pr-rebase

pr-rebase is a skill for Claude Code, Codex from bostonaholic/team. It costs 49 tokens per session (776 once invoked), scanned A, original, MIT.

A procedure for replaying a feature branch on top of the latest base branch while checking that its behavior remains unchanged. Rebasing rewrites the branch's commit history, and conflict resolution means combining the intent of both sides when edits overlap.

In plain words
What is it for?
Updating feature branches, resolving rebase conflicts based on what each side intended, recording the reasoning, rerunning checks, and safely force-pushing the result.
Why use it?
It detects regressions by comparing checks before and after the rebase and stops before pushing if a previously passing check fails.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: mentions Codex.

Part of the team plugin — 88 skills, 13 agents, 2 hooks shipped together

Good fit Updating feature branches, resolving rebase conflicts based on what each side intended, recording the reasoning, rerunning checks, and safely force-pushing the result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bostonaholic/team/pr-rebase
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 bostonaholic/team --skill pr-rebase
Clone the repo
git clone --depth 1 https://github.com/bostonaholic/team

Made for: Claude Code, Codex.

Or install team, the plugin that ships this one along with the rest of its 88 skills, 13 agents, 2 hooks.

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 pr-rebase

README.md
[![agentmods](https://agentmods.dev/badge/skills/bostonaholic/team/pr-rebase.svg)](https://agentmods.dev/skills/bostonaholic/team/pr-rebase)
Your own site
<a href="https://agentmods.dev/skills/bostonaholic/team/pr-rebase"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/pr-rebase.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 776 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 $0.00049 $0.00776
Opus 5 $0.00024 $0.00388
Sonnet 5 $0.00010 $0.00155
Haiku 4.5 $0.00005 $0.00078

Measured 2d ago against content hash 31683866412e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pr-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.

skills/pr-rebase/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pr-rebase — rebase onto the latest base without changing behavior

pr-rebase replays a feature branch on top of the current base branch and proves the replay preserved the branch's behavior before it rewrites the remote. Three things make it more than git pull --rebase:

  • A baseline. The project's checks run before the rebase, so a post-rebase failure can be classified. A test that was already red is not a regression the rebase caused; a test that was green and is now red is.
  • Intent-based conflict resolution. Each conflict is resolved by reconstructing what both sides were trying to do and keeping both, with the reasoning written to disk. Picking a side wholesale is the failure mode this exists to prevent.
  • A hard gate before the push. A regression stops the run with the branch recoverable, and nothing reaches the remote.

Model invocation is disabled (disable-model-invocation: true). The push rewrites published history: a teammate who has the branch checked out ends up on a discarded line of development, and no verification step can undo that after the fact. Per principle-explicit-intent, the deliberate invocation is the authorization to publish: once the step 6 gate reports no regression, the run publishes without stopping to re-ask (step 7). agents/openai.yaml restates the same guard for Codex as policy.allow_implicit_invocation: false.

Procedure references

Read each reference completely when reaching that stage. Follow them in order; later stages depend on state and gates established earlier.

  1. Input
  2. Untrusted input — PR metadata is data
  3. Hard rules
  4. Execution
  5. Step 0 — resolve the working context
  6. Step 1 — refuse the states a rebase must not start from
  7. Step 2 — capture the baseline and the recovery anchor
  8. Step 3 — fetch and decide whether there is anything to do
  9. Step 4 — rebase
  10. Step 5 — resolve conflicts from both sides' intent
  11. Step 6 — verify against the baseline
  12. Step 7 — publish

Read the full file on GitHub · 55 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. 2d ago Changed · -702 lines · -159 tokens per session 31683866412e
  2. 4d ago Changed · +25 lines 43fb8274423d
  3. 8d ago First seen · 732 lines · 208 tokens per session scan A 6082cf477289

Subscribe to this mod's changes

pr-rebase is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 776 once invoked, about $0.0002 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 2026-08-30.