agentdevsl/tf-consumer-implement
docker/skills-cache/tf-consumer-implement/SKILL.md
SDD Phases 3-4 for consumer provisioning. Implementation and validation from an existing consumer-design.md. Composes modules, validates, deploys to sandbox, creates PR.
$ install --global
skillsauthnpx skillsauth add agentdevsl/agentpane tf-consumer-implementInstall 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 21, 2026, 12:56 PM49.2s1 file scanned
SKILL.md
- name:
- tf-consumer-implement
- description:
- SDD Phases 3-4 for consumer provisioning. Implementation and validation from an existing consumer-design.md. Composes modules, validates, deploys to sandbox, creates PR.
- source:
- image
SDD — Consumer Implement
Builds and validates a consumer deployment from specs/{FEATURE}/consumer-design.md.
Post progress at key steps: bash .foundations/scripts/bash/post-issue-progress.sh $ISSUE_NUMBER "<step>" "<status>" "<summary>". Valid status values: started, in-progress, complete, failed.
Checkpoint after each phase: bash .foundations/scripts/bash/checkpoint-commit.sh --dir . --prefix feat "<step_name>". The <step_name> must be a short hyphenated identifier (e.g., "scaffolding", "checklist-item-b", "validation") — NOT a sentence or file path.
Prerequisites
- Resolve
$FEATUREfrom$ARGUMENTSor current git branch name. - Run
bash .foundations/scripts/bash/validate-env.sh --json. Stop ifgate_passed=false. - Verify
specs/{FEATURE}/consumer-design.mdexists via Glob. Stop if missing — tell user to run/tf-consumer-planfirst. - Find
$ISSUE_NUMBERfrom$ARGUMENTSorgh issue list --search "$FEATURE".
Phase 3: Build
- Extract checklist items from consumer-design.md Section 5 via Grep.
- For each checklist item (sequentially — items depend on prior items):
- Launch
tf-consumer-developersubagent with FEATURE path and item description. - When it completes, verify expected files exist via Glob.
- Run
terraform fmt -checkandterraform validate(validate may requireterraform initfirst). - Checkpoint commit. Use concurrent subagents for independent items only when their outputs do not overlap.
- Launch
- After all items: run
terraform validate. If failures remain, re-launchtf-consumer-developersubagents targeted at the specific errors. - Verify all checklist items in consumer-design.md Section 5 are marked
[x]via Grep. If any remain[ ], either mark them (if the work was done by a prior item) or flag the gap before proceeding.
Phase 4: Validate & Deploy
- Deploy to sandbox — trigger
terraform apply -auto-approveagainst the HCP Terraform workspace. Capture the run ID and URL. Remediate any issues until deployment succeeds. - Launch
tf-consumer-validatorwith$FEATUREpath, run ID, and workspace name. - Verify report exists via Glob. Read the quality score from it. If score < 7.0:
- Fix issues with
tf-consumer-developersubagents - Destroy sandbox, redeploy, re-launch validator (max 3 rounds)
- Fix issues with
- Checkpoint commit, push branch, create PR linking to
$ISSUE_NUMBER. - Ask user: "Destroy sandbox resources?" If yes, trigger destroy run and report status.
Done
Report at specs/{FEATURE}/reports/deployment-report.md. Output: quality score, sandbox deploy status, PR link.
Related Skills
agentdevsl/tf-security-baselines
development
VerifiedTrustedCommunity
AWS security assessment domains, risk rating framework, CIS/NIST reference baselines, and evidence-based finding format. Use when reviewing AWS security posture, assessing risk, or applying CIS/NIST baselines to Terraform configurations.
5SKILL.mdUpdated Apr 21, 2026
agentdevsl/docker/skills-cache/tf-runtask
testing
VerifiedTrustedCommunity
--- name: "tf-runtask" description: "Retrieve and display Terraform Cloud/Enterprise run task results for a given run. Use this skill whenever the user asks about run task results, run task checks, task stage statuses, or wants to inspect what run tasks reported for a Terraform Cloud/Enterprise run. Triggers on phrases like "check the run tasks", "what did the run tasks say", "show run task results", "get task results for run-xxx", or any reference to run task outcomes on a specific run." source
5SKILL.mdUpdated Apr 21, 2026
agentdevsl/tf-research
devops
VerifiedTrustedCommunity
Research strategies for AWS documentation, provider docs, and public registry patterns. Use when researching AWS services, investigating provider resources, or studying public registry modules for design patterns.
5SKILL.mdUpdated Apr 21, 2026
agentdevsl/tf-report-template
development
VerifiedTrustedCommunity
Validation results summary template for Phase 4 output. Provides the format for reporting terraform test, validate, fmt, tflint, pre-commit, trivy, and security checklist results.
5SKILL.mdUpdated Apr 21, 2026