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/saajunaid/caddis-pluginWrote 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/saajunaid/caddis-plugin/review-and-refactor)<a href="https://agentmods.dev/commands/saajunaid/caddis-plugin/review-and-refactor"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/review-and-refactor/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/saajunaid/caddis-plugin/review-and-refactor"><img src="https://agentmods.dev/badge/commands/saajunaid/caddis-plugin/review-and-refactor.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 | $0.00011 | $0.00506 |
| Opus 5.5 | $0.00004 | $0.00202 |
| Sonnet 5.5 | $0.00002 | $0.00101 |
| Haiku 4.5 | $0.00001 | $0.00051 |
Grade A, and why
review-and-refactor 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 1mo 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.
Review and Refactor
Act as a senior software engineer. Review the specified code (or the full project) and apply refactoring improvements while maintaining correctness.
Instructions
Step 1: Understand the Standards
Check for project-level coding guidelines in common locations:
CONTRIBUTING.md,CODING_STANDARDS.md, or similar docs- Linter/formatter configs (
.eslintrc,pyproject.toml,.editorconfig) - Existing code patterns and conventions
If coding standards exist, all refactoring must conform to them.
Step 2: Review the Code
Analyze each file for these issues:
Readability
- Unclear variable or function names
- Missing or misleading comments
- Overly complex expressions that could be simplified
- Inconsistent formatting or style
Maintainability
- Functions longer than ~40 lines (candidates for extraction)
- Duplicated logic across files
- Deep nesting (> 3 levels) that could be flattened
- Magic numbers or hardcoded strings (extract to constants)
Best Practices
- Missing error handling or overly broad exception catches
- Unused imports, variables, or dead code
- Mutable default arguments or other language-specific pitfalls
- Missing type hints or annotations (where the project uses them)
Step 3: Refactor
Apply improvements while following these rules:
- Keep existing file structure — do not split files unless explicitly asked.
- Preserve behavior — refactoring must not change what the code does.
- Run tests after changes — if the project has tests, verify they still pass.
- Make small, reviewable changes — each refactoring should be easy to understand.
Step 4: Summarize
After refactoring, provide a summary:
## Refactoring Summary
### Changes Made
| File | Change | Reason |
|------|--------|--------|
| ... | ... | ... |
### Tests
- All existing tests: PASS / FAIL
- New issues introduced: None / <list>
### Recommendations
- <any further improvements that were out of scope>
What NOT to Do
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.
- 1mo ago First seen · 77 lines · 11 tokens per session scan A 8953a47dcb07
review-and-refactor is a command published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 506 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-09.
Other commands, from other repositories
proof-capture
Capture PR-ready proof artifacts for a feature, with an attested fail-closed controller in strict mode.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
specify
Command dispatcher for specify.
run-workflow
Validate and establish the proven rn-dev-agent operating sequence before a real React Native journey — declared package manager and dependencies, read-only inventory, typed session recovery, one exclusive device, managed integration and Metro, only the requested proof, reverse-order cleanup.
observe
Show the observability web UI URL (it autostarts with the session); stop or restart it.
accept
Command dispatcher for accept.