How do I install the Phase 7 5 Code Validation skill?

Run npx skillmds@latest add awslabs/phase-7-5-code-validation in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Phase 7 5 Code Validation safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Phase 7 5 Code Validation?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Phase 7 5 Code Validation free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Phase 7 5 Code Validation?

awslabs (@awslabs) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Phase 7 5 Code Validation by awslabs

Name: Phase 7 5 Code Validation
Author: awslabs

File contents

Phase 7.5: Code Validation Analysis

Objective

Inspect the implementation and record evidence for every current threat and mitigation. This phase runs only when source code is detected in the project recorded with manage_workflow(action="set_project").

Tool

manage_code_validation(action, values=None)

Action	Purpose
`describe`	Show the finding payload and accepted outcomes
`record`	Atomically store findings and update canonical statuses
`get`	Show current findings, missing IDs, and stale records
`validate`	Check that every current threat and mitigation has fresh evidence
`report`	Render the evidence-based report and finalize the current snapshot
`clear`	Remove findings before starting a new validation

record accepts values.threat_findings and values.mitigation_findings. Each finding requires its record ID, an outcome, and at least one non-empty evidence string. recommendation is optional.

Threat outcomes:

fully_mitigated
partially_mitigated
not_mitigated
not_applicable

Mitigation outcomes:

implemented
partially_implemented
not_implemented
not_applicable

Workflow

Call manage_workflow(action="guidance", phase="7.5").
Call manage_code_validation(action="describe").
Inspect the relevant files and identify concrete file, line, configuration, or test evidence.
Call manage_code_validation(action="record", values=FINDINGS). Findings may be submitted incrementally.
Call manage_code_validation(action="validate"); record every missing or stale item.
Call manage_code_validation(action="report") to finalize the current snapshot.
Call manage_workflow(action="advance") to proceed to Phase 8.

Observed code behavior belongs in finding evidence. Use manage_assumptions(action="add", values=ASSUMPTION) only when a statement remains unverified.

Completion Criteria

Every current threat has a fresh finding
Every current mitigation has a fresh finding
Each finding contains concrete evidence or a not-applicable rationale
Validation reports complete coverage
The final report has been generated for the current snapshot
manage_workflow(action="advance") proceeds to Phase 8

---name: phase-7-5-code-validationdescription: Phase 7.5 Code Validation guide. Use when validating threats and mitigations against actual code or reviewing implementation evidence.---# Phase 7.5: Code Validation Analysis## ObjectiveInspect the implementation and record evidence for every current threat and mitigation. This phase runs only when source code is detected in the project recorded with `manage_workflow(action="set_project")`.## Tool### manage_code_validation(action, values=None)| Action | Purpose ||---|---|| `describe` | Show the finding payload and accepted outcomes || `record` | Atomically store findings and update canonical statuses || `get` | Show current findings, missing IDs, and stale records || `validate` | Check that every current threat and mitigation has fresh evidence || `report` | Render the evidence-based report and finalize the current snapshot || `clear` | Remove findings before starting a new validation |`record` accepts `values.threat_findings` and `values.mitigation_findings`. Each finding requires its record ID, an outcome, and at least one non-empty evidence string. `recommendation` is optional.Threat outcomes:- `fully_mitigated`- `partially_mitigated`- `not_mitigated`- `not_applicable`Mitigation outcomes:- `implemented`- `partially_implemented`- `not_implemented`- `not_applicable`## Workflow1. Call `manage_workflow(action="guidance", phase="7.5")`.2. Call `manage_code_validation(action="describe")`.3. Inspect the relevant files and identify concrete file, line, configuration, or test evidence.4. Call `manage_code_validation(action="record", values=FINDINGS)`. Findings may be submitted incrementally.5. Call `manage_code_validation(action="validate")`; record every missing or stale item.6. Call `manage_code_validation(action="report")` to finalize the current snapshot.7. Call `manage_workflow(action="advance")` to proceed to Phase 8.Observed code behavior belongs in finding evidence. Use`manage_assumptions(action="add", values=ASSUMPTION)` only when a statementremains unverified.## Completion Criteria- [ ] Every current threat has a fresh finding- [ ] Every current mitigation has a fresh finding- [ ] Each finding contains concrete evidence or a not-applicable rationale- [ ] Validation reports complete coverage- [ ] The final report has been generated for the current snapshot- [ ] `manage_workflow(action="advance")` proceeds to Phase 8

Frequently asked questions

Phase 7 5 Code Validation