ai safety commands

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.

Hmbown/Hegelion

Command Claude Code

Command "hegelion" from Hmbown/Hegelion, covering /hegelion, routing and autocoding loop.

assafkip/research-mode

Command

Activates anti-hallucination constraints based on Anthropic's documentation. Stay in this mode until the user says to exit.

FlyFission/nuclear-grade-context-engineering

Command

Portable command prompt generated from skills/breaking-down-the-work/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.

FlyFission/nuclear-grade-context-engineering

Command

Portable command prompt generated from skills/rating-change-risk/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.

FlyFission/nuclear-grade-context-engineering

Command

Portable command prompt generated from skills/organizing-project-folders/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.

frmoretto/hardstop

Command

Hardstop - Pre-execution safety layer for shell commands. Shows status and help.

frmoretto/hardstop

Command

Show Hardstop audit log entries.

frmoretto/hardstop

Command

Disable Hardstop protection temporarily.

logi-cmd/agent-guardrails

Command

Run guardrail check on recent changes.

logi-cmd/agent-guardrails

Command

Plan a task with scope contract and confidence check.

logi-cmd/agent-guardrails

Command

Review changes before merge with risk analysis.

IgorGanapolsky/ThumbGate

Command Claude Code

Show what ThumbGate has actually blocked — gate enforcement stats and the full enforcement matrix. Use for "what has ThumbGate blocked", "show gate stats", "is enforcement working", "how many tokens did we save", "enforcement matrix".

IgorGanapolsky/ThumbGate

Command Claude Code

Turn the last agent mistake into a hard prevention rule the agent cannot bypass. Use after a bad tool call, a wrong action, or a thumbs-down — "guard against this", "block this from happening again", "never do that again", "promote this to a rule".

IgorGanapolsky/ThumbGate

Command Claude Code

Show this repo's branch/release governance and grant a scoped, time-limited approval for an action that touches protected files. Use for "protect this branch", "is main protected", "approve this protected change", "branch governance", "let me edit a protected file".

Hulupeep/Specflow

Command Claude Code

Audit a README's reading flow by treating it as a conversion funnel. Every section is evaluated against a target reader and a terminal action. Produces a structured audit blueprint that feeds directly into /readme-restructure.

Hulupeep/Specflow

Command Claude Code

Execute a /readme-audit blueprint. Rewrites the README to the evaluator → conversion → links structure and creates linked docs by extracting and reorganising existing content.

agentkitai/agentlens

Command Claude Code

You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.

agentkitai/agentlens

Command Claude Code

Create a comprehensive PRD (Product Requirements Document) through structured workflow facilitation.

agentkitai/agentlens

Command Claude Code

Create comprehensive product briefs through collaborative step-by-step discovery as creative Business Analyst working with the user as peers.

airblackbox/airblackbox

Command

Discover runtime AI components and static AI dependencies with AIR Blackbox.

airblackbox/airblackbox

Command

Export a signed compliance evidence package as JSON or PDF for regulatory handoff.

airblackbox/airblackbox

Command

Replay recorded AI traces to detect behavioral drift between model versions.