Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/paulthorson-policy-alignment-check
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/policy-alignment-check
What's inside
- Skill name
policy-alignment-check- Description
- Stateless skill. Checks the work against stated policy Returns findings with severity.
- License
- Apache-2.0
- Instructions
- 20 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Policy Alignment Check Checks the work against stated policy This is the shared check that any reviewer can run. ## Method 1. Read the work in full. 2. Apply the check to the work. 3. Assign severity (BLOCKER/CONCERN/NOTE) to each finding. ## Output ``` ## Findings - <finding> | Severity: BLOCKER/CONCERN/NOTE | What would clear it ``` A BLOCKER finding is a veto: only a human clears it.
From paulthorson/agentic-governance, Apache-2.0.
More from paulthorson/agentic-governance
- 0.609score
adversarial-engineer
paulthorson
Run engineering work (code, architecture, config, infrastructure) through a governed adversarial loop instead of producing it in one pass.
SkillAFreshness: A★ 4Claude Code +9 - 0.609score
framework-technical-writing
paulthorson
Use when writing or reviewing public framework git docs.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
complexity-analysis
paulthorson
Map cyclomatic, coupling, and state-space hotspots in a proposed change, without a verdict, so the Critic can check maintainability against facts.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
constraint-elicitation
paulthorson
Elicit the non-negotiable constraints on an engineering change (performance, budget, stack, ops, security) and their owners, so a fast-path can never silently…
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
ops-runbook
paulthorson
Produce deploy, rollback, monitor, and incident-runbook artifacts for an engineering change, so the Reliability Reviewer and Ops Advocate can check them.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
option-generation
paulthorson
Generate at least two distinct implementation options for an engineering problem, each with a "trades away X to get Y" sentence, without picking one.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
performance-check
paulthorson
Stateless skill.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
altitude-check
paulthorson
Re-state the engineering request at problem altitude, naming the assumed solution so it can be examined rather than taken at face value.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
doc-usability-check
paulthorson
Stateless skill.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
compliance-evidence
paulthorson
Stateless skill.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
liability-scan
paulthorson
Stateless skill.
SkillAFreshness: A★ 4Claude Code +9 - 0.603score
regulatory-gate-check
paulthorson
Stateless skill.
SkillAFreshness: A★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 2
- Open issues
- 0
- Last commit (this folder)
- Sep 29, 2026 (1 month ago)
- Last release
- Oct 15, 2026 (14 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Website
- www.agenticgovernance.app
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from paulthorson
- 0.609score
framework-technical-writing
paulthorson
Use when writing or reviewing public framework git docs.
SkillAFreshness: A★ 4Claude Code +9 - 0.609score
adversarial-engineer
paulthorson
Run engineering work (code, architecture, config, infrastructure) through a governed adversarial loop instead of producing it in one pass.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
altitude-check
paulthorson
Re-state the engineering request at problem altitude, naming the assumed solution so it can be examined rather than taken at face value.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
complexity-analysis
paulthorson
Map cyclomatic, coupling, and state-space hotspots in a proposed change, without a verdict, so the Critic can check maintainability against facts.
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
constraint-elicitation
paulthorson
Elicit the non-negotiable constraints on an engineering change (performance, budget, stack, ops, security) and their owners, so a fast-path can never silently…
SkillAFreshness: A★ 4Claude Code +9 - 0.606score
ops-runbook
paulthorson
Produce deploy, rollback, monitor, and incident-runbook artifacts for an engineering change, so the Reliability Reviewer and Ops Advocate can check them.
SkillAFreshness: A★ 4Claude Code +9
Cite this page
policy-alignment-check skill. Agent Mart. https://agentmart.dev/skills/paulthorson-policy-alignment-check (last updated 2026-10-24)