infrastructure review", "review infrastructure", "infra quality review", "arn infra review", "check infra change", "review infrastructure change", "infra change review", "quality check infrastructure",
$ npx -y skills add AppsVortex/arness --skill arn-infra-review-change --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/arn-infra-review-changeContext preview
The summary Claude sees to decide when to auto-load this skill.
This skill should be used when the user says "review infra change", "infrastructure review", "review infrastructure", "infra quality review", "arn infra review", "check infra change", "review infrastructure change", "infra change review", "quality check infrastructure",
name: arn-infra-review-change description: >- This skill should be used when the user says "review infra change", "infrastructure review", "review infrastructure", "infra quality review", "arn infra review", "check infra change", "review infrastructure change", "infra change review", "quality check infrastructure", "arn-infra-review-change", "post-deployment review", or wants to perform a comprehensive post-execution quality review of completed infrastructure changes, producing a structured review report with a PASS/WARN/NEEDS_FIXES verdict. version: 1.0.0
Perform a comprehensive post-execution quality review of completed infrastructure changes. This skill reads all phase execution reports, the original spec, and the source plan, then invokes the `arn-infra-change-reviewer` agent to evaluate 7 quality categories and produce a structured review report with an overall verdict.
This is the quality gate between execution and documentation. A PASS or WARN verdict enables documentation generation. A NEEDS_FIXES verdict identifies specific remediation actions and suggests re-executing affected phases.
Read `## Arness` from the project's CLAUDE.md. If no `## Arness` section exists or Arness Infra fields are missing, inform the user: "Arness Infra is not configured for this project yet. Run `/arn-infra-wizard` to get started — it will set everything up automatically." Do not proceed without it.
Check the **Deferred** field. If `Deferred: yes`, inform the user: "Infrastructure is in deferred mode. Change review is not available until infrastructure is fully configured. Run `/arn-infra-assess` to un-defer." Stop.
Extract:
Search for completed or in-progress change projects:
Glob <infra-plans-dir>/*/PROGRESS_TRACKER.json
For each project found, read the PROGRESS_TRACKER.json and filter to projects where at least one phase has `execution.status === "completed"`.
**If one eligible project found:** Auto-select it. **If multiple eligible projects found:** Present the list with project names, phase completion status, and overall status. Ask the user to select. **If no eligible project found:** Inform the user: "No completed change projects found. Run `/arn-infra-execute-change` to execute a change plan first."
---
Read all artifacts from the selected project:
1. **Phase reports:** Read all `INFRA_CHANGE_REPORT_PHASE_N.json` files from the project's `reports/` directory:
Glob <project-dir>/reports/INFRA_CHANGE_REPORT_PHASE_*.json
2. **Change spec:** Locate and read the original change spec:
3. **Source plan:** Read `<project-dir>/SOURCE_PLAN.md`
4. **INTRODUCTION.md:** Read `<project-dir>/INTRODUCTION.md` for cost budget and security requirements
**If any phase reports are missing (some phases not executed):** Warn: "Phase [N] has not been executed yet. The review will cover completed phases only. Consider running `/arn-infra-execute-change` to complete all phases before reviewing."
Present a review scope summary: "**Review scope:**
Ask (using `AskUserQuestion`):
**"Proceed with review?"**
Options: 1. **Yes** -- Start the quality review 2. **No** -- Cancel
---
Invoke the `arn-infra-change-reviewer` agent via the Task tool, passing the model from `.arness/agent-models/infra.md` as the `model` parameter (see `plugins/arn-infra/skills/arn-infra-ensure-config/references/ensure-config.md` "Dispatch convention" for fallback). Structured context:
--- PHASE REPORTS --- Phase 1 Report: [full JSON content of INFRA_CHANGE_REPORT_PHASE_1.json] Phase 2 Report: [full JSON content of INFRA_CHANGE_REPORT_PHASE_2.json] ... --- END PHASE REPORTS --- --- CHANGE SPEC --- [full content of the INFRA_CHANGE_*.md specification] --- END CHANGE SPEC --- --- CHANGE PLAN --- [full content of SOURCE_PLAN.md] --- END CHANGE PLAN --- --- PROVIDER CONFIG --- Providers: [from ## Arness] Environments: [from ## Arness] Cost threshold: [from ## Arness] --- END PROVIDER CONFIG --- --- REVIEW INSTRUCTIONS --- Perform a comprehensive review across all 7 categories: 1. Security posture delta (before vs after -- any regressions?) 2. Cost compliance (estimated vs actual vs threshold) 3. Blast radius compliance (planned vs actual impact) 4. Rollback documentation (complete and actionable?) 5. Environment parity (consistent where expected?) 6. State consistency (clean state, no orphaned resources?) 7. Resource tagging (compliant with policy?) Produce a structured review report with: - Per-category evaluation with findings - Per-finding entries with severity, description, resource, and suggestion - Overall verdict: pass / warn / needs-fixes - Recommendation and suggested next step Focus on cross-phase cons
Arness — H not required. Structured AI workflows for Claude Code. From first idea to production deploy. Seven entry commands. That's all you need to remember.
This skill should be used when the user says "assessing", "arness assessing", "assess", "assess codebase", "technical review", "codebase assessment", "find…
This skill should be used when the user says "arness code assess", "arn-code-assess", "assess codebase", "technical review", "codebase assessment", "find…
This skill should be used when the user says "fix CVEs", "patch vulnerabilities", "apply security patches", "resolve security advisories", "batch CVE fix",…
This skill should be used when the user says "scan for CVEs", "CVE scan", "check for vulnerabilities", "find vulnerabilities", "check security advisories",…
This skill should be used when the user says "batch implement", "implement all", "batch execution", "implement all features", "parallel implement", "implement…
This skill should be used when the user says "batch merge", "merge batch", "arness batch merge", "arn-code-batch-merge", "merge all PRs", "merge batch PRs",…