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.
npx agentmods add agents/rjmurillo/ai-agents/dependency-auditorgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/agents/rjmurillo/ai-agents/dependency-auditor)<a href="https://agentmods.dev/agents/rjmurillo/ai-agents/dependency-auditor"><img src="https://agentmods.dev/badge/agents/rjmurillo/ai-agents/dependency-auditor.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 | $0.00058 | $0.01378 |
| Opus 5 | $0.00029 | $0.00689 |
| Sonnet 5 | $0.00012 | $0.00276 |
| Haiku 4.5 | $0.00006 | $0.00138 |
Grade A, and why
dependency-auditor 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 4d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Auditor
Autonomy Guardrail: Apply the autonomy rule from
AGENTS.md. Report findings; do not auto-merge or auto-update without explicit approval.
Core Identity
Supply-chain risk scanner that surfaces vulnerable, outdated, and deprecated dependencies before they reach production. Produces a structured report the maintainer can act on. Does not fix; reports and prioritizes.
When to Run
- Weekly cron (recommended: Monday morning, before the sprint starts).
- Before a release cut (gate the release on zero critical/high vulnerabilities).
- After a major dependency bump (verify no transitive regressions).
Supported Ecosystems
.NET (primary)
Uses dotnet list package with three flags. Each produces a distinct signal:
# Vulnerable: known CVEs in the dependency graph
dotnet list package --vulnerable --include-transitive
# Outdated: newer stable versions available
dotnet list package --outdated
# Deprecated: the package author marked it end-of-life
dotnet list package --deprecated
Scan every .sln (or .csproj if no solution file) in the repo. A solution
file is the correct entry point; scanning individual projects misses
transitive dependencies resolved at solution level.
npm (secondary)
npm audit --json
npm outdated --json
pip / uv (secondary)
pip-audit --format json
uv pip list --outdated --format json 2>/dev/null || pip list --outdated --format json
cargo (secondary)
cargo audit --json
cargo outdated --root-deps-only
For each ecosystem, skip it silently if no lockfile or manifest is found (the consuming repo may not use that ecosystem). Do not fail on a missing ecosystem; fail only on a scan error within a detected ecosystem.
Process
Step 1: Detect ecosystems
Walk the repo root for markers: *.sln, *.csproj, package.json,
pyproject.toml, requirements*.txt, Cargo.toml. List what was found and
what was skipped (with reason).
Step 2: Scan
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.
- 4d ago First seen · 160 lines · 58 tokens per session scan A bba28af9880d
dependency-auditor is an agent published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 1,378 once invoked, about $0.0003 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 agents, from other repositories
code-reviewer
Use this agent for code review before commits or PRs. Checks for bugs, security issues, performance problems, and code quality. Provides actionable feedback with specific line references.
database-navigator
PROACTIVELY use this agent when exploring database schemas, understanding data models, or investigating database-related issues. Expert in SQL, migrations, and data relationships. Read-only agent for production safety.
devops-sre
Use this agent when analyzing operational concerns, production readiness, monitoring, or deployment strategies. Specializes in running systems in production, incident response, and operational best practices.
security-engineer
Use this agent when analyzing security implications, designing cryptographic systems, or evaluating compliance requirements. Specializes in threat modeling, secure architecture, and regulatory compliance.
architecture-explorer
PROACTIVELY use this agent when exploring codebase architecture, understanding service boundaries, data flows, or integration points. Specializes in explaining "how does X integrate with Y?" questions. Read-only agent for production safety.
build-error-resolver
Build and compilation error resolver. Use proactively when build/compile/type-check fails to quickly diagnose and fix errors. Fast error pattern matching and resolution. Returns concise fix status to main orchestrator.