Install
$ agentstack add skill-manhvann-codexkit-plan ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Planning
Create detailed technical implementation plans through research, codebase analysis, solution design, and comprehensive documentation.
Default (No Arguments)
If invoked with a task description, proceed with planning workflow. If invoked WITHOUT arguments or with unclear intent, ask the user to choose an operation:
| Operation | Description | |-----------|-------------| | (default) | Create implementation plan for a task | | archive | Write journal entry & archive plans | | red-team | Adversarial plan review | | validate | Critical questions interview |
Present options with header "Planning Operation", question "What would you like to do?".
Workflow Modes
Default: --auto (analyze task complexity and auto-pick mode).
| Flag | Mode | Research | Red Team | Validation | Cook Flag | |------|------|----------|----------|------------|-----------| | --auto | Auto-detect | Follows mode | Follows mode | Follows mode | Follows mode | | --fast | Fast | Skip | Skip | Skip | --auto | | --hard | Hard | 2 researchers | Yes | Optional | (none) | | --parallel | Parallel | 2 researchers | Yes | Optional | --parallel | | --two | Two approaches | 2+ researchers | After selection | After selection | (none) |
Add --no-tasks to skip task hydration in any mode.
Load: references/workflow-modes.md for auto-detection logic, per-mode workflows, context reminders.
When to Use
- Planning new feature implementations
- Architecting system designs
- Evaluating technical approaches
- Creating implementation roadmaps
- Breaking down complex requirements
Core Responsibilities & Rules
Always honoring YAGNI, KISS, and DRY principles. Be honest, be brutal, straight to the point, and be concise.
1. Research & Analysis
Load: references/research-phase.md Skip if: Fast mode or provided with researcher reports
2. Codebase Understanding
Load: references/codebase-understanding.md Skip if: Provided with scout reports
3. Solution Design
Load: references/solution-design.md
4. Plan Creation & Organization
Load: references/plan-organization.md
5. Task Breakdown & Output Standards
Load: references/output-standards.md
Workflow Process
- Pre-Creation Check → Check Plan Context for active/suggested/none
- Mode Detection → Auto-detect or use explicit flag (see
workflow-modes.md) - Research Phase → Spawn researchers (skip in fast mode)
- Codebase Analysis → Read docs, scout if needed
- Plan Documentation → Write comprehensive plan via planner subagent
- Red Team Review → Use
Skilltool:plan:red-team {plan-path}(hard/parallel/two modes) - Post-Plan Validation → Use
Skilltool:plan:validate {plan-path}(hard/parallel/two modes) - Hydrate Tasks → Create tracked tasks from phases when task tools exist (default on,
--no-tasksto skip) - Context Reminder → Output cook command with absolute path (MANDATORY)
Output Requirements
- DO NOT implement code - only create plans
- Respond with plan file path and summary
- Ensure self-contained plans with necessary context
- Include code snippets/pseudocode when clarifying
- Fully respect the workflow rules in
./.codex/rules/development-rules.md
Task Management
Plan files = persistent. Tasks = session-scoped. Hydration bridges the gap.
Default: Auto-hydrate tasks after plan files are written. Skip with --no-tasks. 3-Task Rule: <3 phases → skip task creation.
Load: references/task-management.md for hydration pattern, task creation patterns, cook handoff protocol.
Hydration Workflow
- Write plan.md + phase files (persistent layer)
- Create one tracked task per phase with dependency chain when task tools exist
- Create tracked tasks for critical/high-risk steps within phases when useful
- Metadata: phase, priority, effort, planDir, phaseFile
- Cook picks up existing tasks when available or re-hydrates from plan files in a new session
Active Plan State
Check ## Plan Context injected by hooks:
- "Plan: {path}" → Active plan. Ask "Continue? [Y/n]"
- "Suggested: {path}" → Branch hint only. Ask if activate or create new.
- "Plan: none" → Create new using
Plan dir:from## Naming
After creating plan: node .codex/scripts/set-active-plan.cjs {plan-dir} Reports: Active plans → plan-specific path. Suggested → default path.
Important
DO NOT create plans or reports in USER directory. ALWAYS create plans or reports under the configured Plan dir: / Reports: paths from the injected ## Naming and ## Paths context. For umbrella repositories, this may point at the umbrella root even when the current work context is a child repo.
Subcommands
| Subcommand | Reference | Purpose | |------------|-----------|---------| | ck:plan archive | references/archive-workflow.md | Archive plans + write journal entries | | ck:plan red-team | references/red-team-workflow.md | Adversarial plan review with hostile reviewers | | `` validation workflow | references/validate-workflow.md | Validate plan with critical questions interview |
Quality Standards
- Thorough and specific, consider long-term maintainability
- Research thoroughly when uncertain
- Address security and performance concerns
- Detailed enough for junior developers
- Validate against existing codebase patterns
Remember: Plan quality determines implementation success. Be comprehensive and consider all solution aspects.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: manhvann
- Source: manhvann/codexkit
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.