Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AmineDjeghri/personal-os-setupnpx agentmods add skills/aminedjeghri/personal-os-setup/claude-code-opsWrote 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/claude-code-ops)<a href="https://agentmods.dev/skills/aminedjeghri/personal-os-setup/claude-code-ops"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/claude-code-ops/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/claude-code-ops"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/claude-code-ops.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 | $0.00025 | $0.05039 |
| Opus 5.5 | $0.00010 | $0.02016 |
| Sonnet 5.5 | $0.00005 | $0.01008 |
| Haiku 4.5 | $0.00003 | $0.00504 |
Grade C, and why
claude-code-ops scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
2. `npm install -g @anthropic-ai/claude-code` → wiped on addon update. Native installer only (`curl -fsSL https://claude.ai/install.sh | bash`). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. `npm install -g @anthropic-ai/claude-code` → wiped on addon update. Native installer only (`curl -fsSL https://claude.ai/install.sh | bash`). How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Ops (this box)
When to Use
- Installing, upgrading, or re-authenticating Claude Code on this machine (Hermes HA addon).
- A
claudecommand fails with "command not found", auth is lost, ordoctorreports issues. - Any session that needs to verify the Claude Code install (version / auth / health) before delegating work to it.
Companion to the bundled claude-code skill: delegation workflows (print mode, tmux, flags, hooks) live there; INSTALL / AUTH / UPDATE operations for THIS machine live here.
Model defaults (cost rule — user's standing instruction, 2026-09-28)
-
Model = the newest Sonnet, always explicit:
--model claude-sonnet-5-5(or the alias--model sonnet, same family). The user's words: "use Claude 5.5 sonnet per default … don't use opus because it is very expensive". -
Never
--model opus, any version. The bundledclaude-codeskill's "--model opusfor complex multi-step work" line is superseded here — buy reasoning with--effort high|xhigh, not with a pricier model.--model haikuis fine only for a trivial 1-turn task and as--fallback-model haiku. -
Pass
--modelon every run instead of relying on the account default, so a config/subscription change can never silently swap in an expensive model. -
The newest Sonnet id only appears after
claude update. Verified 2026-09-28: Claude Code 2.1.248 topped out atclaude-sonnet-5; updating to 2.1.284 addedclaude-sonnet-5-5. So when the user names a model you cannot find, update first, then re-check the binary:HOME=/config /config/.local/bin/claude update grep -aoE 'claude-(sonnet|opus|fable)-[0-9][a-z0-9.-]*' \ $(readlink -f /config/.local/bin/claude) | sort -u | tail -
Re-link relative after every update. The updater rewrites
~/.local/bin/claudeas an ABSOLUTE symlink (/config/.local/share/claude/versions/<ver>); pitfall 10 wants the relative form:cd ~/.local/bin && ln -sfn ../share/claude/versions/<ver> claude && HOME=/config ./claude --version.
What ships with it
2 files 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 · +56 lines · +7 tokens per session 8109312c1b8b
- 18d ago Changed · +47 lines 951acceaadf5
- 27d ago First seen · 122 lines · 18 tokens per session scan C 1e9c625579ae
claude-code-ops is a skill published in the GitHub repository AmineDjeghri/personal-os-setup (654 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 5,039 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.
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…
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.
wsl-bash-crlf-or-tempfile
When a Windows shell (PowerShell/cmd) feeds a bash script into WSL, CRLF line endings can corrupt the first shell builtin; force LF or pipe via a temp file.
wsl-networking-mode-dns-fallback
When WSL's mirrored networking fails and falls back to "None", plus /etc/wsl.conf has generateResolvConf=false, the distro has no DNS; fix both layers.