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 jpd44/mesh44-plugins --skill github-repogit clone --depth 1 https://github.com/jpd44/mesh44-pluginsWrote 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/jpd44/mesh44-plugins/github-repo)<a href="https://agentmods.dev/skills/jpd44/mesh44-plugins/github-repo"><img src="https://agentmods.dev/badge/skills/jpd44/mesh44-plugins/github-repo/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/jpd44/mesh44-plugins/github-repo"><img src="https://agentmods.dev/badge/skills/jpd44/mesh44-plugins/github-repo.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 | $0.00024 | $0.00489 |
| Opus 5.5 | $0.00010 | $0.00196 |
| Sonnet 5.5 | $0.00005 | $0.00098 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
github-repo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/app-kit:github-repo — private repo under the configured org
Load config first
GH_ORG=$(jq -r .github.org ~/.config/mesh44/config.json)
Prereqs
ghCLI installed and authed (gh auth status). If not, tell the user to rungh auth login— don't try to do it for them.- User is a member of
$GH_ORGwith repo-create permission.
Steps
-
Sanity-check there isn't already a repo with this name:
gh repo view $GH_ORG/<app-name> 2>&1 | head -1If it exists, stop and ask the user whether to reuse it or pick a new name. Do not delete.
-
Initial commit in the local repo (created by
new-appscaffold step):cd <app-path> git add . git commit -m "Initial commit from app-kit" -
Create the repo and push:
gh repo create $GH_ORG/<app-name> \ --private \ --source . \ --remote origin \ --description "<app description from user, or leave blank>" \ --push -
Default branch to
main(gh respects local default, but verify):gh repo edit $GH_ORG/<app-name> --default-branch main -
No branch protection by default — the existing repos in this org (e.g.,
daily-deutsch,munichmotoclub) don't use it and adding it would block the CodePipeline auto-merges the user may rely on. If the user wants protection, they'll ask. -
Print the repo URL so the user can visit it.
What NOT to do
- Don't push secrets. Inspect
git statusbefore staging if the local scaffold may have written.envor*.pemfiles. - Don't create a GitHub Actions workflow — deployment runs through CodePipeline, not Actions, in this setup.
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 · 56 lines · 24 tokens per session scan A 48e703753dce
github-repo is a skill published in the GitHub repository jpd44/mesh44-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 489 once invoked, about $0.0001 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.