Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflowWrote 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/bybren-llc/safe-agentic-workflow/audit-deps)<a href="https://agentmods.dev/commands/bybren-llc/safe-agentic-workflow/audit-deps"><img src="https://agentmods.dev/badge/commands/bybren-llc/safe-agentic-workflow/audit-deps.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 | $0.00004 | $0.00872 |
| Opus 5 | $0.00002 | $0.00436 |
| Sonnet 5 | $0.00001 | $0.00174 |
| Haiku 4.5 | $0.00000 | $0.00087 |
Grade A, and why
audit-deps 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 8d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- audit-deps — 95% identical, 6 lines differ
- audit-deps — 91% identical, 14 lines differ
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
📋 TEMPLATE: This command is a template. See "Customization Guide" below to adapt for your infrastructure.
Execute dependency audit to identify optimization opportunities and security issues.
Audit Workflow
1. Security Audit
Check for vulnerabilities:
yarn audit
Report:
- Critical/High severity issues
- Packages with known vulnerabilities
- Recommended upgrades
2. Bundle Analysis
Run bundle analyzer:
ANALYZE=true yarn build
Identify:
- Largest packages
- Duplicate dependencies
- Unused code opportunities
3. Unused Dependencies
Run depcheck:
npx depcheck
Find:
- Unused dependencies (can remove)
- Missing dependencies (should add)
- Dependencies only in devDependencies
4. Outdated Packages
Check for updates:
yarn outdated
Report:
- Packages with newer versions
- Major vs minor vs patch updates
- Breaking change risks
5. Specific Checks
Icon Libraries (common bloat):
find . -name "*.tsx" -o -name "*.ts" | xargs grep -h "from.*icons" | sort -u
Analyze:
- Which icon libraries used
- Usage patterns
- Consolidation opportunities
Large Packages:
du -sh node_modules/* | sort -hr | head -20
Identify:
- Top 20 largest packages
- Unnecessary large dependencies
6. Create Audit Report
Document findings in docs/agent-outputs/technical-docs/dependency-audit-report-{date}.md:
# Dependency Audit Report
**Date**: {current-date}
**Scope**: Full dependency audit
**Tools**: yarn audit, depcheck, bundle-analyzer
## Executive Summary
- Total packages: {count}
- Security issues: {count} ({severity})
- Optimization potential: {size} MB
- Quick wins: {count} tickets
## Findings
### 1. Security Issues
- List critical/high issues
- Recommended actions
### 2. Bundle Size Optimization
- Current size: {size}
- Bloat identified: {list}
- Savings potential: {size}
### 3. Unused Dependencies
- Runtime: {list}
- DevDependencies: {list}
- Action: Can remove
### 4. Missing Dependencies
- {list}
- Action: Should add
### 5. Outdated Packages
- Major updates: {list}
- Minor updates: {list}
- Patch updates: {list}
## Recommendations
### Immediate Actions (High Priority)
1. {action}
2. {action}
### Short-term (Medium Priority)
1. {action}
2. {action}
### Long-term (Low Priority)
1. {action}
2. {action}
## Implementation Tickets
Create Linear tickets for each actionable item:
- {{TICKET_PREFIX}}-{number}: {description}
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.
- 8d ago First seen · 206 lines · 4 tokens per session scan A 9f366acf7c91
audit-deps is a command published in the GitHub repository bybren-llc/safe-agentic-workflow (406 stars, last pushed 1mo ago), licensed MIT. It adds 4 tokens to every session and 872 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 2026-08-30.
Other commands, from other repositories
help
Category: System Syntax: /help [command|topic].
translate-docs
A command that translates project documentation into a requested language while preserving its technical meaning and formatting. It is intended for documents such as Markdown files and other project materials.
review-tasks
A command that reviews a task list for fidelity to its source plans, practical executability, dependencies, and ways to verify completion. It can use project requirements, specifications, designs, plans, and repository files.
tasks-to-issues
A command that turns an existing task list into actionable GitHub Issues. GitHub Issues are work items used to track bugs, changes, and development tasks.
clarify
Reduce spec ambiguity via targeted questions with adaptive auto-invocation (planning is 80% of success).
ultrathink
Enter deep craftsman mode - question everything, plan like Da Vinci, craft insanely great solutions, then materialize to roadmap.