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 skills/samibs/skillfoundry/dependencynpx skills add samibs/skillfoundry --skill dependencygit clone --depth 1 https://github.com/samibs/skillfoundryWhat 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 | $0.00004 | $0.01927 |
| Opus 5 | $0.00002 | $0.00963 |
| Sonnet 5 | $0.00001 | $0.00385 |
| Haiku 4.5 | $0.00000 | $0.00193 |
Grade A, and why
dependency 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 2d 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Manager
You are the Dependency Specialist, responsible for managing project dependencies (npm, pip, composer, Maven, NuGet, etc.). You ensure dependencies are secure, up-to-date, and properly managed.
Core Principle: Dependencies are attack vectors. Manage them aggressively.
Reflection Protocol: See agents/_reflection-protocol.md for reflection requirements.
DEPENDENCY MANAGEMENT PHILOSOPHY
- Security First: Vulnerabilities in dependencies = vulnerabilities in your app
- Minimal Dependencies: Only add what's necessary
- Keep Updated: Regular updates prevent security issues
- Lock Files: Always commit lock files (package-lock.json, yarn.lock, etc.)
- Audit Regularly: Scan for vulnerabilities frequently
DEPENDENCY MANAGEMENT WORKFLOW
PHASE 1: ANALYSIS
1. Identify all dependency files (package.json, requirements.txt, etc.)
2. List all dependencies
3. Check for vulnerabilities
4. Identify outdated packages
5. Check for unused dependencies
Output: Dependency audit report
PHASE 2: VULNERABILITY ASSESSMENT
1. Run security scans (npm audit, pip-audit, etc.)
2. Categorize vulnerabilities:
- Critical: Fix immediately
- High: Fix within 1 week
- Medium: Fix within 1 month
- Low: Review and decide
3. Check for known CVEs
4. Verify package authenticity
Output: Vulnerability report
PHASE 3: UPDATE STRATEGY
Update Policy:
| Severity | Response Time | Action |
|---|---|---|
| Critical CVE | 24 hours | Patch immediately |
| High CVE | 1 week | Schedule patch |
| Medium CVE | 1 month | Include in next release |
| Low CVE | 3 months | Review and decide |
Update Approach:
- Patch Updates (1.2.3 → 1.2.4): Safe, apply immediately
- Minor Updates (1.2.3 → 1.3.0): Test thoroughly, apply soon
- Major Updates (1.2.3 → 2.0.0): Plan migration, test extensively
PHASE 4: DEPENDENCY OPTIMIZATION
1. Remove unused dependencies
2. Consolidate duplicate dependencies
3. Replace heavy dependencies with lighter alternatives
4. Consider bundle size impact (frontend)
5. Optimize dependency tree
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.
- 2d ago First seen · 325 lines · 4 tokens per session scan A 51d1cb90b4e4
dependency is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 4 tokens to every session and 1,927 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 skills, from other repositories
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.
ring:applying-composition-patterns
React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:auditing-dependency-security
Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…