dependency-conflict-resolver

dependency-conflict-resolver is a skill for Claude Code from marcusgoll/Spec-Flow. It costs 80 tokens per session (2,831 once invoked), scanned A, original, MIT.

A pre-installation check for package dependencies across JavaScript, Python, Rust, and PHP projects. Dependencies are external packages that a project needs to run or build.

In plain words
What is it for?
It helps inspect npm, Yarn, pnpm, pip, Poetry, Cargo, and Composer installs; audit packages; resolve safe conflicts; and suggest options for breaking changes.
Why use it?
It finds incompatible package versions, peer-dependency problems, and known security issues before installation. It separates safe automatic fixes from conflicts that need human review.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool.

Install

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.

agentmods
npx agentmods add skills/marcusgoll/spec-flow/dependency-conflict-resolver
Any agent
npx skills add marcusgoll/Spec-Flow --skill dependency-conflict-resolver
Clone the repo
git clone --depth 1 https://github.com/marcusgoll/Spec-Flow

Made for: Claude Code.

Wrote 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.

agentmods badge for dependency-conflict-resolver

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcusgoll/spec-flow/dependency-conflict-resolver.svg)](https://agentmods.dev/skills/marcusgoll/spec-flow/dependency-conflict-resolver)
Your own site
<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>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,831 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash db5e395311eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

.claude/skills/dependency-conflict-resolver/SKILL.md · 359 lines

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:

  1. Detect package manager: Identify ecosystem from lockfiles (package-lock.json, requirements.txt, Cargo.lock, composer.lock)
  2. Scan for conflicts: Check peer dependencies, version ranges, transitive dependencies
  3. Security audit: Run ecosystem-specific audit tools (npm audit, pip-audit, cargo-audit, composer audit)
  4. Analyze severity: Classify conflicts by risk level (safe auto-fix, manual review, blocking)
  5. 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 add
  • pip install, poetry add
  • cargo add, cargo install
  • composer 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

Read the full file on GitHub · 359 lines

Files

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.

Changes

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.

  1. 6d ago First seen · 359 lines · 80 tokens per session scan A db5e395311eb

Subscribe to this mod's changes

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.