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 GalaxyRuler/Galactic-skills --skill repo-stewardshipgit clone --depth 1 https://github.com/GalaxyRuler/Galactic-skillsWrote 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/galaxyruler/galactic-skills/repo-stewardship)<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.
<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>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 | $0.00102 | $0.00994 |
| Opus 5 | $0.00051 | $0.00497 |
| Sonnet 5 | $0.00020 | $0.00199 |
| Haiku 4.5 | $0.00010 | $0.00099 |
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.
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
- Inspect before modifying.
- Never assume the default branch is
master; detect it. - Never overwrite user changes.
- Never rewrite shared history without explicit approval.
- Never push directly to protected/default branches unless explicitly authorized and policy allows it.
- Prefer small, reversible commits.
- Run the cheapest relevant validation gates first.
- Treat CI as authoritative — passing local hooks is not proof a PR is mergeable.
- Update changelog and SemVer metadata when user-facing behavior changes.
- 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
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.
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.
- 5d ago Changed 3b63c1136dab
- 12d ago First seen · 82 lines · 102 tokens per session scan A 9338523cba5c
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.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.