GS

gsd-secure-phase

Audits and verifies security mitigations for a completed development phase.

Install

mkdir -p .claude/skills/gsd-secure-phase && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/19256" && unzip -o skill.zip -d .claude/skills/gsd-secure-phase && rm skill.zip

Installs to .claude/skills/gsd-secure-phase

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Retroactively verify threat mitigations for a completed phase
61 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Verify threat mitigations for a completed phase
  • Audit existing SECURITY.md for mitigation verification
  • Run verification from PLAN.md if SECURITY.md is absent
  • Output an updated SECURITY.md file
  • Preserve all workflow gates during execution

How it works

It verifies threat mitigations for a completed phase by auditing existing security documentation or running from a threat model. This process updates the SECURITY.md file.

Inputs & outputs

You give it
Completed phase (optional, defaults to last completed phase)
You get back
Updated SECURITY.md file with verified threat mitigations

When to use gsd-secure-phase

  • Security auditing
  • Post-phase threat verification
  • Updating security documentation

About this skill

<objective> Verify threat mitigations for a completed phase. Three states: - (A) SECURITY.md exists — audit and verify mitigations - (B) No SECURITY.md, PLAN.md with threat model exists — run from artifacts - (C) Phase not executed — exit with guidance

Output: updated SECURITY.md. </objective>

<execution_context> @.agent/get-shit-done/workflows/secure-phase.md </execution_context>

<context> Phase: $ARGUMENTS — optional, defaults to last completed phase. </context> <process> Execute @.agent/get-shit-done/workflows/secure-phase.md. Preserve all workflow gates. </process>

When not to use it

  • When there is no existing security documentation or threat model
  • When the goal is to create a new threat model rather than verify mitigations

Limitations

  • Exits with guidance if the phase is not executed
  • Requires existing security documentation (SECURITY.md) or a threat model (PLAN.md)
  • Output is limited to updated SECURITY.md

How it compares

This skill specifically focuses on retroactive verification of threat mitigations against completed work, which is distinct from initial threat modeling or proactive security design.

Compared to similar skills

gsd-secure-phase side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
gsd-secure-phase (this skill)02moNo flagsIntermediate
secrets-management53moReviewAdvanced
security-scanning-security-hardening33moNo flagsAdvanced
sast-configuration32moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry