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/motlin/claude-code-plugins/openrewrite-analyze-recipesgit clone --depth 1 https://github.com/motlin/claude-code-pluginsWrote 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/motlin/claude-code-plugins/openrewrite-analyze-recipes)<a href="https://agentmods.dev/commands/motlin/claude-code-plugins/openrewrite-analyze-recipes"><img src="https://agentmods.dev/badge/commands/motlin/claude-code-plugins/openrewrite-analyze-recipes.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 | $0.00013 | $0.00756 |
| Opus 5 | $0.00006 | $0.00378 |
| Sonnet 5 | $0.00003 | $0.00151 |
| Haiku 4.5 | $0.00001 | $0.00076 |
Grade A, and why
openrewrite-analyze-recipes 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 yesterday.
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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenRewrite Analyze Recipes
Dry-run all configured OpenRewrite recipes, rank them by number of violations, and present the ranked list. Optionally run a selected recipe in isolation.
Parse active recipes from the POM
Find the rewrite-maven-plugin configuration in pom.xml and extract the list of <recipe> elements inside <activeRecipes>. Save this list for later; you'll need the fully-qualified recipe names.
Also extract the <activeStyles> entries if any exist.
Run the dry run
mvn rewrite:dryRun 2>&1 | tee .llm/rewrite-dryrun.log | tail -20
This may take several minutes. The dry run produces:
- Console output with
[WARNING]lines listing which recipes would change which files - A patch file at
./target/rewrite/rewrite.patch
Save the patch
cp ./target/rewrite/rewrite.patch .llm/rewrite-dryrun.patch
Count violations per recipe
The Maven log contains indented [WARNING] lines with recipe names. Extract and count them:
grep '\[WARNING\]' .llm/rewrite-dryrun.log \
| grep -E '^\S+\s+\[WARNING\]\s{4,}' \
| sed 's/.*\[WARNING\] *//' \
| sort | uniq -c | sort -rn \
> .llm/rewrite-violations-per-rule.txt
Compute summary statistics
echo "Total files changed: $(grep 'These recipes would make changes' .llm/rewrite-dryrun.log | wc -l | tr -d ' ')"
echo "Patch size: $(wc -l < .llm/rewrite-dryrun.patch) lines"
echo "Total rule violations: $(awk '{s+=$1}END{print s}' .llm/rewrite-violations-per-rule.txt)"
echo "Unique rules triggered: $(wc -l < .llm/rewrite-violations-per-rule.txt | tr -d ' ')"
Present the ranked list
Show the user:
- The summary statistics
- The full ranked table from
.llm/rewrite-violations-per-rule.txtformatted as a markdown table with columnsCountandRecipe - Mark composite recipes (recipes that contain other recipes) with "(composite)" if you can identify them from the log's tree structure
Ask which recipe to run
Use AskUserQuestion to ask which recipe to run. Offer the top 3 leaf (non-composite) recipes as options, using their fully-qualified names. The user may also type any recipe name.
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.
- yesterday First seen · 86 lines · 13 tokens per session scan A 20646badd597
openrewrite-analyze-recipes is a command published in the GitHub repository motlin/claude-code-plugins (15 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 756 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 2026-09-04.
Other commands, from other repositories
profile
Coordinate a reproducible Java profiling and optimization lifecycle.
scaffold-spring-api
Scaffold a new Spring Boot 3.5.x WebFlux REST API project with standard structure, build config, and sample endpoint.
savant-jvm
JVM performance optimization with JVM Developer agent.
java-exercise-pattern
Новое упражнение по паттернам проектирования или принципам SOLID.
java-exercise-fix
Исправить код с объяснениями и мнемотехникой.
ContinuationTask
Package: net.minecraft.commands.execution.tasks Type: class implements EntryAction.