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 agent-skills-architecturegit 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/agent-skills-architecture)<a href="https://agentmods.dev/skills/aminedjeghri/personal-os-setup/agent-skills-architecture"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/agent-skills-architecture/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/agent-skills-architecture"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/agent-skills-architecture.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 | $0.06744 |
| Opus 5.5 | $0.00010 | $0.02698 |
| Sonnet 5.5 | $0.00005 | $0.01349 |
| Haiku 4.5 | $0.00003 | $0.00674 |
Grade B, and why
agent-skills-architecture scanned grade B with 1 finding 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Destructive cleanup (`rm -rf`, `git clean -f`, a `tar` into a protected path) raises its OWN approval prompt, and a Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent skills & plugins — architecture, deployment, installation, audit, port, retire
How this user's agent skills and plugins are organized across Hermes and Claude Code: how to deploy,
vendor or install them, and how to audit, port live-only skills into git, or retire them. Canonical
governance text: personal-os-setup AGENTS.md § "Skills & plugins — 2-track governance". Verifying
what a configured dir actually LOADS → hermes-instance-audit.
When to use
- Deploying, vendoring, promoting or installing a skill; "where does this skill belong?"
- Installing a Claude Code plugin, or a vendor bundle that ships skills (and MCP) for one or both agents
- "Why doesn't the agent see skill X" — the wiring side (diagnose with
hermes-instance-audit) - "Too many skills — which can I delete?" · "list my skills with their origin" · "find me skills I'm missing"
- Porting a live-only skill into git, or reviewing a rewrite the user pushed
- Repo-local runbooks, AGENTS.md vs CLAUDE.md layout questions
- Not for: auditing an install's config/plugins/curator behaviour, or a repo's own
skills-link/skills-checkflow (hermes-instance-audit,skill-layout).
The zones
| Zone | Path | Read by |
|---|---|---|
| Hermes own store | /config/.hermes/skills/ |
Hermes only |
| Hermes-only — SOURCE (repo = truth) | personal-os-setup/src/personal_os_setup/config/chezmoi/dot_hermes/skills/<category>/<skill>/ |
Hermes only, via make skills-deploy |
| Shared general — SOURCE (repo = truth) | personal-os-setup/src/personal_os_setup/config/chezmoi/dot_claude/skills/ |
both agents, via deployment |
| Shared general — DEPLOYED | /config/.claude/skills/ (chezmoi target; HOME=/config) |
Claude Code (global) + Hermes external_dirs |
| Repo-specific | <repo>/.claude/skills/ + .agents/skills/ git symlinks |
Claude Code in that repo; Hermes only from a session rooted there or via external_dirs |
| Track 2 (not skill files) | ~/.claude/plugins/, $HERMES_HOME/mcp-tokens/ |
Claude plugins; Hermes MCP servers |
What ships with it
11 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.
- references/audit-and-origin-inventory.md 4.3 KB
- references/chezmoi-dot-claude-deployment.md 3.3 KB
- references/community-skills-npx.md 6.7 KB
- references/deploy-drift-and-reconciliation.md 3.4 KB
- references/install-and-track-procedures.md 4.0 KB
- references/platform-lifecycle-and-gates.md 6.2 KB
- references/repo-hook-gate.md 2.5 KB
- references/reviewing-a-rewrite.md 5.0 KB
- references/sanitizing-skills-for-public-repos.md 7.1 KB
- references/store-writers-curator-and-pins.md 5.0 KB
- scripts/review-drift.py 4.3 KB runs code
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 · -114 lines ec410a729eea
- 18d ago Changed · +200 lines · +8 tokens per session scan A → B 5d4f7c3a47f9
- 27d ago First seen · 251 lines · 17 tokens per session scan A 7ec5fa46b032
agent-skills-architecture 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 6,744 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (recursive force delete). 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.