repo-of-repos: Skill for Claude Code

.agents/skills/commit-all-repos/SKILL.md

commit-all-repos is a skill for Claude Code from raffertyuy/repo-of-repos. It costs 32 tokens per session (581 once invoked), scanned A, original, MIT.

A repository maintenance tool that goes through Git repositories inside `repos/`, then the main repository, to stage, commit, and push their changes.

In plain words
What is it for?
Use it to review changes, follow each repository’s instructions and commit style, and publish updates for all Git sub-repositories and the master repository.
Why use it?
It avoids repeating the same Git checks and commit steps for every repository in a multi-repository project.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions CLAUDE.md; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is raffertyuy/repo-of-repos's own configuration. It tells Claude Code how to work on repo-of-repos itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything repo-of-repos configures →

Reuse

Borrowing it

Nothing to install: this file belongs to raffertyuy/repo-of-repos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/raffertyuy/repo-of-repos/main/.agents/skills/commit-all-repos/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/raffertyuy/repo-of-repos

Made for: Claude Code.

Wrote 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.

agentmods badge for commit-all-repos

README.md
[![agentmods](https://agentmods.dev/badge/skills/raffertyuy/repo-of-repos/commit-all-repos/github.svg)](https://agentmods.dev/skills/raffertyuy/repo-of-repos/commit-all-repos)
Your own site
<a href="https://agentmods.dev/skills/raffertyuy/repo-of-repos/commit-all-repos"><img src="https://agentmods.dev/badge/skills/raffertyuy/repo-of-repos/commit-all-repos/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.

agentmods 80×15 button for commit-all-repos

Your own site · 80×15
<a href="https://agentmods.dev/skills/raffertyuy/repo-of-repos/commit-all-repos"><img src="https://agentmods.dev/badge/skills/raffertyuy/repo-of-repos/commit-all-repos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 581 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00581
Opus 5 $0.00016 $0.00291
Sonnet 5 $0.00006 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured 12d ago against content hash 54890317c0ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

commit-all-repos 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 12d 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.

.agents/skills/commit-all-repos/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit All Repos

Iterate through every sub-repo in repos/ and stage, commit, and push changes in each one individually, then do the same for the master repo last.

Order of Operations

  1. Sub-repos first — iterate through each directory in repos/*/ that is a git repository
  2. Master repo last — commit root-level changes after all sub-repos are done

For Each Sub-Repo

For each directory under repos/<name>/ that is a git repository (has a .git directory):

Note: Skip type: local entries from repos/repos.yaml — local source folders have no git history of their own. Their changes are committed via the root repo's /commit skill.

  1. cd into the repo directory
  2. Run git status (never use -uall) — if no changes, skip it
  3. Run git diff to review what changed
  4. Run git log --oneline -5 to match that repo's commit message style
  5. Read the sub-repo's agentic instructions if they exist (in priority order):
    • CLAUDE.md in the sub-repo root
    • AGENTS.md in the sub-repo root
    • .github/copilot-instructions.md in the sub-repo
    • These instructions take precedence over root-level instructions for that repo's commit
  6. Follow the sub-repo's commit message guidelines if they define any; otherwise fall back to the root .claude/prompt-snippets/commit-message.md
  7. Stage relevant files using explicit paths — never git add -A
  8. Create the commit
  9. Run git push to push the commit to the remote
  10. Run git status to verify

For the Master Repo

After all sub-repos are committed:

  1. Run the /commit skill for the root workspace (which excludes repos/)
  2. If there are no root-level changes, skip — don't create an empty commit

Notes

  • Report a summary at the end: which repos had commits, which were skipped (clean), and any errors
  • If a sub-repo has no changes, skip it silently — don't create empty commits
  • If a pre-commit hook fails in a sub-repo, report the error and continue to the next repo
  • Never force-push or amend existing commits in sub-repos

Read the full file on GitHub · 51 lines

Changes

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.

  1. 12d ago First seen · 51 lines · 32 tokens per session scan A 54890317c0ce

Subscribe to this mod's changes

commit-all-repos is a skill published in the GitHub repository raffertyuy/repo-of-repos (12 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 581 once invoked, about $0.0002 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.