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/anilcancakir/claude-code-plugins/my_commitgit clone --depth 1 https://github.com/anilcancakir/claude-code-pluginsWhat 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 | $0.00029 | $0.01908 |
| Opus 5 | $0.00015 | $0.00954 |
| Sonnet 5 | $0.00006 | $0.00382 |
| Haiku 4.5 | $0.00003 | $0.00191 |
Grade A, and why
my_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 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.
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smart Commit Command
Create a commit following the project's commit message conventions. Auto-detects style from git history.
Arguments
Parse from $ARGUMENTS:
- message: Optional commit message (if not provided, generate from changes)
- --amend: Amend the previous commit (only your own commits)
Execution Steps
Step 1: Pre-Commit Checks
# Verify there are changes to commit
git status --porcelain
# Check we're not on protected branch
BRANCH=$(git branch --show-current)
if [ "$BRANCH" = "main" ] || [ "$BRANCH" = "master" ]; then
echo "Warning: Committing directly to $BRANCH"
fi
Step 2: Detect Commit Style
Analyze recent commits to detect project convention:
# Get last 10 commit messages
git log --oneline -10
Detection with Regex Patterns:
# Run these patterns against git log output to detect style
# Conventional Commits with scope: type(scope): message
CONVENTIONAL_SCOPED="^[a-f0-9]+ (feat|fix|docs|style|refactor|perf|test|chore|ci|build|revert)\([a-zA-Z0-9_-]+\)!?: .+"
# Conventional Commits without scope: type: message
CONVENTIONAL_SIMPLE="^[a-f0-9]+ (feat|fix|docs|style|refactor|perf|test|chore|ci|build|revert)!?: .+"
# Gitmoji: :emoji: message or unicode emoji
GITMOJI="^[a-f0-9]+ :[a-z_]+: .+|^[a-f0-9]+ (🎨|🐛|✨|📝|🔥|💚|✅|🔒|⬆️|⬇️|♻️|🔧|🌐|💄|🎉|🚀|💥) .+"
# Simple: Plain text (fallback)
Detection Algorithm:
COMMITS=$(git log --oneline -10 2>/dev/null)
TOTAL=$(echo "$COMMITS" | wc -l)
# Count matches for each style
CONV_SCOPED=$(echo "$COMMITS" | grep -cE '^[a-f0-9]+ (feat|fix|docs|style|refactor|perf|test|chore)\([^)]+\): ' || echo 0)
CONV_SIMPLE=$(echo "$COMMITS" | grep -cE '^[a-f0-9]+ (feat|fix|docs|style|refactor|perf|test|chore): ' || echo 0)
GITMOJI_COUNT=$(echo "$COMMITS" | grep -cE '^[a-f0-9]+ :[a-z_]+: ' || echo 0)
# Determine dominant style (>50% of commits)
if [ $CONV_SCOPED -gt $((TOTAL / 2)) ]; then
STYLE="conventional-scoped"
elif [ $CONV_SIMPLE -gt $((TOTAL / 2)) ]; then
STYLE="conventional"
elif [ $GITMOJI_COUNT -gt $((TOTAL / 2)) ]; then
STYLE="gitmoji"
else
STYLE="simple"
fi
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 · 278 lines · 29 tokens per session scan A 94b3d6e705c2
my_commit is a command published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 29 tokens to every session and 1,908 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 2026-08-31.
Other commands, from other repositories
debug
Systematic debugging with hypotheses and evidence gathering.
create-hook
Create a new custom automation hook.
health
Run the Self-Star Doctor - a green/yellow/red health board across all 7 junctions of the self- loop.
plan-new
Plan a complex project with discovery, structure, and kill criteria.
remember
Explicitly save something to memory as an experience.
review
Structured code review with severity categorization (distinct from Claude Code's PR review).