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/plan-improvements.eval)<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/plan-improvements.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/plan-improvements.eval/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/davistroy/claude-marketplace/plan-improvements.eval"><img src="https://agentmods.dev/badge/commands/davistroy/claude-marketplace/plan-improvements.eval.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00546 |
| Opus 5 | $0.00000 | $0.00273 |
| Sonnet 5 | $0.00000 | $0.00109 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
plan-improvements.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 10d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval: /plan-improvements
Purpose
Analyzes a codebase and generates a prioritized IMPLEMENTATION_PLAN.md with improvement recommendations. Unlike /create-plan (requirements-driven), this is codebase-driven. Good output: a plan that reflects actual issues in the code, not generic advice.
Fixtures
None — operates on the current repository. Run against the marketplace repo itself for a meaningful eval.
Test Scenarios
S1: Happy path — analyze current repo
Invocation: /plan-improvements
Must:
- Performs codebase reconnaissance (scans files, identifies structure)
- Produces
IMPLEMENTATION_PLAN.mdor aRECOMMENDATIONS.md(per command docs, it generates both) - Plan has STATUS markers (
<!-- STATUS:todo -->) on all work items - Findings reference specific files from the actual codebase (not generic "add unit tests")
- At least 2 phases with at least 2 items each
Should:
- Priority rubric is applied (higher priority items appear in earlier phases)
- Items include file count and LOC estimates for sizing
- Plan covers multiple improvement dimensions (not just one category)
Must NOT:
- Generate a plan that could apply to any project (must be specific to this codebase)
- Exceed 8 phases or 6 items per phase
S2: Recommendations-only mode
Invocation: /plan-improvements --recommendations-only
Must:
- Generates
RECOMMENDATIONS.mdwithout creatingIMPLEMENTATION_PLAN.md - Recommendations include priority and rationale
- Does not write a plan file
S3: Focus on specific dimension
Invocation: /plan-improvements --focus security
Must:
- Analysis emphasizes security-related issues
- Generated plan items are predominantly security-focused
S4: Does not modify source files
Must:
- Only creates/modifies
IMPLEMENTATION_PLAN.mdand/orRECOMMENDATIONS.md - Does not modify any existing plugin commands, skills, or references
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.
- 10d ago First seen · 77 lines · 0 tokens per session scan A 19f4f0a045f8
plan-improvements.eval is a command published in the GitHub repository davistroy/claude-marketplace (5 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 546 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
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.
security-review
AI-powered security review of the current git diff (or specified paths). Dispatches the security-reviewer agent and prints findings grouped by severity.