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/quick-commitgit clone --depth 1 https://github.com/solanabr/solana-ai-kitWhat 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 | $0.00013 | $0.03577 |
| Opus 5 | $0.00006 | $0.01788 |
| Sonnet 5 | $0.00003 | $0.00715 |
| Haiku 4.5 | $0.00001 | $0.00358 |
Grade A, and why
quick-commit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
2 near-identical copies found in the catalogue:
- quick-commit — 100% identical, 0 lines differ
- quick-commit — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 526 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are creating a quick commit. This command formats code, runs lints, generates a conventional commit message, and commits changes. If starting a new task, it creates a feature branch first.
Overview
This command automates the commit workflow:
- Check if new task → create feature branch
- Stage changes (or confirm staged changes)
- Format and lint code
- Run quick tests
- Generate conventional commit message
- Create commit
Step 0: Check for New Task / Feature Branch
echo "🌿 Checking branch status..."
# Check if we're in a git repository
if ! git rev-parse --is-inside-work-tree >/dev/null 2>&1; then
echo "❌ Not a git repository"
exit 1
fi
# Get current branch
CURRENT_BRANCH=$(git branch --show-current)
echo "Current branch: $CURRENT_BRANCH"
# Check if we're on main/master (starting a new task)
if [ "$CURRENT_BRANCH" = "main" ] || [ "$CURRENT_BRANCH" = "master" ]; then
echo ""
echo "📌 You're on $CURRENT_BRANCH. Starting a new task?"
echo ""
# Get today's date in DD-MM-YYYY format
TODAY=$(date +%d-%m-%Y)
# Analyze changes to determine branch type and name
analyze_for_branch() {
local diff_output=$(git diff --name-status)
local staged_output=$(git diff --cached --name-status)
local all_changes="$diff_output$staged_output"
# Determine type
if echo "$all_changes" | grep -q "test"; then
BRANCH_TYPE="test"
elif echo "$all_changes" | grep -q "\.md$"; then
BRANCH_TYPE="docs"
elif echo "$all_changes" | grep -qE "\.(ts|tsx|js|jsx)$" && echo "$all_changes" | grep -qv "^programs/"; then
BRANCH_TYPE="feat"
elif echo "$all_changes" | grep -q "^programs/\|\.rs$"; then
BRANCH_TYPE="feat"
else
BRANCH_TYPE="feat"
fi
# Get descriptive name from first significant file
local first_file=$(echo "$all_changes" | head -1 | awk '{print $2}')
local file_basename=$(basename "$first_file" 2>/dev/null | sed 's/\.[^.]*$//' | tr '_' '-' | tr '[:upper:]' '[:lower:]')
# Determine scope for name
if echo "$all_changes" | grep -q "^programs/"; then
BRANCH_SCOPE="program"
elif echo "$all_changes" | grep -qE "^(app|src|components)/"; then
BRANCH_SCOPE="frontend"
elif echo "$all_changes" | grep -q "^tests/"; then
BRANCH_SCOPE="tests"
else
BRANCH_SCOPE=""
fi
# Generate branch name
if [ -n "$BRANCH_SCOPE" ]; then
SUGGESTED_BRANCH="$BRANCH_TYPE/$BRANCH_SCOPE-$file_basename-$TODAY"
else
SUGGESTED_BRANCH="$BRANCH_TYPE/$file_basename-$TODAY"
fi
}
analyze_for_branch
echo "💡 Suggested branch: $SUGGESTED_BRANCH"
echo ""
echo "Options:"
echo " 1. Create branch: $SUGGESTED_BRANCH"
echo " 2. Enter custom branch name"
echo " 3. Stay on $CURRENT_BRANCH (not recommended)"
echo ""
# ASK USER which option they prefer
# Default: create the suggested branch
# Create branch
echo "Creating branch: $SUGGESTED_BRANCH"
git checkout -b "$SUGGESTED_BRANCH"
if [ $? -eq 0 ]; then
echo "✅ Created and switched to: $SUGGESTED_BRANCH"
CURRENT_BRANCH="$SUGGESTED_BRANCH"
else
echo "❌ Failed to create branch"
exit 1
fi
fi
echo ""
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.
- yesterday First seen · 526 lines · 13 tokens per session scan A 383de92f33c7
quick-commit is a command published in the GitHub repository solanabr/solana-ai-kit (98 stars, last pushed 12d ago), licensed MIT. It adds 13 tokens to every session and 3,577 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
create-command
Create slash commands with brainstorming and best practices.
validate-hook
Validate hooks for security, performance, and SDK compliance.
evaluate-skill
Manually evaluate a recent skill execution to record qualitative feedback.
test-skill
Test Claude Code skills using RED/GREEN/REFACTOR TDD phases in fresh subagents to prevent priming bias.
strict
Enable strict RIPER protocol enforcement.
db-migrate
You are a database migration expert specializing in zero-downtime deployments, data integrity, and multi-database environments. Create comprehensive migration scripts with rollback strategies, validation checks, and performance optimization.