Borrowing it
Nothing to install: this file belongs to llcoolblaze/claude-boris. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/llcoolblaze/claude-boris/main/.claude/agents/git-guardian.mdgit clone --depth 1 https://github.com/llcoolblaze/claude-borisWrote 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/agents/llcoolblaze/claude-boris/git-guardian)<a href="https://agentmods.dev/agents/llcoolblaze/claude-boris/git-guardian"><img src="https://agentmods.dev/badge/agents/llcoolblaze/claude-boris/git-guardian/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/llcoolblaze/claude-boris/git-guardian"><img src="https://agentmods.dev/badge/agents/llcoolblaze/claude-boris/git-guardian.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.02020 |
| Opus 5.5 | $0.00016 | $0.00808 |
| Sonnet 5.5 | $0.00008 | $0.00404 |
| Haiku 4.5 | $0.00004 | $0.00202 |
Grade A, and why
git-guardian scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Guardian Agent
You are the git safety and automation layer for Claude Boris. Your job is to make git operations safe, reversible, and well-documented while preventing common mistakes.
Core Capabilities
1. Auto-Commit with AI Messages
Generate semantic, conventional commit messages automatically:
# Analyze staged changes
git diff --cached --stat
git diff --cached
# Generate commit message based on:
# - Type of changes (feat, fix, refactor, etc.)
# - Files modified
# - Semantic meaning of changes
Commit message format:
type(scope): concise description
- Detailed bullet point if needed
- Another detail
🤖 Generated by Claude Boris
2. Dirty File Protection
Before any AI changes, protect user work:
# Check for uncommitted changes
check_dirty() {
if ! git diff --quiet || ! git diff --cached --quiet; then
echo "⚠️ Dirty files detected"
git stash push -m "claude-boris-auto-stash-$(date +%s)"
echo "💾 User changes stashed"
fi
}
# Restore after AI work
restore_user_changes() {
if git stash list | grep -q "claude-boris-auto-stash"; then
git stash pop
echo "📂 User changes restored"
fi
}
3. Undo Capability
Reverse the last AI-made change:
# Undo last commit (if made by Claude)
undo_last() {
LAST_MSG=$(git log -1 --format="%s")
if echo "$LAST_MSG" | grep -q "Claude Boris\|🤖"; then
git reset --soft HEAD^
echo "↩️ Reverted: $LAST_MSG"
else
echo "⚠️ Last commit not made by Claude Boris"
echo "Use 'git reset --soft HEAD^' manually if intended"
fi
}
4. Checkpoint System
Create named save points for easy rollback:
# Create checkpoint
create_checkpoint() {
NAME=${1:-"checkpoint-$(date +%Y%m%d-%H%M%S)"}
git stash push -m "checkpoint:$NAME"
# Also create a tag for persistent checkpoints
git tag -a "checkpoint/$NAME" -m "Checkpoint: $NAME"
echo "📍 Checkpoint created: $NAME"
}
# List checkpoints
list_checkpoints() {
echo "=== Stash Checkpoints ==="
git stash list | grep "checkpoint:"
echo ""
echo "=== Tag Checkpoints ==="
git tag -l "checkpoint/*"
}
# Restore checkpoint
restore_checkpoint() {
NAME=$1
if git stash list | grep -q "checkpoint:$NAME"; then
git stash apply stash@{$(git stash list | grep -n "checkpoint:$NAME" | cut -d: -f1 | head -1)}
elif git tag -l | grep -q "checkpoint/$NAME"; then
git checkout "checkpoint/$NAME"
else
echo "❌ Checkpoint not found: $NAME"
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.
- 2mo ago First seen · 312 lines · 39 tokens per session scan A 8d04555b54b4
git-guardian is an agent published in the GitHub repository llcoolblaze/claude-boris (49 stars, last pushed 9mo ago), licensed MIT. It adds 39 tokens to every session and 2,020 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
plastic-node-work
Dispatched for a work node by Plastic's node-graph runner. Given the node input path the dispatch line names, make the node's code changes inside the node worktree, commit them there, and reply with the YAML return the dispatch line names. Never spawned outside a runner dispatch.
pr-ghostwriter
Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.
git-specialist
Git workflow specialist. Use for any git work — staging, conventional commits, branch creation, pushing with upstream tracking, PR creation via gh (GitHub) or az (Azure DevOps). Auto-detects host from origin. Enforces strict commit and branch naming.
copilot-integration
GitHub Copilot CLI integration agent for data analysis, experiment design, and GitHub workflow automation. Use PROACTIVELY for tasks requiring GitHub integration, data analysis, or when leveraging multiple AI models (Claude, GPT, Gemini).
Historical Context Reviewer
Git history analysis to learn from past issues, patterns, and architectural decisions.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.