agt-check
01microsoft/agent-governance-toolkit
Command
Check text against AGT prompt-injection, context-poisoning, and MCP threat detectors.
113 tagged governance, measured the same way as everything else here.
Browse within: scaffolding 42github 41arckit 25enterprise-architecture 25compliance 11ai-security 9appsec 9devsecops 9iac 9agent-evaluation 7multi-agent-systems 7python 7agent-coordination 6Constitutional AI 5
microsoft/agent-governance-toolkit
Command
Check text against AGT prompt-injection, context-poisoning, and MCP threat detectors.
microsoft/agent-governance-toolkit
Command
Show the active AGT governance status for this Claude Code session.
starmynd-org/infinite-brain-os
Command Claude Code
Slash command that creates a new namespace file under system/namespaces/ in the personal repo, with lifecyclestate: scratch.
Command
You are in AUDIT MODE. Perform a constitutional compliance scan.
Command
You are being initialized as the arifOS Forge Agent on the VPS (srv1325122).
Command
Report the current state of the VPS and arifOS project.
Command Claude Code
Run the full OpsML test suite (Rust + Python) before submitting a PR. Capture and report all errors clearly at each step. Stop a workflow only if a step produces errors that would block the next step from running correctly.
Command
When analyzing large codebases or multiple files that might exceed context limits, use the Gemini CLI with its massive context window. Use gemini -p to leverage Google Gemini's large context capacity.
Command
Audit software engineering practices in a repository — check ADR health, GitHub config, CODEOWNERS coherence, project ways alignment, and documentation state. Use when verifying a project is still up to standards.
Command
Score way matching, analyze vocabulary, and validate frontmatter.
Command Claude Code
Audit a code path, crate, or flow for trust boundary violations, regulatory terminology, and economic invariant risks.
Command Claude Code
Reconcile durable project truth after work by updating the actual domain owner, not a universal state document.
Command Claude Code
Trace a feature or concept across crates, routes, tests, and docs — produce a full cross-cutting map.
Command
Create a strategy-compliant git branch. Same flow as the natural-language new-branch skill — dispatches here when users prefer explicit slash commands. Accepts positional args for purpose + slug so /nyann:branch feature login works directly without the skill having to parse phrasing.
Command
Run nyann's read-only hygiene + documentation audit on the current repo. Emits the same drift sections retrofit uses, but never offers remediation or writes to the filesystem. Use this on session start, in CI, or any time you want to sanity-check a repo without risking mutations.
Command
Audit an existing repo against a profile and fix what's drifted. Unlike doctor (read-only), retrofit detects missing hooks, misconfigured gitignore, documentation gaps, and non-compliant history, then offers to remediate via bootstrap. Idempotent — safe to re-run.
Command
Assess the repository against SicarioSpec guardrails.
Command
Generate or update docs/compliance/control-applicability.md.
Command
Run deterministic verification.
Command
Perform comprehensive governance quality analysis across architecture artifacts (requirements, principles, designs, assessments).
Command
Generate prioritised product backlog from ArcKit artifacts - convert requirements to user stories, organise into sprints.
Command
Generate architecture diagrams using Mermaid or PlantUML C4 for visual documentation.
Command
Manual UNITARES governance check-in for the current turn.
Command
Close out a UNITARES workspace before final response.