Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/pmatos/skills/rebase-pr)<a href="https://agentmods.dev/skills/pmatos/skills/rebase-pr"><img src="https://agentmods.dev/badge/skills/pmatos/skills/rebase-pr.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 | $0.00108 | $0.08860 |
| Opus 5 | $0.00054 | $0.04430 |
| Sonnet 5 | $0.00022 | $0.01772 |
| Haiku 4.5 | $0.00011 | $0.00886 |
Grade A, and why
rebase-pr 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.
How it starts
The opening of the file, as written. The whole thing — 506 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rebase PR
Rebase a GitHub PR branch onto its base branch, resolve every conflict by hand, re-run the
project's quality gate, and force-push without clobbering a concurrent writer. One invocation,
gh CLI only, no GitHub MCP dependency.
Core Principle: Never Bulk-Resolve a Conflict
A rebase conflict is resolved file by file, by reading both sides and writing a coherent
result. Never run git checkout ORIG_HEAD -- ., git checkout --ours ., git checkout --theirs .,
git restore --source=... ., or any other bulk path operation while a rebase is in progress — each
one silently discards resolutions already made for the other files in the same conflict.
Core Principle: The Lease Is Taken Before the Rebase
--force-with-lease only protects a concurrent writer if the value it is armed with predates that
writer's push. Fetching the branch and then computing the lease anchor arms the lease with the
other writer's commit, so the push succeeds and destroys their work — the exact failure the lease
exists to prevent. Capture EXPECTED_REMOTE_SHA before the rebase (Step 2); every later fetch
of that branch is for inspection only. See references/force-push-safety.md.
Core Principle: Gate Steps Never Chain
Quality-gate commands run as separate invocations, never &&-chained. A flaky test must not
silently skip the build step that follows it — each step's own exit status has to be observed.
Prerequisites
ghCLI, installed and authenticated (gh auth status). This is the only GitHub dependency; the skill stops at preflight if it is missing. A GitHub MCP server is never required and never waited for (same posture aspm-autofix-pr).- A clean worktree. The skill refuses to start with uncommitted tracked changes — a rebase over a dirty tree is how resolutions get lost.
Configuration
Override via prompt arguments (e.g. /rebase-pr 42 --watch-ci --ci-budget 20).
| Parameter | Default | Description |
|---|---|---|
WATCH_CI |
off | Whether to wait for post-push CI (Step 8) instead of exiting immediately after the push. Enable with --watch-ci. |
CI_BUDGET |
15 | Wall-clock ceiling (minutes) on the whole Step 8 wait, initialized once when Step 8 is entered. Only meaningful with --watch-ci. |
POLL_INTERVAL |
30 | Seconds between check re-fetches; also the --interval passed to gh pr checks --watch. |
What ships with it
4 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.
- 8d ago First seen · 506 lines · 108 tokens per session scan A 3a2ee6cf2d7c
rebase-pr is a skill published in the GitHub repository pmatos/skills (2 stars, last pushed 2d ago), licensed MIT. It adds 108 tokens to every session and 8,860 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
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.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
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…