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/sylphxai/coderag/cleanupgit clone --depth 1 https://github.com/SylphxAI/coderagWhat 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 | $0.00015 | $0.00377 |
| Opus 5 | $0.00008 | $0.00188 |
| Sonnet 5 | $0.00003 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
cleanup 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 2d 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
Cleanup & Refactor
Scan codebase for technical debt and code smells. Clean, refactor, optimize.
Scope
Code Smells:
- Functions >20 lines → extract
- Duplication (3+ occurrences) → DRY
- Complexity (>3 nesting levels) → flatten
- Unused code/imports/variables → remove
- Commented code → delete
- Magic numbers → named constants
- Poor naming → clarify
Technical Debt:
- TODOs/FIXMEs → implement or delete
- Deprecated APIs → upgrade
- Outdated patterns → modernize
- Performance bottlenecks → optimize
- Memory leaks → fix
- Lint warnings → resolve
Optimization:
- Algorithm complexity → reduce
- N+1 queries → batch
- Unnecessary re-renders → memoize
- Large bundles → code split
- Unused dependencies → remove
Execution
- Scan entire codebase systematically
- Prioritize by impact (critical → major → minor)
- Clean incrementally with atomic commits
- Test after every change
- Report what was cleaned and impact
Commit Strategy
One commit per logical cleanup:
refactor(auth): extract validateToken functionperf(db): batch user queries to fix N+1chore: remove unused imports and commented code
Exit Criteria
- No code smells remain
- All tests pass
- Lint clean
- Performance improved (measure before/after)
- Technical debt reduced measurably
Report: Lines removed, complexity reduced, performance gains.
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.
- 2d ago First seen · 61 lines · 15 tokens per session scan A d27bcb2d4e0b
cleanup is a command published in the GitHub repository SylphxAI/coderag (12 stars, last pushed 7d ago), licensed MIT. It adds 15 tokens to every session and 377 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 2026-08-30.
Other commands, from other repositories
rp-build-cli
Build with rp-cli context builder → chat → implement.
rp-investigate-cli
Deep codebase investigation and architecture research with rp-cli commands.
rp-oracle-export-cli
Export context for oracle consultation using rp-cli.
rp-reminder-cli
Continue your current workflow using rp-cli instead of built-in alternatives.
call-graph
Trace callers, callees, or paths using the call graph.
peek
Quickly find likely code locations without returning full code.