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/centminmod/my-claude-code-setup/cleanup-contextgit clone --depth 1 https://github.com/centminmod/my-claude-code-setupWhat 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 | $0.01601 |
| Opus 5 | $0.00000 | $0.00800 |
| Sonnet 5 | $0.00000 | $0.00320 |
| Haiku 4.5 | $0.00000 | $0.00160 |
Grade A, and why
cleanup-context 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 3d 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Bank Context Optimization
You are a memory bank optimization specialist tasked with reducing token usage in the project's documentation system while maintaining all essential information and improving organization.
Task Overview
Analyze the project's memory bank files (CLAUDE-*.md, CLAUDE.md, README.md) to identify and eliminate token waste through:
- Duplicate content removal
- Obsolete file elimination
- Content consolidation
- Archive strategy implementation
- Essential content optimization
Analysis Phase
1. Initial Assessment
# Get comprehensive file size analysis
find . -name "CLAUDE-*.md" -exec wc -c {} \; | sort -nr
wc -c CLAUDE.md README.md
Examine for:
- Files marked as "REMOVED" or "DEPRECATED"
- Generated content that's no longer current (reviews, temporary files)
- Multiple files covering the same topic area
- Verbose documentation that could be streamlined
2. Identify Optimization Opportunities
High-Impact Targets (prioritize first):
- Files >20KB that contain duplicate information
- Files explicitly marked as obsolete/removed
- Generated reviews or temporary documentation
- Verbose setup/architecture descriptions in CLAUDE.md
Medium-Impact Targets:
- Files 10-20KB with overlapping content
- Historic documentation for resolved issues
- Detailed implementation docs that could be consolidated
Low-Impact Targets:
- Files <10KB with minor optimization potential
- Content that could be streamlined but is unique
Optimization Strategy
Phase 1: Remove Obsolete Content (Highest Impact)
Target: Files marked as removed, deprecated, or clearly obsolete
Actions:
- Delete files marked as "REMOVED" or "DEPRECATED"
- Remove generated reviews/reports that are outdated
- Clean up empty or minimal temporary files
- Update CLAUDE.md references to removed files
Expected Savings: 30-50KB typically
Phase 2: Consolidate Overlapping Documentation (High Impact)
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.
- 3d ago First seen · 274 lines · 0 tokens per session scan A e4c41373c200
cleanup-context is a command published in the GitHub repository centminmod/my-claude-code-setup (2,614 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,601 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
sp.reverse-engineer
Reverse engineer a codebase into SDD-RI artifacts (spec, plan, tasks, intelligence).
sp.checklist
Generate a custom checklist for the current feature based on user requirements.
sp.clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
sp.specify
Create or update the feature specification from a natural language feature description.
sp.git.commit_pr
An autonomous Git agent that intelligently executes git workflows. Your task is to intelligently executes git workflows to commit the work and create PR.
sp.adr
Review planning artifacts for architecturally significant decisions and create ADRs.