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 commands/parkerm2/create-claude-workflow/new-plangit clone --depth 1 https://github.com/ParkerM2/create-claude-workflowWrote 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/commands/parkerm2/create-claude-workflow/new-plan)<a href="https://agentmods.dev/commands/parkerm2/create-claude-workflow/new-plan"><img src="https://agentmods.dev/badge/commands/parkerm2/create-claude-workflow/new-plan.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 | $0.00023 | $0.04741 |
| Opus 5 | $0.00012 | $0.02371 |
| Sonnet 5 | $0.00005 | $0.00948 |
| Haiku 4.5 | $0.00002 | $0.00474 |
Grade A, and why
new-plan 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 4d 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 — 688 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/new-plan — Deep Technical Planning for /agent-team
Invoke this skill to produce an in-depth technical plan for a feature before handing it off to
/agent-team. Uses brainstorming, codebase analysis, and architectural thinking to create a design document that the Team Leader can execute directly — no interpretation needed.
When to Use
- Before running
/agent-teamon a complex or ambiguous feature - When you have a feature idea but need to refine requirements and design
- When you want the Team Leader to receive a ready-made decomposition plan
- When the feature touches unfamiliar parts of the codebase and needs deep analysis first
- When conversation context contains scattered requirements that need consolidation
When NOT to Use
- The feature is small and well-defined (just run
/agent-teamdirectly) - You already have a complete design document
Phase 1: Gather Requirements
1a. Source the Feature Description
The feature description comes from one of these sources (check in order):
- The current prompt — if the user included a feature description with this invocation
- Conversation context — if the feature was discussed in earlier messages
- A referenced document — if the user points to a design doc, issue, or spec
If the source is conversation context, consolidate all relevant details into a single requirements summary. Do not lose nuance from the discussion.
1b. Clarify Ambiguities
Use the AskUserQuestion tool to resolve any unknowns. Focus on questions that affect architecture or scope:
Questions to consider:
- What is the primary user-facing behavior this feature enables?
- Are there specific UI/UX requirements or wireframes?
- Which existing systems does this feature interact with?
- Are there performance requirements or constraints?
- Are there security or privacy implications?
- Should this feature be behind a feature flag?
- What is the expected data volume / scale?
- Are there any hard constraints on technology choices?
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.
- 4d ago First seen · 688 lines · 23 tokens per session scan A bb4aa1e9c6c0
new-plan is a command published in the GitHub repository ParkerM2/create-claude-workflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 4,741 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.