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 chipi/agentic-ai-homelab --skill shipgit clone --depth 1 https://github.com/chipi/agentic-ai-homelabWrote 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/chipi/agentic-ai-homelab/ship)<a href="https://agentmods.dev/skills/chipi/agentic-ai-homelab/ship"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/ship/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/chipi/agentic-ai-homelab/ship"><img src="https://agentmods.dev/badge/skills/chipi/agentic-ai-homelab/ship.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 | $0.00115 | $0.01060 |
| Opus 5.5 | $0.00046 | $0.00424 |
| Sonnet 5.5 | $0.00023 | $0.00212 |
| Haiku 4.5 | $0.00012 | $0.00106 |
Grade A, and why
ship 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 17d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ship
The disciplined path from "work is done" to "pushed and green", so nothing lands unrebased, unvalidated, unapproved or unwatched. A push is shared state and needs the operator's approval (below: per push, or for an arc when the operator grants it that way).
Pick the path
| Path | When |
|---|---|
| A. Feature branch + PR | the default; anything that wants review; any repo without a trunk-based habit |
| B. Direct to main | a repo that works trunk-based and the operator has said so for this kind of change: a small fix, a red main after a merge, a doc fix, or an arc where the operator said "push everything when done" |
Path B is never self-granted. Without the operator's word for this repo and arc, use A.
Steps (both paths)
- Branch check.
- A: on a feature branch, never
main; confirm what it is ahead of. - B: confirm the local commits about to land (
git log origin/main..HEAD), and that nothing unrelated rides along.
- A: on a feature branch, never
- Secrets. Run
~/.claude/skills/secrets-scan/scripts/scan.sh --push(thesecrets-scanskill) over what the push sends.SECRETS SCAN: FAILblocks the push. - Rebase onto the trunk.
git fetch origin main && git rebase origin/main. Resolve conflicts; never leave a merge commit. Every push, not just the first. If the rebase pulled in code (not only docs) that touches what you changed, re-run the affected gates. - Run the right gates, not the heaviest. Run the validation that covers the change:
docs-preflightfor docs, the repo's own gate target, the specific tests. Reproduce green locally; don't push and let CI find it. End each gate with an unambiguous PASS/FAIL, quoted in the report. - Show what ships.
git status, plusgit --no-pager diff origin/main...HEAD --stat, plus the commit log about to land. Summarize it. - Approval.
- Per push by default: wait for "push" / "ship it" / "go". Approval for a previous push does not carry to this one.
- Per arc only when the operator granted it that way ("push everything when done", "stop asking me per commit"). That covers this arc's pushes, never the next arc's. Never ask per commit inside it.
- Push.
- A:
git push --force-with-leaseif the branch is already on the remote, elsegit push -u origin <branch>. PRs default to ready, not draft, unless asked otherwise. - B:
git push origin HEAD:main. If it is rejected because main moved, fetch, rebase and re-check step 3; never force main.
- A:
- Watch what you pushed. Load
ci-watchand run it on the pushed SHA under the Monitor tool, re-arming on expiry until it prints a verdict.VERDICT RED: read the tail it printed and fix the cause now. Red main is yours to fix first.INCOMPLETEwithNOT RUN — cancelled: your checks did not run. Watch the commit that superseded them instead (it contains yours), or wait and re-run; never report it as green.- The order rule: don't push a docs-only commit while your fix's run is still pending, or that run is cancelled before it starts.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 17d ago Changed · +27 lines · +34 tokens per session dbde18bf8f92
- 2mo ago First seen · 38 lines · 81 tokens per session scan A 62d5320c0457
ship is a skill published in the GitHub repository chipi/agentic-ai-homelab (3 stars, last pushed today), licensed MIT. It adds 115 tokens to every session and 1,060 once invoked, about $0.0005 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
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…