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 agentmods add skills/evoelsewhere/evoflux/coding-git-workflownpx skills add evoelsewhere/evoflux --skill coding-git-workflowgit clone --depth 1 https://github.com/evoelsewhere/evofluxWrote 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/evoelsewhere/evoflux/coding-git-workflow)<a href="https://agentmods.dev/skills/evoelsewhere/evoflux/coding-git-workflow"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/coding-git-workflow.svg" alt="Measured on agentmods" 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 | $0.00083 | $0.00984 |
| Opus 5 | $0.00042 | $0.00492 |
| Sonnet 5 | $0.00017 | $0.00197 |
| Haiku 4.5 | $0.00008 | $0.00098 |
Grade A, and why
coding-git-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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structure commits, branches, and PR submission
Prefer many small, independently reviewable, working commits over one large branch held open. Do not load bundled references when this skill activates.
Choose commit granularity
- Commit at each point the working tree passes its narrow check — that state is a save point you could safely reset back to, not a checkpoint to defer. Do not batch unrelated changes into one commit; do not split one logical change across commits that each leave the tree broken.
- Prefer several small, focused commits over one broad commit when the change spans independent concerns; do not force multiple commits onto a change that is genuinely small and cohesive.
- Write the commit message as a statement about behavior, not a diary of edits: state what changed and why, not "fix stuff" or a restated diff.
- Read references/commit-and-release-discipline.md for atomic-commit criteria, branch-lifetime guidance, and versioning as a consumer promise.
Execute one commit
- Stage. Run
git status --porcelain. Review it — and the content of any unfamiliar or sensitive-looking file — before staging; do notgit adda credential, key, or unrelated in-progress file. Stage only the files that belong to this logical change. - Analyze. Run
git diff --cachedto assess technical scope and architectural impact — a boundary, schema, or public-contract shift documented underdocuments/architecture/ordocuments/reference/, not only the literal lines changed. - Reconcile docs where the change requires it. Update the specific documented contract the diff touches (a feature page, an architecture boundary, a reference page) when accepted behavior shipped; do not blanket-sync unrelated documentation on every commit.
- Generate the message.
- Format:
<type>: <subject>— see the type table below. - Subject: a concise imperative summary of the staged diff.
- Body: a blank line, then Motivation, a bulleted Technical Changes deep dive, and Impact (what a consumer or operator would observe).
- Format:
- Commit. Run
git commit -m "<message>"and report the resulting commit hash with a brief summary. Never use--no-verifyor bypass a commit hook to force a commit through.
What ships with it
3 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.
- today First seen · 90 lines · 83 tokens per session scan A 4b319eb68dd5
coding-git-workflow is a skill published in the GitHub repository evoelsewhere/evoflux (7 stars, last pushed today), licensed Apache-2.0. It adds 83 tokens to every session and 984 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
heartbeat
Periodic heartbeat check that reads HEARTBEAT.md from the workspace and executes any tasks listed there. Use for autonomous background monitoring, periodic maintenance, and proactive task execution. Triggered by a cron schedule.
yutori-computer-use
Run local Mac desktop tasks with Yutori computer use. Use when the user wants to operate macOS apps, websites in a local browser, or cross-app workflows on the visible desktop, or to drive one app's window in the background while they keep working.
jobs
Create and manage scheduled jobs (cron tasks, reminders, heartbeat checks, polling watchers) that vixd runs automatically. Use when the user asks to schedule, automate, monitor, watch, or be reminded about something.
expertise-exchange
Team expertise billboard via adept exchange: ask teammates for expertise and stack responses. Apply when the user wants a colleague's input, mentions the exchange, or when you start using adept — sample open requests and offer to answer ones the user knows about.
ponytail
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports…
pre-post-hooks
Guide for configuring PreToolUse, PostToolUse, and Stop hooks in Claude Code. Use when the user asks about hooks, wants to run commands before/after tool calls, needs auto-formatting, auto-linting, validation gates, or mentions settings.json hook config.