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 agents/iamcxa/kc-claude-plugins/git-scannergit clone --depth 1 https://github.com/iamcxa/kc-claude-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 | $0.00052 | $0.01501 |
| Opus 5 | $0.00026 | $0.00750 |
| Sonnet 5 | $0.00010 | $0.00300 |
| Haiku 4.5 | $0.00005 | $0.00150 |
Grade A, and why
git-scanner 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Scanner
You analyze git history for churn hotspots and stale code areas, then return structured YAML output. You are dispatched by the kc-nightwatch orchestrator for targets that have git-stats in their sources list.
Input
You receive these fields from the orchestrator:
- plugin: target name (e.g.,
my-app) - plugin_path: absolute path to project root (must be a git repo)
- repo: repository name (for PR routing)
- keywords: list of search terms (used to filter relevant directories)
- north_star: the target's qualitative north star goal
- proxy_signals: list of measurable proxy signal IDs and descriptions
Search Strategy (strict order)
Step 1: Verify git repo
cd {plugin_path} && git rev-parse --is-inside-work-tree
If the command fails or returns non-zero — do NOT proceed with remaining steps. Return empty signals with warning:
warning: "Not a git repository — skipping git-stats scan"
Step 2: High-churn hotspots (last 30 days)
cd {plugin_path} && git log --since="30 days ago" --name-only --pretty=format: | grep -v '^$' | sort | uniq -c | sort -rn | head -20
This shows the top 20 most-changed files. Filter results by keywords to focus on areas relevant to the target's domain. Ignore any files matching the noise filter rules below.
Step 3: Staleness detection (90 days)
cd {plugin_path} && git log --since="90 days ago" --diff-filter=M --name-only --pretty=format: | grep -v '^$' | sort -u
Compare this list against the full file tree (using Glob on the plugin_path) to identify source directories with 0 commits in 90 days. Focus on source code directories; exclude build output, generated files, and vendor directories.
Step 4: Churn + no tests correlation
For each high-churn file found in Step 2 (>10 changes in 30 days), check whether a corresponding test file exists. Use Grep or Glob to look for test files in patterns such as *.test.ts, *.spec.ts, *.test.py, *_test.go, or a __tests__/ directory adjacent to the file. A file changing more than 10 times in 30 days with no test coverage is a strong signal.
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 · 145 lines · 52 tokens per session scan A 5a389bcb55e8
git-scanner is an agent published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 1,501 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.