What is coding-workflow?

A shared set of rules for coding tasks across multiple repositories. It assigns work between Hermes and Claude Code, requires a plan and approval before changes, and defines review and pull-request steps.

It helps start coding tasks, inspect repository instructions, plan changes, delegate work, review edits, and prepare repository-specific pull requests.

It prevents agents from editing the wrong place, acting without approval, or skipping important review and repository procedures.

coding-workflow — Skill for Claude Code and Codex by AmineDjeghri

Install

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.

Any agent

npx skills add AmineDjeghri/personal-os-setup --skill coding-workflow

Clone the repo

git clone --depth 1 https://github.com/AmineDjeghri/personal-os-setup

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/coding-workflow/github.svg)](https://agentmods.dev/skills/aminedjeghri/personal-os-setup/coding-workflow)

Your own site

<a href="https://agentmods.dev/skills/aminedjeghri/personal-os-setup/coding-workflow"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aminedjeghri/personal-os-setup/coding-workflow"><img src="https://agentmods.dev/badge/skills/aminedjeghri/personal-os-setup/coding-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 655 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00046	$0.00655
Opus 5	$0.00023	$0.00328
Sonnet 5	$0.00009	$0.00131
Haiku 4.5	$0.00005	$0.00065

Measured today against content hash d6e2fd22ca95, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 today.

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.

src/personal_os_setup/config/chezmoi/dot_claude/skills/coding-workflow/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coding Workflow — Hermes & Claude Code

Shared workflow rules for coding tasks. Both agents read this skill; rules are agent-agnostic (terminal/git/gh only).

1. Division of labor

Task	Agent
Home Assistant, Hermes gateway/admin, scheduling (cron), memory, audits, container/system ops	Hermes
In-repo code changes, features, bugfixes, PRs (in any repo the user works on)	Claude Code (Hermes delegates via `claude -p` or interactive)
Repo docs (docs/, README, skills)	Either — follow repo-conventions

Hermes orchestrates and can delegate coding to Claude Code. Claude Code works inside a repo; it does NOT manage the Hermes agent, HA gateway, or cron.

2. Plan first (MANDATORY)

Never jump straight into editing. For anything non-trivial:

Restate the goal and constraints in your own words.
Read the repo's AGENTS.md/CLAUDE.md and .claude/skills/; explore the relevant files.
Write the plan (files to touch, approach, test strategy) and get explicit user approval before mutating.
If the user says "grill me" / "stress-test this" — interview them about the plan branch by branch until the design tree is resolved.

3. Confirm before mutating (MANDATORY)

Per-action approval for: system changes, git push, opening PRs, anything destructive.
A prior "yes" is not standing approval — re-confirm scope.
Prefer approval-free git ops: regular push, new commit, merge over rebase; no force-push without explicit approval.

4. Review

Run the repo's own checks before any PR: its make test/make pre-commit where defined, or the CI-equivalent.
Verify git identity before committing (wrong email = phantom PR participants — see repo-conventions).
Review your own diff before pushing; for PRs, diff against the base branch.

5. Per-repo PR flows

Load repo-conventions and follow the row for that repo. Default when unsure: branch from the default branch, conventional commit, squash-merge PR with a conventional title.

Read the full file on GitHub · 48 lines

Changes

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.

today First seen · 48 lines · 46 tokens per session scan A d6e2fd22ca95

Subscribe to this mod's changes

coding-workflow is a skill published in the GitHub repository AmineDjeghri/personal-os-setup (602 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 655 once invoked, about $0.0002 per session on Opus 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 2026-09-08.

Git and workflow Planning apps windows windows-11 windows11 wsl wsl2

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…

HuLaSpark/HuLa · 86 tokens

coding-workflow

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Coding Workflow — Hermes & Claude Code

1. Division of labor

2. Plan first (MANDATORY)

3. Confirm before mutating (MANDATORY)

4. Review

5. Per-repo PR flows

What this file has done since we first saw it

Other skills, from other repositories

hula-skill

commit-push-pr

microsoft-powertoys

eartrumpet

flow-launcher

release-helper