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 hermes-coding-workflowgit 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/hermes-coding-workflow)<a href="https://agentmods.dev/skills/aminedjeghri/personal-os-setup/hermes-coding-workflow"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/hermes-coding-workflow/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/hermes-coding-workflow"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/hermes-coding-workflow.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 | $0.00771 |
| Opus 5.5 | $0.00010 | $0.00308 |
| Sonnet 5.5 | $0.00005 | $0.00154 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
hermes-coding-workflow 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 18d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding Workflow — Hermes & Claude Code
Hermes-only orchestration rules for coding tasks: how the Hermes orchestrator plans work, briefs the Claude Code delegate, and verifies the result. Claude Code does not read this skill — it follows each repo's own AGENTS.md / CLAUDE.md.
1. Division of labor
| Task | Agent |
|---|---|
| Home Assistant, Hermes gateway/admin, scheduling (cron), memory, audits, container/system ops | Hermes |
| Every in-repo file change — code, workflows/CI, docs, READMEs, skills, and one-line edits — in any repo the user works on | Claude Code, driven by Hermes via claude -p (or interactive) |
| Reading a repo, writing the spec/plan, reviewing a diff or PR, verifying CI state | Hermes |
Every in-repo edit is delegated — including the small and the mechanical. "It is only one line" or "it is just a YAML tweak" is not a reason to reach for the orchestrating agent's own file tools: the delegate owns the edit, the repo's pre-commit hooks, the commit and the push. Bypassing it skips the delegate's checks and leaves the work without its normal verification trail.
Rules that follow from this:
- Follow-ups stay on the branch that is already open ("same branch as PR #52"): brief the delegate to add a commit there — never a new PR, never a force-push.
- Brief precisely: goal, exact files, the constraints that matter (repo conventions, what NOT to touch, which validation commands to run), and the shape of the answer wanted back.
- Verify the artifact, never the summary. The delegate's report is a self-report: afterwards
check the real thing —
git diff origin/main...origin/<branch>,gh pr checks,gh run list,gh api repos/<owner>/<repo>/actions/runs/<id>/jobs. Only then report success to the user. - Approvals still gate the outward actions (push, PR, merge, force-push) — per action, every time. A delegation does not inherit a previous yes.
Claude Code works inside a repo; it does NOT manage the Hermes agent, the HA gateway or cron. Hermes orchestrates, writes the specs/briefs and reviews.
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.
- 18d ago Changed · +3 lines 5e00be04f3fd
- 27d ago First seen · 48 lines · 25 tokens per session scan A 9ea27364b979
hermes-coding-workflow 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 771 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 2026-09-19.
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.