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 skills add sawrus/agent-guides --skill dependency-auditgit clone --depth 1 https://github.com/sawrus/agent-guidesWrote 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/skills/sawrus/agent-guides/dependency-audit)<a href="https://agentmods.dev/skills/sawrus/agent-guides/dependency-audit"><img src="https://agentmods.dev/badge/skills/sawrus/agent-guides/dependency-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sawrus/agent-guides/dependency-audit"><img src="https://agentmods.dev/badge/skills/sawrus/agent-guides/dependency-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00375 |
| Opus 5 | $0.00000 | $0.00187 |
| Sonnet 5 | $0.00000 | $0.00075 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
dependency-audit 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 7d 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.
What it actually says
Skill: Dependency Audit
When to load
When adding/updating dependencies, handling security findings, preparing releases, or reviewing supply-chain risk in PRs.
Objective
Produce a dependency risk decision based on exploitability and business impact, not scanner output alone.
Audit Workflow
-
Inventory
- Identify direct and transitive dependencies changed in PR/release.
- Record package source (registry), maintainer trust indicators, and version deltas.
-
Scan
- Run ecosystem-native audit tools + repository policy checks.
- Capture High/Critical findings with package path and affected components.
-
Exploitability Triage
- Determine runtime reachability (is vulnerable code path invoked?).
- Evaluate exposure (public endpoint, privileged process, internal-only).
- Assess mitigations (WAF, sandbox, feature flags, auth boundaries).
-
Classify each finding
exploitable-now→ block release, fix immediately.not-reachable→ document evidence and add VEX status.accepted-risk→ temporary exception with owner + expiry.
-
Remediation Plan
- Prefer upgrade to patched version.
- If upgrade is breaking: isolate vulnerability, add compensating controls, schedule upgrade milestone.
Supply-Chain Red Flags
- Maintainer transfer shortly before suspicious release.
- Sudden dependency graph expansion unrelated to package purpose.
- install/postinstall scripts performing unexpected network activity.
- Obfuscated source in runtime package.
- Package source not in approved registries.
Output Template (required)
- Dependency name and version delta
- Severity and advisory source
- Reachability evidence
- Classification (
exploitable-now/not-reachable/accepted-risk) - Decision and next action
- Owner and deadline
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.
- 7d ago First seen · 51 lines · 0 tokens per session scan A 5832f76c091f
dependency-audit is a skill published in the GitHub repository sawrus/agent-guides (17 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 375 tokens. 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 2026-09-03.
Other skills, from other repositories
architecture-decision-records
Comprehensive patterns for creating, maintaining, and managing Architecture Decision Records (ADRs) that capture the context and rationale behind significant technical decisions.
agent-orchestration-improve-agent
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
agentmail
Email infrastructure for AI agents. Create accounts, send/receive emails, manage webhooks, and check karma balance via the AgentMail API.
aws-cdk-development
AWS Cloud Development Kit (CDK) expert for building cloud infrastructure with TypeScript/Python.
aws-cost-cleanup
Automated cleanup of unused AWS resources to reduce costs.
azd-deployment
Deploy containerized frontend + backend applications to Azure Container Apps with remote builds, managed identity, and idempotent infrastructure.