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 urmzd/dotfiles --skill repo-statusgit clone --depth 1 https://github.com/urmzd/dotfilesWrote 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/urmzd/dotfiles/repo-status)<a href="https://agentmods.dev/skills/urmzd/dotfiles/repo-status"><img src="https://agentmods.dev/badge/skills/urmzd/dotfiles/repo-status/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/urmzd/dotfiles/repo-status"><img src="https://agentmods.dev/badge/skills/urmzd/dotfiles/repo-status.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 | $0.00140 | $0.00774 |
| Opus 5 | $0.00070 | $0.00387 |
| Sonnet 5 | $0.00028 | $0.00155 |
| Haiku 4.5 | $0.00014 | $0.00077 |
Grade A, and why
repo-status 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 8d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Status
Scan a directory for git repositories with recent activity and report their status.
Invocation
The user may pass a folder path as an argument. Default to $REPO_ROOT, falling back to ~/github if unset.
Steps
-
Discover repos: Find all directories containing a
.gitfolder (one level deep only; do not recurse into nested repos). -
Filter by activity: Only include repos that have commits in the last 7 days on any local branch (
git log --all --since='7 days ago' --oneline -1). Skip repos with no recent activity. -
For each active repo, gather:
- Repo name (directory basename)
- Current branch vs default branch (use
gh repo view --json defaultBranchRef -q .defaultBranchRef.nameor fall back to checking for main/master) - Uncommitted changes:
git status --porcelain(staged, unstaged, untracked counts) - Unpushed commits: commits ahead of upstream (
git rev-list @{u}..HEAD --count 2>/dev/null) - Behind upstream: commits behind (
git fetch --quiet && git rev-list HEAD..@{u} --count 2>/dev/null) - CI status:
gh run list --limit 1 --json status,conclusion,name. Show latest workflow run status (passing/failing/in-progress)
-
Output format: Print a clean, grouped summary. For each repo use this structure:
## repo-name [branch: feature/xyz -> main]
- Status: 3 modified, 1 untracked
- Ahead: 2 commits unpushed
- Behind: 5 commits (needs pull/rebase)
- CI: passing | failing (ci.yml) | in progress
- Action needed: pull, push, commit changes, fix CI
- Summary table at the end: one-line-per-repo showing repo name, branch, dirty/clean, ahead/behind counts, CI status, and action needed.
Rules
- Run
git fetch --quietbefore checking ahead/behind so counts are current. - Run repo checks in parallel where possible (use
&andwaitin bash). - If a directory isn't a valid git repo or has no remote, note it and move on.
- Keep output concise; skip sections that have nothing to report (e.g., don't show "Behind: 0").
- Only show repos with recent activity (last 7 days) to keep the report focused.
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.
- 8d ago First seen · 62 lines · 140 tokens per session scan A deb579f2ef7b
repo-status is a skill published in the GitHub repository urmzd/dotfiles (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 140 tokens to every session and 774 once invoked, about $0.0007 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 skills, from other repositories
create-pr
Rebase from the latest origin/main, squash the commits from it, and then create a PR on github with intelligent commit messages based on staged changes.
scan-commit
Automatically scan the repository for unstaged/untracked changes, group them into logical commits using hunk-level analysis, stage and commit them following Conventional Commits.
smart-commit
Analyze staged changes and split them into multiple logical commits following Conventional Commits.
pr-review
Intelligent PR code review with dynamic agent allocation based on change types. Analyzes PR changes and generates targeted review tasks.
analyze-pr
Analyze a GitHub/GitLab Pull Request by fetching its diff, reading its web description, and generating a comprehensive document. Use when the user provides a PR link and wants to understand what changes the PR introduces, or asks to review/analyze/summarize a pull request.
gen-commit-msg
Generate intelligent commit messages based on staged changes following Conventional Commits format.