rebase

rebase is a skill for Claude Code, Codex from jstoup111/ai-conductor. It costs 44 tokens per session (3,005 once invoked), scanned A, original, Apache-2.0.

A workflow step for finishing a paused Git rebase, which is the process of applying one branch's commits onto another branch.

In plain words
What is it for?
Use it when a rebase is in progress: fix conflict markers, stage the corrected files, and run `git rebase --continue`, repeating as needed.
Why use it?
It helps resolve conflicts that stopped the rebase and continue until the operation finishes or a conflict is unsafe to resolve automatically.

Skill for Claude CodeCodex

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

Good fit Use it when a rebase is in progress: fix conflict markers, stage the corrected files, and run git rebase --continue, repeating as needed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jstoup111/ai-conductor/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 jstoup111/ai-conductor --skill rebase
Clone the repo
git clone --depth 1 https://github.com/jstoup111/ai-conductor

Made for: Claude Code, 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 rebase

README.md
[![agentmods](https://agentmods.dev/badge/skills/jstoup111/ai-conductor/rebase.svg)](https://agentmods.dev/skills/jstoup111/ai-conductor/rebase)
Your own site
<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/rebase"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/rebase.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,005 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 227
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
How audits are shown
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 $0.00044 $0.03005
Opus 5 $0.00022 $0.01503
Sonnet 5 $0.00009 $0.00601
Haiku 4.5 $0.00004 $0.00300

Measured 8d ago against content hash 114c76daf0d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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 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.

skills/rebase/SKILL.md · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Resumes a paused rebase that stopped on a conflict hunk. The conductor's finish-time runRebaseStep calls this skill when git rebase exits mid-flight (exit code 1 with conflict markers in the working tree). The operator can also invoke it manually as /rebase.

This skill has ONE job: resolve the conflict markers in the affected files, stage the fixes, and run git rebase --continue to advance — repeating for any additional conflict hunks — until the rebase completes cleanly or a hunk is judged unsafe to resolve automatically.

The conductor retries this skill up to a configured cap (default 3) before issuing a HALT. Each invocation is one bounded attempt.

Practices

1. Confirm Rebase State

Verify a rebase is actually in progress before touching anything:

git status
test -d "$(git rev-parse --git-path rebase-merge)" || test -d "$(git rev-parse --git-path rebase-apply)"

(--git-path resolves the state dir correctly in linked worktrees, where .git is a file and ls .git/rebase-merge/ always fails. Note that rev-parse --git-path prints the path unconditionally — only test -d on it proves a rebase is in progress.)

If no rebase is in progress, emit {"resolved": false, "reason": "no rebase in progress"} and stop.

2. Capture Replay Intent Before Editing

Before touching a conflicted file, capture an evidence ledger for the replay source commit currently being applied. REBASE_HEAD identifies the commit being replayed during a paused rebase; record its object ID and its parent commit before making edits:

git rev-parse REBASE_HEAD
git rev-parse REBASE_HEAD^
git show --format=fuller --stat REBASE_HEAD
git diff --find-renames REBASE_HEAD^ REBASE_HEAD

Read the source commit and its parent context/diff to establish what behavior the replay source commit intended to introduce or change. Then read the upstream context that is currently checked out and caused the conflict:

git show --format=fuller --stat HEAD
git log --oneline --decorate -n 20 HEAD
git diff --find-renames REBASE_HEAD^ HEAD

Read the full file on GitHub · 288 lines

Files

What ships with it

1 file 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. 8d ago First seen · 288 lines · 44 tokens per session scan A 114c76daf0d5

Subscribe to this mod's changes

rebase is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 3,005 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 2026-08-31.

Related

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.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

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.

rpamis/comet · 72 tokens

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.

zeenie-ai/OpenCompany · 51 tokens

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…

LilMGenius/paperthin · 70 tokens

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…

leo-lilinxiao/codex-autoresearch · 80 tokens