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 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/coding-workflow)<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.
<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>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 | $0.00049 | $0.01332 |
| Opus 5.5 | $0.00020 | $0.00533 |
| Sonnet 5.5 | $0.00010 | $0.00266 |
| Haiku 4.5 | $0.00005 | $0.00133 |
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 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding workflow (any repo, any coding agent)
Applies to every repo the user works on. The repo's own rules win: read AGENTS.md / CLAUDE.md /
CONTRIBUTING.md and its .claude/skills/ before touching anything.
1. Plan first
For anything non-trivial: restate the goal and the constraints, name the files you will touch and the test/validation strategy, and get an explicit go-ahead before mutating. If asked to be grilled, resolve the design branch by branch until nothing is left open.
2. Confirm before mutating
- Per-action approval for
git commitandgit push, system changes (package installs,chezmoi apply, driver/VM/WSL work,sudo), destructive commands, opening/merging a PR and release actions. - A previous "yes", a plan, a task description or "implement this" is NOT standing approval — ask again, every time, and run exactly what was approved. Commit and push are separate approvals: a yes to one is not a yes to the other. When the repo's own rules say nothing about committing, ask before the FIRST commit of a task. A delegated brief must never pre-authorise a commit the user did not approve for that task.
- Never fold
git commit/git pushinto a compound command — the gate becomes the scanner, not the user. Ask in chat, wait for the yes, run the git action as its own command. - Never bypass a tool's own confirmation dialog.
3. Work in reviewable steps
- One concern per change; keep diffs small enough to read.
- Run the repo's own gates before proposing a PR: its
make test/make pre-commit(or the documented CI-equivalent) — a local pass is the only signal before CI. - Review your own diff against the base branch before pushing.
- Never commit secrets; follow the repo's convention for suppression (inline allowlist comments, never whole-file excludes).
4. Open the PR, then verify
- Branch from the repo's base branch (
mainunless the repo says otherwise); conventional commit and PR title — most repos squash-merge, so the PR title becomes the released commit message. - Verify the real artifact, not the summary: the diff, the CI run status, the PR state.
What ships with it
1 file 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.
- 6d ago Changed · +28 lines · +24 tokens per session 0f99f2fa57e2
- 22d ago Changed · +4 lines 0ac308796908
- 27d ago Changed · +3 lines 8e8d2e3ddd4a
- 28d ago Changed · +3 lines 9971bf1be8f0
- 1mo ago Changed · -2 lines · -21 tokens per session 4e1c35ca2b25
- 1mo ago First seen · 48 lines · 46 tokens per session scan A d6e2fd22ca95
coding-workflow is a skill published in the GitHub repository AmineDjeghri/personal-os-setup (662 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 1,332 once invoked, about $0.0002 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 2026-09-08.
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…
pr-monitor
Read and triage AEGIS pull requests, review contributor changes, or monitor a specified PR when requested.
ship
Complete an explicitly requested AEGIS PR/merge or deployment workflow. Use commit-and-track for a commit-and-push-only request.
commit-and-track
Commit and push a completed AEGIS change when requested or already authorized as part of the active task. Preserve unrelated work and stage only task files.
github-auth
GitHub auth setup via gh CLI, SSH keys, HTTPS PATs.
github-pr-workflow
Pull request lifecycle: create, review, merge, manage (gh CLI).