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 sethdford/claude-skills --skill dependency-governancegit clone --depth 1 https://github.com/sethdford/claude-skillsWrote 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/sethdford/claude-skills/dependency-governance)<a href="https://agentmods.dev/skills/sethdford/claude-skills/dependency-governance"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/dependency-governance/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/sethdford/claude-skills/dependency-governance"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/dependency-governance.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 | $0.00039 | $0.00634 |
| Opus 5 | $0.00019 | $0.00317 |
| Sonnet 5 | $0.00008 | $0.00127 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
dependency-governance 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 11d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Governance
Systematically manage dependencies to reduce coupling, track vulnerabilities, and maintain security.
Context
You are governing dependencies in the system. Reduce external library reliance, manage service dependencies, deprecate old systems. Read dependency graphs, vulnerability reports, deployment constraints.
Domain Context
Based on dependency management and architectural modularity:
- Library Dependencies: Third-party code you compile into application. Vulnerability risk, maintenance burden, version conflicts.
- Service Dependencies: Other services your system calls (REST, gRPC, message queues). Coupling, availability risk, latency impact.
- Data Dependencies: Databases, caches, data lakes shared between systems. Schema coupling, migration complexity.
- Transitive Dependencies: Dependencies of your dependencies. Hard to track, security risk. Dependency hell.
Instructions
-
Map Dependency Graph: What does your system depend on? List direct dependencies (libraries, services, databases). Then transitive (dependencies of dependencies).
-
Audit for Risk: Libraries: any known vulnerabilities? Check with OWASP, CVE databases. Services: what's the SLA? What happens if it fails? Data: can you evolve schema independently?
-
Reduce Coupling: Remove unused libraries. Extract service dependencies into adapters (easier to swap). Copy small utilities instead of depending on library. Use event-driven instead of direct service calls.
-
Version Management: Update regularly; don't skip versions (harder to jump 5 versions than 1). Automate dependency updates (dependabot, renovate). Test each update in CI before merging.
-
Plan Deprecation: For dependencies you want to remove, announce timeline. Give teams 6-12 months to migrate. Finally remove or mark as deprecated. Track adoption.
Anti-Patterns
- Transitive Dependency Hell: 100 libraries installed, only use 5. Result: bloated, security risk, slow builds. Guard: Audit transitive deps; remove heavy frameworks for simple use cases.
- Version Pinning Forever: Pin to old version to avoid updates. Result: security vulnerabilities, incompatibility with new tools. Guard: Regular updates; automate testing.
- Service Coupling Without Fallback: Service A calls Service B without retry logic. Result: cascading failure. Guard: Circuit breaker, fallback, timeout; design for fault tolerance.
- No Deprecation Path: Remove dependency without warning. Result: broken builds. Guard: Announce 6+ months early; provide migration guide; track adoption.
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.
- 11d ago First seen · 47 lines · 39 tokens per session scan A 02c817922b11
dependency-governance is a skill published in the GitHub repository sethdford/claude-skills (40 stars, last pushed 6mo ago), licensed MIT. It adds 39 tokens to every session and 634 once invoked, about $0.0002 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 skills, from other repositories
videodb
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize…
lead-intelligence
AI-native lead intelligence and outreach pipeline. Replaces Apollo, Clay, and ZoomInfo with agent-powered signal scoring, mutual ranking, warm path discovery, and personalized outreach. Use when the user wants to find, qualify, and reach high-value contacts.
springboot-verification
Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
team-builder
Interactive agent picker for composing and dispatching parallel teams.
cmd_aside
Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.
seo
Audit, plan, and implement SEO improvements across technical SEO, on-page optimization, structured data, Core Web Vitals, and content strategy. Use when the user wants better search visibility, SEO remediation, schema markup, sitemap/robots work, or keyword mapping.