Borrowing it
Nothing to install: this file belongs to AI-agents-incubator/n8n-pilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AI-agents-incubator/n8n-pilot/main/.claude/commands/security-dialogs.mdgit clone --depth 1 https://github.com/AI-agents-incubator/n8n-pilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/ai-agents-incubator/n8n-pilot/security-dialogs)<a href="https://agentmods.dev/commands/ai-agents-incubator/n8n-pilot/security-dialogs"><img src="https://agentmods.dev/badge/commands/ai-agents-incubator/n8n-pilot/security-dialogs.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00008 | $0.02020 |
| Opus 5 | $0.00004 | $0.01010 |
| Sonnet 5 | $0.00002 | $0.00404 |
| Haiku 4.5 | $0.00001 | $0.00202 |
Grade A, and why
security-dialogs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Dialogs — Deep Credential Scan
Purpose: Use AI agent to analyze dialog files for context-dependent credentials that regex cannot detect.
When to use:
- Before creating GitHub release (paranoia mode)
- When bash cleanup found credentials and you want deeper analysis
- Manual security audit of dialog history
- Suspected credential leak in conversations
Implementation
Step 0: Check Why Agent Was Invoked
This command can be invoked in two ways:
- Manual: User types
/security-dialogs - Automatic: Triggered by
security/auto-invoke-agent.shbased on risk triggers
echo ""
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo "🔒 Security Dialogs — Deep AI Credential Scan"
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
echo ""
# Check if auto-invoked (environment variables set by auto-invoke-agent.sh)
if [ -n "$DEEP_SCAN_TRIGGER_LEVEL" ]; then
echo "🤖 Auto-invoked due to: $DEEP_SCAN_TRIGGER_LEVEL trigger level"
echo ""
echo "Trigger reasons:"
echo "$DEEP_SCAN_TRIGGER_REASONS" | grep -o '"reasons": *\[[^]]*\]' | sed 's/.*\[\(.*\)\].*/\1/' | tr ',' '\n' | sed 's/^ *"/ • /' | sed 's/"$//'
echo ""
else
echo "🔍 Manual deep scan requested by user"
echo ""
fi
Step 1: Run Regex Cleanup First
# Layer 1-3: Run standard bash cleanup (if not already run)
if [ ! -f "security/reports/"*"cleanup-report"* ] || [ -z "$CLEANUP_EXIT" ]; then
echo "Step 1: Running regex-based cleanup (fast)..."
bash security/cleanup-dialogs.sh --last
REGEX_EXIT_CODE=$?
if [ $REGEX_EXIT_CODE -eq 0 ]; then
echo "✓ Regex cleanup: No credentials detected"
else
echo "⚠️ Regex cleanup: Credentials found and redacted"
fi
else
echo "Step 1: Regex cleanup already completed"
REGEX_EXIT_CODE=$CLEANUP_EXIT
fi
echo ""
Step 2: Identify Sprint Changes to Analyze
Key principle: Analyze ONLY changes from current sprint, not entire codebase.
echo "Step 2: Identifying sprint changes for deep scan..."
echo ""
# 1. Get last dialog (current session)
LAST_DIALOG=$(find dialog -name "*.md" 2>/dev/null | sort -r | head -1)
if [ -z "$LAST_DIALOG" ]; then
echo "⚠️ No dialog files found"
exit 0
fi
DIALOG_SIZE=$(du -h "$LAST_DIALOG" | awk '{print $1}')
echo " • Dialog: $(basename $LAST_DIALOG) ($DIALOG_SIZE)"
# 2. Get git diff (changed files in sprint)
CHANGED_FILES=$(git diff --name-only HEAD~5..HEAD 2>/dev/null)
CHANGED_COUNT=$(echo "$CHANGED_FILES" | grep -v '^$' | wc -l | tr -d ' ')
if [ "$CHANGED_COUNT" -gt 0 ]; then
echo " • Changed files: $CHANGED_COUNT files in last 5 commits"
# Show file types for context
echo "$CHANGED_FILES" | grep '\.' | sed 's/.*\.//' | sort | uniq -c | while read count ext; do
echo " - $count .$ext files"
done
else
echo " • Changed files: No git changes detected"
fi
echo ""
echo "Scope: Sprint changes only (NOT entire codebase)"
echo ""
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 276 lines · 8 tokens per session scan A 3738a1e6744c
security-dialogs is a command published in the GitHub repository AI-agents-incubator/n8n-pilot (29 stars, last pushed 6mo ago), licensed MIT. It adds 8 tokens to every session and 2,020 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.