agentdevsl/tf-module-plan
docker/skills-cache/tf-module-plan/SKILL.md
SDD Phases 1-2. Clarify requirements, research, produce design.md, and await human approval before any code is written.
$ install --global
skillsauthnpx skillsauth add agentdevsl/agentpane tf-module-planInstall 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, 12:58 PM50.8s1 file scanned
SKILL.md
- name:
- tf-module-plan
- description:
- SDD Phases 1-2. Clarify requirements, research, produce design.md, and await human approval before any code is written.
- source:
- image
- executionSkill:
- tf-module-implement
SDD — Plan
Produces specs/{FEATURE}/design.md from requirements. Stops for human approval before any code is written.
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 "<step_name>". The <step_name> must be a short hyphenated identifier (e.g., "clarify", "research-and-design", "design-approved") — NOT a sentence or file path.
Phase 1: Requirements & Research
- Run
bash .foundations/scripts/bash/validate-env.sh --json. Stop ifgate_passed=false. - Parse
$ARGUMENTSfor module name, provider, and description. Ask viaAskUserQuestionif incomplete. - Create GitHub issue: read
.foundations/templates/issue-body-template.md, fill in the placeholders with parsed requirements, and rungh issue create --title "Module: {name}" --body "$FILLED_BODY". Capture$ISSUE_NUMBER. Update the issue body again after Step 6 (clarification) to include security decisions and scope boundaries. - Create feature branch:
bash .foundations/scripts/bash/create-new-feature.sh --json --issue $ISSUE_NUMBER --short-name "<module-name>" "<feature description>". Parse the JSON output to capture$BRANCH_NAMEas$FEATUREand$DESIGN_FILE. - Scan requirements against the
tf-domain-categoryskill - Ask up to 4 clarification questions via
AskUserQuestion. Must include a security-defaults question. - Launch 3-4 concurrent
tf-module-researchsubagents for provider docs, AWS best practices, registry patterns, and edge cases. Wait for all to complete. Verify research files exist atspecs/{FEATURE}/research-*.mdvia Glob.
Phase 2: Design
- Launch
tf-module-designagent with FEATURE path and clarified requirements. The agent reads the constitution, design template, and research files fromspecs/{FEATURE}/research-*.mditself. - Verify
specs/{FEATURE}/design.mdexists via Glob. Re-launch once if missing. - Grep to confirm all 7 sections present (
## 1. Purposethrough## 7. Open Questions). Fix inline if any missing. - Present design summary to user via
AskUserQuestion: input/output counts, resource count, security controls, test scenarios, checklist items. Options: approve, review file first, request changes. - If changes requested, apply and re-present. Repeat until approved.
Done
Design approved at specs/{FEATURE}/design.md. Run /tf-module-implement $FEATURE to build.
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