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.
git clone --depth 1 https://github.com/davistroy/claude-marketplaceWrote 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/davistroy/claude-marketplace/create-plan.eval)<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/create-plan.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/create-plan.eval.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 | $0.00000 | $0.00767 |
| Opus 5 | $0.00000 | $0.00383 |
| Sonnet 5 | $0.00000 | $0.00153 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
create-plan.eval 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 8d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval: /create-plan
Purpose
Generates a detailed IMPLEMENTATION_PLAN.md from requirements documents (BRD, PRD, TDD, design specs). Good output: a machine-readable plan with phases, work items, sizing estimates, acceptance criteria, and status markers — following the standard schema used by /implement-plan.
Fixtures
| Fixture | Purpose |
|---|---|
docs/sample-prd.md |
Well-formed PRD — good source for a complete plan |
docs/draft-prd.md |
Incomplete PRD — tests handling of ambiguous requirements |
Test Scenarios
S1: Happy path — complete PRD input
Invocation: /create-plan fixtures/docs/sample-prd.md
Must:
- Creates
IMPLEMENTATION_PLAN.mdin the current directory (or specified output) - Plan has at least 2 phases
- Each work item has: Status (todo), Size (S/M/L), Tasks list, Acceptance Criteria
- Items include
<!-- STATUS:todo -->machine-readable markers - Plan covers the P0 requirements from the PRD (F-01, F-07 at minimum)
- Total phases ≤ 8, items per phase ≤ 6 (plan size limits)
Should:
- Work items align with the PRD's functional requirements (F-01 through F-15)
- Phases are logically ordered (e.g., database schema before API layer)
- Sizing estimates (S/M/L) are proportional to the described complexity
- Non-goals from PRD Section 1.4 are NOT included as work items
Must NOT:
- Include more than 8 phases
- Include work items for features explicitly listed as out of scope
- Create the file without status markers (plan is not machine-readable without them)
S2: Draft/incomplete PRD input
Invocation: /create-plan fixtures/docs/draft-prd.md
Must:
- Either: generates a plan with placeholder/TBD items for unresolved requirements
- Or: asks clarifying questions before generating the plan
- Does not generate a plan that assumes specific answers to open questions in the PRD
Should:
- Notes which requirements were ambiguous and how they were interpreted
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.
- 8d ago First seen · 98 lines · 0 tokens per session scan A cb205da37e37
create-plan.eval is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 767 tokens. 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
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.