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 skills add cpliakas/claude-code-engineering-leaders --skill analyze-code-churngit clone --depth 1 https://github.com/cpliakas/claude-code-engineering-leadersWrote 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/skills/cpliakas/claude-code-engineering-leaders/analyze-code-churn)<a href="https://agentmods.dev/skills/cpliakas/claude-code-engineering-leaders/analyze-code-churn"><img src="https://agentmods.dev/badge/skills/cpliakas/claude-code-engineering-leaders/analyze-code-churn/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/skills/cpliakas/claude-code-engineering-leaders/analyze-code-churn"><img src="https://agentmods.dev/badge/skills/cpliakas/claude-code-engineering-leaders/analyze-code-churn.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 | $0.00059 | $0.03240 |
| Opus 5.5 | $0.00024 | $0.01296 |
| Sonnet 5.5 | $0.00012 | $0.00648 |
| Haiku 4.5 | $0.00006 | $0.00324 |
Grade A, and why
analyze-code-churn 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 1mo 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 — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Churn
Analyze code churn and thrash patterns in a git repository. Produces a structured report with hotspot detection, rework vs. refactor classification, temporal coupling analysis, and severity-rated findings with investigation recommendations.
Input
$ARGUMENTS = analysis scope — time window (e.g., "30 days", "last sprint",
"since v2.1"), optional path filter (e.g., "src/api/"), and optional focus area
(e.g., "why is auth churning", "sprint-over-sprint comparison").
Process
1. Parse Scope
Extract from $ARGUMENTS:
- Time window: Default to 30 days if not specified. Accept natural language
("last sprint", "since January") and convert to
--since/--aftergit flags. - Path filter: If a directory or file pattern is specified, scope all git commands to that path. Default to the entire repository.
- Focus area: If a specific question is asked, tailor the analysis toward answering it. Otherwise, produce the full report.
If $ARGUMENTS is empty, use a 30-day window across the entire repository.
2. Establish Baseline
Run the baseline period (the window immediately preceding the analysis window) to enable trend comparison. For a 30-day analysis window, the baseline is the prior 30 days.
Gross churn (analysis window):
git log --numstat --format="" --no-merges --since="<start>" -- <path> \
| awk '{a+=$1; d+=$2} END {print "added:", a, "deleted:", d, "gross:", a+d}'
Gross churn (baseline window):
git log --numstat --format="" --no-merges --since="<baseline_start>" --until="<start>" -- <path> \
| awk '{a+=$1; d+=$2} END {print "added:", a, "deleted:", d, "gross:", a+d}'
Commit counts (both windows):
git rev-list --count --no-merges --since="<start>" HEAD -- <path>
git rev-list --count --no-merges --since="<baseline_start>" --until="<start>" HEAD -- <path>
Record the baseline metrics for trend comparison in Step 7.
3. Detect Hotspots
Identify files with the highest change frequency, weighted by size as a complexity proxy.
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.
- 1mo ago First seen · 339 lines · 59 tokens per session scan A 05f06bad4dc6
analyze-code-churn is a skill published in the GitHub repository cpliakas/claude-code-engineering-leaders (4 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 3,240 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 2026-08-31.
Other skills, from other repositories
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.