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/stefan-jansen/claude-code-toolkit/prepare-reviewgit clone --depth 1 https://github.com/stefan-jansen/claude-code-toolkitWrote 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/stefan-jansen/claude-code-toolkit/prepare-review)<a href="https://agentmods.dev/commands/stefan-jansen/claude-code-toolkit/prepare-review"><img src="https://agentmods.dev/badge/commands/stefan-jansen/claude-code-toolkit/prepare-review.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 | $0.00000 | $0.00495 |
| Opus 5 | $0.00000 | $0.00247 |
| Sonnet 5 | $0.00000 | $0.00099 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
prepare-review 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.
What it actually says
Prepare External Code Review Package
Package codebase for external review using RepoMix.
Usage
/development:prepare-review # Generic review
/development:prepare-review "API authentication" # Focused review
Process
-
Determine Scope
- With focus: Select relevant files only
- No focus: All main source files, exclude tests
-
Select Files
Include: Entry points, core logic, API routes, models, key config
Exclude: tests/, node_modules/, venv/, dist/, build/, migrations
-
Summarize Docs (if >10k tokens total)
- README >5k tokens → summarize
- Multiple specs → combine and summarize
-
Generate RepoMix Config
{ "output": { "style": "xml", "showLineNumbers": false, "removeEmptyLines": true }, "include": ["src/**/*.py", "config.yaml"], "ignore": {"useGitignore": true} } -
Run RepoMix
npx -y repomix --config .repomix/config.json -
Create Package
- Location:
.claude/external_reviews/YYYY-MM-DD-HHMM/review_package.md - Contains: Review prompt + docs summary + codebase (RepoMix XML)
- Location:
Token Budget
Target: <100,000 tokens total
- Review prompt: ~5k
- Docs summary: ~10k
- Codebase: ~40-80k
Review Prompt Template
# Code Review Request
## Focus Areas
1. Architecture & Design
2. Completeness & Correctness
3. Code Quality & Maintainability
4. Integration & Dependencies
5. Best Practices
## Not Included
- Tests (N files) - excluded for focus
- Build artifacts
## Output Format
1. Executive Summary
2. Critical Issues (must fix)
3. Important Issues (should fix)
4. Minor Issues
5. Positive Observations
If Token Count >100k
Reduce by: narrowing focus, summarizing docs more, excluding utility files
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 · 89 lines · 0 tokens per session scan A 71d02fee08be
prepare-review is a command published in the GitHub repository stefan-jansen/claude-code-toolkit (85 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 495 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 2026-08-30.
Other commands, from other repositories
deploy
Deploy the application.
hello
A test command.
coder-eval-implement-plan
Implement an approved codereval plan phase by phase with risk-scaled per-phase review, then a final code review.
configure-blob
Create and configure an Azure Blob Storage account with security best practices.
run
Command "run" from ErisPulse/ErisPulse, covering erispulse.cli.commands.run 模块, 模块概述, 类列表, class reloadhandler(filesystemeventhandler) and class runcommand(command).
task-verify
PitWay: Run an inprogress task's approved verification command and persist evidence.