plugins/dev-utils/skills/context-bundler/SKILL.md
Interactively creates targeted code, design, and documentation bundles for external review (Markdown or ZIP). Includes a comprehensive library of review & delegation persona templates (Adversarial Security, Plan Critique, Refactoring Quality, Sub-Agent Task Handoff, Documentation Synthesis, Architecture, Compliance).
npx skillsauth add richfrem/agent-plugins-skills context-bundlerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill requires Python 3.8+ and standard library only. No external packages needed.
This skill centralizes workflows for compiling codebase files, documentation, and instructions into portable payloads (.md for AI chat UIs or .zip for offline/agent handoffs).
context-bundler supports 3 Execution Modes:
prompt.md) ahead of codebase files./skills, /agents, /scripts, /docs).assets/templates/)When bundling context for external models, sub-agents, or human reviews, select or recommend a template from assets/templates/:
adversarial-security-auditor.md: OWASP Top 10, auth bypasses, injection vectors, exploit scenarios, CVSS risk ratings.refactoring-quality-specialist.md: DRY violations, code smells, cyclomatic complexity reduction, before/after code diffs.compliance-standards-reviewer.md: Project conventions, 20-line purpose headers, ADR compliance, type annotations.structural-architecture-reviewer.md: C4 model, SOLID principles, coupling, interface abstraction leaks, component boundaries.plan-critique-reviewer.md: Stress-tests implementation plans, unstated dependencies, execution friction, rollback mechanisms.agent-task-delegator.md: Builds turnkey task prompts for sub-agents (Copilot CLI, Claude Code, Gemini CLI) with explicit tool gates & test criteria.docs-synthesis-specialist.md: Generates ADRs, C4 Mermaid diagrams, README guides, and API specs from raw codebase context.Evaluate the request and negotiate mode and format:
.md) or Portable ZIP archive (.zip).Present execution plan to user before running scripts:
Context Bundle Plan:
- Mode: [Standard / Persona Review (Selected Persona) / Monorepo Segmented]
- Format: [.md or .zip]
- Persona Prompt: assets/templates/[selected-persona].md
- Included Paths:
1. plugins/dev-utils/
2. docs/architecture.md
- Output Target: temp/context-bundle-[name]/payload.[md|zip]
Proceed? (yes / adjust)
Generate file-manifest.json in temporary directory (temp/context-bundle-[name]/).
For Persona-Driven mode, prompt.md (containing the selected persona prompt) MUST be listed as the first file entry in files.
{
"title": "Sub-Agent Handoff Bundle",
"description": "Task delegation bundle for Copilot CLI.",
"excludes": ["**/*.png", "**/node_modules/**"],
"files": [
{
"path": "temp/context-bundle-task/prompt.md",
"note": "Primary Persona & Handoff Instructions"
},
{
"path": "plugins/dev-utils/skills/github-issue-agent/",
"note": "Target codebase"
}
]
}
Markdown (.md):
python3 ./scripts/bundle.py --manifest temp/context-bundle-[name]/file-manifest.json --bundle temp/context-bundle-[name]/payload.md
ZIP Archive (.zip):
python3 ./scripts/bundle_zip.py --manifest temp/context-bundle-[name]/file-manifest.json --bundle temp/context-bundle-[name]/payload.zip
Inform user when payload is ready for handoff or clipboard copying.
testing
Skill for creating and managing isolated git worktrees (`.worktrees/issue-NNN`) for issue execution branches. USE ONLY when setting up or cleaning up isolated git worktrees for specific issue execution. DO NOT USE for managing local task files (use `task-agent`) or escalating tasks to issues (use `github-issue-backlog-agent`).
data-ai
Skill for orchestrating the end-to-end GitHub issue lifecycle flow: Issue -> Worktree -> Implementation -> PR Creation -> Resolution Closure. USE ONLY when running or dry-running full lifecycle orchestration for resolving an issue with a PR. DO NOT USE for isolated worktree management only (use `issue-worktree-agent`) or logging issues (use `github-issue-agent`).
tools
Automatically ranks GitHub issues (P0-P3) based on friction tier, frequency, and blockages, synchronizing priority labels and GitHub Projects v2 custom fields.
testing
Bridge skill for escalating ephemeral local task scratchpad items (`tasks/*.md`) into durable, taxonomy-validated, evidence-rich GitHub Issues. USE ONLY when promoting a single-session local task into durable repository backlog. DO NOT USE for managing local kanban boards (use `task-agent` instead) or directly querying/commenting on issues (use `github-issue-agent` instead).