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 rules/usrrname/cursorrules/release-commit-analysis-autogit clone --depth 1 https://github.com/usrrname/cursorrulesWhat 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 | $0.02227 |
| Opus 5 | $0.00000 | $0.01113 |
| Sonnet 5 | $0.00000 | $0.00445 |
| Haiku 4.5 | $0.00000 | $0.00223 |
Grade A, and why
release-commit-analysis-auto scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Commit Analysis
Critical Rules
- Must analyze both conventional and non-conventional commit messages
- Must categorize commits into Features, Bug Fixes, Breaking Changes, Chore, Documentation, and Other
- Must use intelligent keyword matching for non-conventional commits
- Must analyze file changes to help categorize documentation commits
- Must analyze file changes to help categorize chore commits or renamed files or folders
- Must provide comprehensive change summaries for version bump suggestions
- Must handle cases where no commits exist since last tag
filters:
- type: content pattern: "(release|version|tag|bump|publish|deploy).*(create|make|generate|prepare|ready)"
- type: git_branch pattern: "^(?!main$|master$).*$"
- type: event pattern: "chat_start|chat_response"
actions:
-
type: generate content: |
📊 Commit Analysis Process
I'll analyze your commits to categorize changes and suggest appropriate version bumps.
-
Check User Request for Version Bump:
# Check if user specified version bump in their request if [[ "$USER_REQUEST" == *"major"* ]] || [[ "$USER_REQUEST" == *"Major"* ]]; then VERSION_BUMP="major" echo "User requested major version bump" elif [[ "$USER_REQUEST" == *"minor"* ]] || [[ "$USER_REQUEST" == *"Minor"* ]]; then VERSION_BUMP="minor" echo "User requested minor version bump" elif [[ "$USER_REQUEST" == *"patch"* ]] || [[ "$USER_REQUEST" == *"Patch"* ]]; then VERSION_BUMP="patch" echo "User requested patch version bump" else VERSION_BUMP="" echo "No version bump specified by user" fi -
Analyze Changes for Guidance:
# Get all commits since that tag with full details COMMITS=$(git log --oneline --no-merges $LATEST_TAG..HEAD) # Get detailed commit information for better analysis COMMIT_DETAILS=$(git log --format="%H%n%s%n%b" --no-merges $LATEST_TAG..HEAD) # Analyze conventional commit types for version bump suggestion BREAKING_COUNT=$(echo "$COMMITS" | grep -c "BREAKING:" || echo "0") FEAT_COUNT=$(echo "$COMMITS" | grep -c "feat:" || echo "0") FIX_COUNT=$(echo "$COMMITS" | grep -c "fix:" || echo "0") DOCS_COUNT=$(echo "$COMMITS" | grep -c "docs:" || echo "0") STYLE_COUNT=$(echo "$COMMITS" | grep -c "style:" || echo "0") REFACTOR_COUNT=$(echo "$COMMITS" | grep -c "refactor:" || echo "0") PERF_COUNT=$(echo "$COMMITS" | grep -c "perf:" || echo "0") TEST_COUNT=$(echo "$COMMITS" | grep -c "test:" || echo "0") CHORE_COUNT=$(echo "$COMMITS" | grep -c "chore:" || echo "0") # Analyze non-conventional commits with intelligent categorization NON_CONVENTIONAL_COMMITS=$(echo "$COMMITS" | grep -v "^(feat|fix|docs|style|refactor|perf|test|chore):" | grep -v "BREAKING:") if [ -n "$NON_CONVENTIONAL_COMMITS" ]; then echo "🔍 Found non-conventional commits, analyzing content for categorization..." # Initialize counters for non-conventional commits NC_FEAT_COUNT=0 NC_FIX_COUNT=0 NC_BREAKING_COUNT=0 NC_DOCS_COUNT=0 NC_OTHER_COUNT=0 # Analyze each non-conventional commit while IFS= read -r commit; do HASH=$(echo "$commit" | cut -d' ' -f1) MESSAGE=$(echo "$commit" | cut -d' ' -f2-) # Get files changed in this commit FILES_CHANGED=$(git show --name-only --format="" "$HASH" 2>/dev/null) # Categorize based on message content and file changes if [[ "$MESSAGE" =~ (add|new|implement|create|introduce|support|enable|feature) ]]; then NC_FEAT_COUNT=$((NC_FEAT_COUNT + 1)) echo " 📝 Non-conventional commit categorized as FEATURE: $MESSAGE" elif [[ "$MESSAGE" =~ (fix|bug|issue|problem|error|crash|fail|broken|resolve|correct) ]]; then NC_FIX_COUNT=$((NC_FIX_COUNT + 1)) echo " 🐛 Non-conventional commit categorized as FIX: $MESSAGE" elif [[ "$MESSAGE" =~ (BREAKING|breaking|remove|delete|drop|deprecate|change|update|upgrade|migrate) ]]; then NC_BREAKING_COUNT=$((NC_BREAKING_COUNT + 1)) echo " 💥 Non-conventional commit categorized as BREAKING: $MESSAGE" elif [[ "$MESSAGE" =~ (doc|readme|comment|example|guide|tutorial) ]] || echo "$FILES_CHANGED" | grep -q "\.md$\|\.txt$\|docs/\|README"; then NC_DOCS_COUNT=$((NC_DOCS_COUNT + 1)) echo " 📚 Non-conventional commit categorized as DOCS: $MESSAGE" else NC_OTHER_COUNT=$((NC_OTHER_COUNT + 1)) echo " 🔧 Non-conventional commit categorized as OTHER: $MESSAGE" fi done <<< "$NON_CONVENTIONAL_COMMITS" # Add non-conventional counts to conventional counts FEAT_COUNT=$((FEAT_COUNT + NC_FEAT_COUNT)) FIX_COUNT=$((FIX_COUNT + NC_FIX_COUNT)) BREAKING_COUNT=$((BREAKING_COUNT + NC_BREAKING_COUNT)) DOCS_COUNT=$((DOCS_COUNT + NC_DOCS_COUNT)) echo "📊 Non-conventional commit analysis complete:" echo " - Features: $NC_FEAT_COUNT" echo " - Fixes: $NC_FIX_COUNT" echo " - Breaking: $NC_BREAKING_COUNT" echo " - Docs: $NC_DOCS_COUNT" echo " - Other: $NC_OTHER_COUNT" fi # Determine version bump suggestion based on all analyzed commits if [ "$BREAKING_COUNT" -gt 0 ]; then SUGGESTED_BUMP="major" elif [ "$FEAT_COUNT" -gt 0 ]; then SUGGESTED_BUMP="minor" elif [ "$FIX_COUNT" -gt 0 ]; then SUGGESTED_BUMP="patch" else SUGGESTED_BUMP="patch" fi echo "📈 Commit analysis summary:" echo " - Breaking changes: $BREAKING_COUNT" echo " - New features: $FEAT_COUNT" echo " - Bug fixes: $FIX_COUNT" echo " - Documentation: $DOCS_COUNT" echo " - Style/Refactor: $((STYLE_COUNT + REFACTOR_COUNT))" echo " - Performance: $PERF_COUNT" echo " - Tests: $TEST_COUNT" echo " - Chores: $CHORE_COUNT" echo " - Suggested version bump: $SUGGESTED_BUMP"
-
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 · 211 lines · 0 tokens per session scan A 8be17335835b
release-commit-analysis-auto is a cursor rule published in the GitHub repository usrrname/cursorrules (10 stars, last pushed 4mo ago), licensed ISC. It costs nothing until one of its globs matches a file; then it loads 2,227 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 2026-08-31.
Other cursor rules, from other repositories
code-optimization
Guidelines for optimizing duplicate and poorly structured code.
implementation-workflow
Required plan-first workflow for any implementation request (steps 1–5).
memory-bank
You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…
docs-plain-language
Write clear, jargon-free documentation (README, docs, SECURITY, memory bank).
general
You are running in Cursor IDE. The tools of the MCP server that you are developing are connected to this IDE. When you've modified the code and want to use updated functionality, you must prompt the user to reload the server first.
angular
Angular: signals, standalone components, RxJS patterns.