ergopti: Skill for Claude Code

.agents/skills/commit-and-push/SKILL.md

commit-and-push is a skill for Claude Code, Codex from adrienm7/ergopti. It costs 28 tokens per session (1,006 once invoked), scanned A, original, MIT.

A repository policy for creating commits, pushing branches, and monitoring CI, the automated checks that run after code changes. It distinguishes local commits from pushes that can trigger releases.

In plain words
What is it for?
Use it before committing or pushing, especially on release branches, to decide when approval is required and how local commits should remain organised.
Why use it?
It prevents unauthorised releases, accidental history changes, and unnecessary CI runs while preserving the intended commit structure.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is adrienm7/ergopti's own configuration. It tells Claude Code and Codex how to work on ergopti itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ergopti configures →

Reuse

Borrowing it

Nothing to install: this file belongs to adrienm7/ergopti. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/adrienm7/ergopti/main/.agents/skills/commit-and-push/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/adrienm7/ergopti

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.

agentmods badge for commit-and-push

README.md
[![agentmods](https://agentmods.dev/badge/skills/adrienm7/ergopti/commit-and-push/github.svg)](https://agentmods.dev/skills/adrienm7/ergopti/commit-and-push)
Your own site
<a href="https://agentmods.dev/skills/adrienm7/ergopti/commit-and-push"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/commit-and-push/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.

agentmods 80×15 button for commit-and-push

Your own site · 80×15
<a href="https://agentmods.dev/skills/adrienm7/ergopti/commit-and-push"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/commit-and-push.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,006 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.01006
Opus 5.5 $0.00011 $0.00402
Sonnet 5.5 $0.00006 $0.00201
Haiku 4.5 $0.00003 $0.00101

Measured 8d ago against content hash 51a5c7c3aaf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

commit-and-push 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 8d 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.

.agents/skills/commit-and-push/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit and push discipline

The rule that matters most

dev and main are release branches. Every push to either one triggers CI and cuts a release. Pushing without being asked pollutes the release history and burns CI minutes.

  • Commit freely, without asking. Local commits are free and reversible.
  • Never squash commits without explicit user authorization in the current conversation. A request to merge, integrate, land, finish, or keep history linear does not authorize squashing. Preserve the atomic commits by default.
  • Push to dev or main only when the user explicitly asks in the current conversation — "push", "tu peux pusher", "merge".
  • Approval does not carry over. Authorization given for one push covers that push only; the next one needs a new ask.
  • Do not infer approval from: a green test suite, a finished fix, a request to "continue", or an earlier instruction to work autonomously. Autonomy covers the work, never the release.
  • Leaving several commits stacked locally is the normal, expected end state. Say so plainly: "N commits waiting locally, nothing pushed."

Feature/fix branches that are not dev or main can be pushed freely.

Commit format

Conventional Commits, English, imperative, lowercase, no trailing period, ≤ 72 chars.

<type>(<scope>): <short imperative description>

<body — explain WHY, not WHAT; wrap at 72>

Types: feat fix perf refactor style docs test chore. Breaking change: feat!: plus an explanation in the body.

  • One commit per fix. Do not batch unrelated fixes; each must be revertable alone.
  • The body is for motivation and root cause — the diff already shows the what.

Forcing the next stable version

A push to main numbers its tag from the subjects since the last stable tag: feat bumps the minor, !: or BREAKING: the major, anything else the patch. When the maintainer asks for a specific version, add this line on its own in a commit message after the last stable tag (the newest such commit wins):

Read the full file on GitHub · 97 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.

  1. 8d ago Changed · +17 lines 51a5c7c3aaf2
  2. 15d ago First seen · 80 lines · 28 tokens per session scan A 7714c986d753

Subscribe to this mod's changes

commit-and-push is a skill published in the GitHub repository adrienm7/ergopti (14 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 1,006 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 2026-10-14.

Related

Other skills, from other repositories