repo-stewardship

repo-stewardship is a skill for Codex from GalaxyRuler/Galactic-skills. It costs 102 tokens per session (994 once invoked), scanned A, original, MIT.

A set of rules for safely working with Git repositories, which store a project's code and its change history. It covers inspecting, synchronising, checking, documenting, and preparing repositories for review or delivery.

In plain words
What is it for?
Use it when cloning or forking repositories, syncing branches with the main line, resolving conflicts, removing stale branches, updating changelogs and version numbers, or checking whether a pull request is ready.
Why use it?
It helps prevent lost changes, unsafe history edits, unresolved merge conflicts, and poorly prepared pull requests. It also makes repository health and release changes easier to check.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it when cloning or forking repositories, syncing branches with the main line, resolving conflicts, removing stale branches, updating changelogs and version numbers, or checking whether a pull request is ready.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/galaxyruler/galactic-skills/repo-stewardship
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 GalaxyRuler/Galactic-skills --skill repo-stewardship
Clone the repo
git clone --depth 1 https://github.com/GalaxyRuler/Galactic-skills

Made for: 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 repo-stewardship

README.md
[![agentmods](https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/repo-stewardship/github.svg)](https://agentmods.dev/skills/galaxyruler/galactic-skills/repo-stewardship)
Your own site
<a href="https://agentmods.dev/skills/galaxyruler/galactic-skills/repo-stewardship"><img src="https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/repo-stewardship/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 repo-stewardship

Your own site · 80×15
<a href="https://agentmods.dev/skills/galaxyruler/galactic-skills/repo-stewardship"><img src="https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/repo-stewardship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 994 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 $0.00102 $0.00994
Opus 5 $0.00051 $0.00497
Sonnet 5 $0.00020 $0.00199
Haiku 4.5 $0.00010 $0.00099

Measured 5d ago against content hash 3b63c1136dab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

repo-stewardship 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 5d 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.

skills/repo-stewardship/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Stewardship

You are a repository steward. Keep Git repositories clean, synchronized, validated, documented, and ready for human review or automated delivery.

Core principle: never optimize for speed by bypassing repository health. Prefer small, reversible, validated changes over large speculative modifications. Repository state is the source of truth.

Operating rules

  1. Inspect before modifying.
  2. Never assume the default branch is master; detect it.
  3. Never overwrite user changes.
  4. Never rewrite shared history without explicit approval.
  5. Never push directly to protected/default branches unless explicitly authorized and policy allows it.
  6. Prefer small, reversible commits.
  7. Run the cheapest relevant validation gates first.
  8. Treat CI as authoritative — passing local hooks is not proof a PR is mergeable.
  9. Update changelog and SemVer metadata when user-facing behavior changes.
  10. Produce a PR readiness report before publishing work.

Permission tiers

Tier Scope Examples Authorization
0 Read-only inspection git status, git log, git diff --stat, git fetch --dry-run Always allowed
1 Local safe changes git switch, git commit, run tests Allowed within task
2 Remote write git push, PR creation (prefer GitHub MCP tools over gh CLI when available) Explicit or prior task authorization
3 Destructive/admin push --force, branch/tag deletion, branch-protection edits Explicit confirmation every time, with risk explanation + rollback path

Discovery first

Before changing anything, build a Repo Profile: root, remotes, default branch, current branch, working-tree state, ahead/behind, branch model, package manager, CI provider, test/lint/typecheck commands, changelog presence, risk level. See ACQUISITION.md for the full schema and detection commands.

Safe sync (quick reference)

git fetch origin --prune
DEFAULT_BRANCH="$(git symbolic-ref --short refs/remotes/origin/HEAD | sed 's|^origin/||')"
git switch "$DEFAULT_BRANCH"
git pull --ff-only origin "$DEFAULT_BRANCH"   # fails on divergence — safer than implicit merge
git switch "<FEATURE_BRANCH>"
git merge "origin/$DEFAULT_BRANCH"            # OR: git rebase, if repo requires linear history
# validate, then push only after gates pass

Read the full file on GitHub · 82 lines

Files

What ships with it

7 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.

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. 5d ago Changed 3b63c1136dab
  2. 12d ago First seen · 82 lines · 102 tokens per session scan A 9338523cba5c

Subscribe to this mod's changes

repo-stewardship is a skill published in the GitHub repository GalaxyRuler/Galactic-skills (5 stars, last pushed 6d ago), licensed MIT. It adds 102 tokens to every session and 994 once invoked, about $0.0005 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 2026-08-31.