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/solanabr/solana-ai-kit/cleanupgit clone --depth 1 https://github.com/solanabr/solana-ai-kitWrote 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/solanabr/solana-ai-kit/cleanup)<a href="https://agentmods.dev/commands/solanabr/solana-ai-kit/cleanup"><img src="https://agentmods.dev/badge/commands/solanabr/solana-ai-kit/cleanup.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 5.1 | $0.00016 | $0.00753 |
| Opus 5 | $0.00008 | $0.00377 |
| Sonnet 5 | $0.00003 | $0.00151 |
| Haiku 4.5 | $0.00002 | $0.00075 |
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 6d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize a forked solana-ai-kit template for use as a project. Sets up CLAUDE.md and removes config repo scaffolding files.
Step 1: Setup CLAUDE.md
If CLAUDE.md doesn't exist (or contains "Meta Configuration" indicating it's the repo maintainer version):
- Copy
CLAUDE-solana.md→CLAUDE.md - Create starter
CLAUDE.local.md(gitignored, private notes) if it doesn't exist - Add
CLAUDE.local.mdto.gitignoreif not present
If CLAUDE.md already exists and looks like a project config (not meta), skip this step.
Step 2: Create .env if missing
If .env doesn't exist but .env.example does, copy .env.example → .env before removing .env.example.
Step 3: Remove scaffolding
Files/dirs that exist only for maintaining or distributing the config repo itself. These ship in a full clone/fork of solana-ai-kit but have no purpose in a downstream project. Remove each only if present — never error on a missing path.
Remove (if they exist):
Maintenance scaffolding:
install.sh— installer (not needed after fork)update.sh— deprecation wrappervalidate.sh— config repo validationtests/— config repo test suiteCLAUDE-solana.md— source template (now copied as CLAUDE.md)QUICK-START.md— config repo docsREADME.md— config repo readme (user should write their own).claude/CHANGELOG.md— the kit's changelog (not the user's project changelog).github/workflows/ci.yml— config repo CI (keepclaude-code.ymlif present).env.example— should already be copied to .env
Distribution infra (Claude Code plugin marketplace + Vercel install endpoint — only relevant when publishing the kit):
.claude-plugin/— in-repo plugin marketplace manifestplugin/— symlinked core-plugin subtreevercel.json— install-endpoint redirect config
Preserve (never touch):
.claude/— entire directory (agents, commands, skills, rules, settings, mcp,bin/self-update tooling) — except.claude/CHANGELOG.mdnoted aboveCLAUDE.md— just created/preserved aboveCLAUDE.local.md— private notes.mcp.json— MCP server config (user wants this).env,.env.example(after .env exists) — config.gitmodules— submodule definitions.gitignore— ignore rulesLICENSE— keep unless user wants to change- Any user-created 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.
- 6d ago First seen · 63 lines · 16 tokens per session scan A 66ae75873543
cleanup is a command published in the GitHub repository solanabr/solana-ai-kit (101 stars, last pushed 16d ago), licensed MIT. It adds 16 tokens to every session and 753 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
commit
Smart conventional commit with security validation, branch flow enforcement, and auto-detection. Use for git commit, commit changes, save work, stage and commit.
apex
APEX Methodology - The systematic Analyze-Plan-Execute-eLicit-eXamine approach for intelligent development. Reduces hallucination and defect risk through mandatory parallel research, self-review, and validation gates.
apex-quick
Quick Flow for simple fixes - Single expert handles explore, code, review, and validate in one pass. Inspired by BMAD Barry.
explain-architecture
Analyze and explain software architecture with ASCII diagrams and pattern detection. Creates visual representations of system design.
prompt
Create or optimize prompts using best practices.
watch
Check for Claude Code updates, detect breaking changes, analyze plugin compatibility, and optionally gather community pulse via Exa.