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/marcusgoll/spec-flow/dependency-conflict-resolvernpx skills add marcusgoll/Spec-Flow --skill dependency-conflict-resolvergit clone --depth 1 https://github.com/marcusgoll/Spec-FlowWrote 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/marcusgoll/spec-flow/dependency-conflict-resolver)<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/dependency-conflict-resolver"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/dependency-conflict-resolver.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 | $0.00080 | $0.02831 |
| Opus 5 | $0.00040 | $0.01416 |
| Sonnet 5 | $0.00016 | $0.00566 |
| Haiku 4.5 | $0.00008 | $0.00283 |
Grade A, and why
dependency-conflict-resolver 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 6d 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 — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<quick_start> Pre-installation check workflow:
- Detect package manager: Identify ecosystem from lockfiles (package-lock.json, requirements.txt, Cargo.lock, composer.lock)
- Scan for conflicts: Check peer dependencies, version ranges, transitive dependencies
- Security audit: Run ecosystem-specific audit tools (npm audit, pip-audit, cargo-audit, composer audit)
- Analyze severity: Classify conflicts by risk level (safe auto-fix, manual review, blocking)
- Present resolution: Auto-apply safe fixes, suggest alternatives for breaking changes, block critical vulnerabilities with alternatives
<trigger_detection> Auto-invoke when detecting these commands:
npm install,npm i,yarn add,pnpm addpip install,poetry addcargo add,cargo installcomposer require,composer install</trigger_detection>
<quick_example>
# User attempts: npm install [email protected]
# Skill detects: Peer dependency conflict with [email protected]
[CONFLICT DETECTED]
Package: [email protected]
Conflict: [email protected] requires react ^17.0.0
Risk: MEDIUM (breaking change)
[RECOMMENDED ACTION]
Option 1: Upgrade react-dom to ^18.0.0 (recommended)
npm install [email protected] [email protected]
Option 2: Downgrade react to ^17.0.0
npm install [email protected]
[SECURITY CHECK]
✓ No known vulnerabilities in [email protected]
✓ No known vulnerabilities in [email protected]
</quick_example> </quick_start>
Scan current directory for lockfiles and package manifests:
- JavaScript: package.json + (package-lock.json | yarn.lock | pnpm-lock.yaml)
- Python: requirements.txt | Pipfile | pyproject.toml + (Pipfile.lock | poetry.lock)
- Rust: Cargo.toml + Cargo.lock
- PHP: composer.json + composer.lock
Extract:
- Current dependency versions (from lockfile)
- Requested package and version (from user command)
- Version constraints (from manifest) </detection_phase>
<conflict_analysis> 2. Analyze Dependency Conflicts
Check for conflicts in order of severity:
A. Peer Dependency Conflicts
- Compare requested version against peer dependency requirements
- Identify which packages will be incompatible
- Calculate semver compatibility ranges
B. Transitive Dependency Conflicts
- Build dependency graph of all transitive dependencies
- Detect duplicate packages with incompatible versions
- Identify shared dependencies requiring specific versions
C. Version Constraint Violations
- Validate against existing version constraints in manifest
- Check for semver range compatibility (^, ~, >=, etc.)
- Detect locked versions that prevent resolution
D. Platform/Runtime Conflicts
- Check Node.js, Python, PHP version requirements
- Validate feature flags (Rust features)
- Check platform-specific dependencies </conflict_analysis>
<security_audit> 3. Security Vulnerability Scan
Run ecosystem-specific security audits:
JavaScript (npm/yarn/pnpm):
npm audit --json
# Parse output for HIGH/CRITICAL vulnerabilities
# Check: GHSA IDs, CVE numbers, severity scores
Python (pip/poetry):
pip-audit --format json
# Or: poetry audit --json
# Parse PyPA Advisory Database results
Rust (cargo):
cargo audit --json
# Check RustSec Advisory Database
# Identify RUSTSEC-YYYY-NNNN advisories
PHP (composer):
composer audit --format json
# Parse security advisories
# Check for blocked insecure packages
For each vulnerability found:
- Extract severity (LOW, MODERATE, HIGH, CRITICAL)
- Identify patched versions
- Find alternative packages if no patch available
- Assess exploitability and context </security_audit>
<resolution_strategy> 4. Classify Conflicts and Generate Resolutions
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 359 lines · 80 tokens per session scan A db5e395311eb
dependency-conflict-resolver is a skill published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It adds 80 tokens to every session and 2,831 once invoked, about $0.0004 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
accesslint-audit
Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written report, no edits) and fix (audit→edit→verify loop on a target). Prefers direct-CDP live-DOM auditing; falls back to a browser-MCP composition or HTML-string audits.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
agent-qa-debug-fix
Debug, patch, and verify failed Agent QA runs from MCP evidence, artifacts, logs, and local code without hiding product or infrastructure defects.
agent-qa-result-triage
Triage failed Agent QA runs with MCP evidence, artifacts, logs, fixed failure categories, confidence, and actionable next steps.
accesslint-scan
Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.
application-performance-performance-optimization
Optimize end-to-end application performance with profiling, observability, and backend/frontend tuning. Use when coordinating performance optimization across the stack.