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 AmineDjeghri/personal-os-setup --skill template-adoptiongit clone --depth 1 https://github.com/AmineDjeghri/personal-os-setupWrote 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/aminedjeghri/personal-os-setup/template-adoption)<a href="https://agentmods.dev/skills/aminedjeghri/personal-os-setup/template-adoption"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/template-adoption/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/aminedjeghri/personal-os-setup/template-adoption"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/template-adoption.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 | $0.00029 | $0.02251 |
| Opus 5.5 | $0.00012 | $0.00900 |
| Sonnet 5.5 | $0.00006 | $0.00450 |
| Haiku 4.5 | $0.00003 | $0.00225 |
Grade A, and why
template-adoption 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 6d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
House templates — start a new project, or align an existing repo
0. Starting a NEW project — pick a template
Never start from an empty repo. Fork the template matching the project type — all three already ship CI/CD, a GitHub Pages docs site, pre-commit and release tooling, so you replace content, not plumbing.
| Build target | Fork | Stack / notes |
|---|---|---|
| Python package / library | python-package-template | uv-based package, tests, pre-commit, semantic-release |
| Generative-AI project, or full-stack (backend + frontend) | generative-ai-project-template | FastAPI + NiceGUI; litellm/ollama (cloud + local LLMs); langfuse observability |
| Home Assistant addon | ha-addons (octo-fiesta pattern: per-addon config.yaml/Dockerfile/run.sh, HA Store release flow) — or fork it as the base for your own addon collection |
- Match the type first (package vs gen-ai/full-stack vs addon) — don't retrofit a template.
- Fork, don't clone — keep the upstream link so template improvements can be pulled in later.
- After forking, make the repo self-describing: add
AGENTS.md/CLAUDE.md+.claude/skills/(seecoding-workflow§ 5) so any agent works in it correctly from day one. - Rebrand/rename the package per the template's own README before first use.
- An existing repo that should match a template → the rest of this skill.
Aligning an existing repo with a template
The deliverable is a verified gap matrix, the user's decisions, then the committed change.
1. Establish the facts before proposing anything
- Enumerate every candidate ref before comparing.
git branch -r,gh pr list --state all, and the root tree of each branch (git ls-tree -r --name-only <ref>). A branch whose name says nothing about the template can still carry the ported files; the branch that looks like the port can be stale. - Compare file sets, not file names — and strip CR when either side may be CRLF:
diff <(git show <ref>:$f | tr -d '\r') <(git -C $TPL show HEAD:$f). Byte identity (md5sum) is false the moment one side is CRLF: files can differ on every line and still be content-identical. Never repeat "already ported, byte-identical" until you know which claim is true. - Check the port branch's position against its base first:
git rev-list --left-right --count origin/main...HEAD. A long-lived port branch is usually many commits behind and will not merge at all — that is the headline finding, ahead of any further adoption work. - Dry-run the merges without touching the working tree:
GIT_OBJECT_DIRECTORY=$(mktemp -d) GIT_ALTERNATE_OBJECT_DIRECTORIES=<repo>/.git/objects git merge-tree --write-tree --name-only --messages <A> <B>. Run it for the base branch and for every other open branch, and report the conflict sets as measured. - Verify the template's own files. A file lifted from a template can be stale, wrong, or not from the
template at all (confirm each candidate exists in the template today), and its contact details, emails and
URLs are the template author's — adapt them, never copy them verbatim. The user's privacy rule applies: no
real address, domain or tunnel placeholder in a repo; when the user asks for a placeholder rather than a real
contact, use an obvious
*@example.invalidplus a TODO comment. - Report a gap matrix, not a narrative. One row per item: name, present on each side, how it differs with the command behind the claim, action (adopt / adapt / skip) and WHY. Group the rows so the user can scan them.
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.
- 6d ago First seen · 117 lines · 29 tokens per session scan A b53582827a0d
template-adoption is a skill published in the GitHub repository AmineDjeghri/personal-os-setup (662 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 2,251 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 2026-10-20.
Other skills, from other repositories
hula-skill
HuLa project skill for frontend (Vue 3 + Vite + UnoCSS + Naive UI/Vant), backend (Tauri v2 + Rust + SeaORM/SQLite), full-stack flows, and build/release work. Use when the user mentions hula or HuLa or requests changes in this repository; after triggering, ask which scope (frontend/backend/fullstack/build-release) to…
audit-check
Audit AEGIS repository health or readiness for a push or release, using current CI checks, derived counts and source-backed documentation checks.
ci-monitor
Check AEGIS CI for a specific PR or commit. Also handle recurring CI monitoring or repository metrics when the user requests them.
flow-launcher
Build Flow Launcher plugins with C# or Python JSON-RPC, configure plugin manifests, and integrate Everything search.
microsoft-powertoys
Configure PowerToys FancyZones, Run, Keyboard Manager, and Awake; automate settings and troubleshoot Windows utility behavior.
eartrumpet
Inspect and route per-application audio with EarTrumpet, WASAPI, and pycaw; troubleshoot audio sessions and output devices.