git-branchless

A workflow for using Git without creating branches immediately. Commits act as checkpoints, while branches are created later when work is ready to publish.

In plain words
What is it for?
Planning and carrying out stacked commits, rebasing, editing commit history, recovering changes, and synchronizing with the base branch.
Why use it?
It keeps multi-commit work and history changes easier to recover and organize. It also provides specific ways to undo mistakes and update work from the base branch.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/outlinedriven/odin-codex-plugin/git-branchless
Any agent
npx skills add OutlineDriven/odin-codex-plugin --skill git-branchless
Clone the repo
git clone --depth 1 https://github.com/OutlineDriven/odin-codex-plugin

Made for: Claude Code, Codex.

Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,828 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00131 $0.01828
Opus 5 $0.00066 $0.00914
Sonnet 5 $0.00026 $0.00366
Haiku 4.5 $0.00013 $0.00183

Measured 3d ago against content hash 4721acdd7e87, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-branchless 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/git-branchless/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git-branchless

Branchless treats commits as checkpoints, detached HEAD as the default work mode, and branches as publishing artifacts. This skill enforces that mental model and routes every common git workflow to its branchless equivalent. Reference docs:

  • references/commands.md — every command, flag, revset, config key.
  • references/recipes.md — concrete sequences + decision rubric.
  • references/recovery.md — undo, restack, hide, snapshot, GC semantics.

Pre-flight gate [LOAD-BEARING]

Before applying any rule below, confirm branchless is initialized for the current repository. Run:

test -d "$(git rev-parse --git-common-dir)/branchless" && git config --get branchless.core.mainBranch

(Resolving the git-common-dir handles linked worktrees, where .git is a file rather than a directory and branchless state lives in the main repo's git dir.)

Result Skill behavior
Both succeed Skill is active. Apply the rules below. Acknowledge with one line: git-branchless active — main=<value>.
Either fails Skill is silently inert. Emit one line: git-branchless not initialized; skill inactive. Yield to plain git. Do not suggest git branchless init unless the user explicitly asks how to enable.

The inert path is intentional. This skill does not nag and does not refuse legitimate work in repos where branchless was never adopted.


Always / Never (operation-class framing)

Each rule names an operation class, not a command. Plain-git commands are fine when they fall outside the class.

Class Always Never
Stack edits (reorder, fixup, squash, split) git move, git move -F, git reword, and git split where available [v0.11.0+] (use the Recipe 4 workaround on older versions). git rebase -i to drive stack edits.
Base updates (rebase a stack onto fresh main) git sync --pull (or git move -b 'stack()' -d origin/main). Read the skip summary. git pull --rebase against a stack.
Undoing committed history git undo -i. git reset --hard <SHA> against any commit you have already made.
Discarding local work in progress git hide -r <tip> (recoverable). git branch -D or git reset --hard purely to wipe.
Branch creation for ephemeral work Detached HEAD until publish; commit immediately, branch later. git checkout -b feature/X before the first commit exists.
Publishing Branch the tip then git push -u, or git submit -c on supported forges. Force-push as a way to "fix" your local history.

Read the full file on GitHub · 141 lines

Files

What ships with it

3 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.

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. 3d ago First seen · 141 lines · 131 tokens per session scan A 4721acdd7e87

Subscribe to this mod's changes

git-branchless is a skill published in the GitHub repository OutlineDriven/odin-codex-plugin (15 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 131 tokens to every session and 1,828 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

apm-review-panel

Use this skill to run a multi-persona expert advisory review on a labelled pull request in microsoft/apm. The panel fans out to five mandatory specialists plus a test-coverage specialist (active on every PR that touches src/) plus three conditional specialists (auth, doc-writer, performance-expert), all running in…

microsoft/apm · 178 tokens

batch-bug-shepherd

Use this skill to drive a batch of suspected bugs in microsoft/apm from raw issue list to mergeable PR queue. Fan out one triage subagent per issue (LEGIT / UNCLEAR / FIXED-AT-HEAD), gate every legit bug against PRINCIPLES.md via an apm-ceo strategic-alignment pass, cross-reference legit issues against open PRs, then…

microsoft/apm · 227 tokens

apm-spec-guardian

Use this skill to run a four-panel adversarial advisory review on any pull request that touches the OpenAPM specification artifact (docs/src/content/docs/specs/openapm-.md), its inline / sidecar JSON Schemas (docs/src/content/docs/specs/schemas/.schema.json), or the conformance fixture seed…

microsoft/apm · 215 tokens

apm-triage-panel

Use this skill to triage one microsoft/apm issue selected by the daily sweep, the status/needs-triage fast path, or manual dispatch. Emit one synthesized comment with a decision, label set, exact milestone, and suggested next action.

microsoft/apm · 59 tokens

cli-logging-ux

Use this skill when editing or creating CLI output, logging, warnings, error messages, progress indicators, or diagnostic summaries in the APM codebase. Activate whenever code touches console helpers (richsuccess, richwarning, richerror, richinfo, richecho), DiagnosticCollector, STATUSSYMBOLS, CommandLogger, or any…

microsoft/apm · 94 tokens

pr-description-skill

Use this skill to write the PR description (PR body) for any pull request opened against microsoft/apm. Produces one self-sufficient GitHub-Flavored Markdown artifact: TL;DR, Problem (WHY), Approach (WHAT), Implementation (HOW), 1-3 validated mermaid diagrams, explicit trade-offs, validation evidence, and a…

microsoft/apm · 131 tokens