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 quay/ai-helpers --skill rebasegit clone --depth 1 https://github.com/quay/ai-helpersWrote 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/quay/ai-helpers/rebase)<a href="https://agentmods.dev/skills/quay/ai-helpers/rebase"><img src="https://agentmods.dev/badge/skills/quay/ai-helpers/rebase.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 5.1 | $0.00056 | $0.02637 |
| Opus 5 | $0.00028 | $0.01319 |
| Sonnet 5 | $0.00011 | $0.00527 |
| Haiku 4.5 | $0.00006 | $0.00264 |
Grade A, and why
rebase 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 2d 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rebase Branch
Rebase a branch onto its upstream target.
$ARGUMENTSis a PR number (all digits) → check out the PR branch and rebase onto the PR's base branch.$ARGUMENTSis a branch name → rebase current branch onto that target.$ARGUMENTSis empty → rebase current branch onto the upstream default branch.
Critical Rules
- Never rebase without a backup. Always create a backup ref before starting.
- Never use
--force. Always use--force-with-leasewhen pushing. - Never rebase shared branches without explicit user confirmation.
- Don't rewrite history unless asked. The goal is to replay commits onto a new base — not to squash, fixup, or reword. Only offer commit cleanup if the user explicitly requests it.
- Verify the result. Always diff the tree before and after.
- Conflict sides are swapped from merge. During rebase:
ours= upstream,theirs= your branch. The opposite of what you expect.
Phase 1: Assess
Step 1: Determine target and current state
If $ARGUMENTS is all digits, treat it as a PR number:
# Fetch PR metadata
gh pr view "$ARGUMENTS" --json headRefName,baseRefName,headRepository,headRepositoryOwner \
--jq '{head: .headRefName, base: .baseRefName, repo: .headRepository.name, owner: .headRepositoryOwner.login}'
Check out the PR branch locally and capture its tracking remote:
gh pr checkout "$ARGUMENTS"
CURRENT=$(git rev-parse --abbrev-ref HEAD)
TARGET="<baseRefName from above>"
REMOTE=$(git config "branch.$CURRENT.remote" 2>/dev/null || echo origin)
Otherwise, determine target from the argument or defaults:
TARGET="${ARGUMENTS:-$(git rev-parse --abbrev-ref origin/HEAD 2>/dev/null | sed 's|origin/||')}"
DEFAULT_BRANCH="${PRIMARY_BRANCH:-master}"
TARGET="${TARGET:-$DEFAULT_BRANCH}"
CURRENT=$(git rev-parse --abbrev-ref HEAD)
REMOTE="origin"
echo "Rebasing $CURRENT onto $TARGET"
git status --porcelain
If there are uncommitted changes, stop. Ask the user: stash, commit, or abort.
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.
- 2d ago First seen · 369 lines · 56 tokens per session scan A 23191da56117
rebase is a skill published in the GitHub repository quay/ai-helpers (3 stars, last pushed 19d ago), licensed MIT. It adds 56 tokens to every session and 2,637 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".