A Graphite command that distributes uncommitted changes among the earlier branches they belong to. It can first show a proposed assignment for review before applying it.

Use it to send separate fixes to the appropriate branches, amend those branches, and update the branches built on top of them.

It avoids manually checking out several branches to place fixes in the right commits. This is useful when review feedback affects multiple pull requests in a stack.

absorb — Command for Claude Code by pleaseai

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.

Clone the repo

git clone --depth 1 https://github.com/pleaseai/claude-code-plugins

Made for: Claude Code.

Or install graphite, the plugin that ships this one along with the rest of its 3 skills, 16 commands.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/pleaseai/claude-code-plugins/absorb/github.svg)](https://agentmods.dev/commands/pleaseai/claude-code-plugins/absorb)

Your own site

<a href="https://agentmods.dev/commands/pleaseai/claude-code-plugins/absorb"><img src="https://agentmods.dev/badge/commands/pleaseai/claude-code-plugins/absorb/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/pleaseai/claude-code-plugins/absorb"><img src="https://agentmods.dev/badge/commands/pleaseai/claude-code-plugins/absorb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 379 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.

Model	Per session	Once invoked
Fable 5.1	$0.00015	$0.00379
Opus 5	$0.00008	$0.00189
Sonnet 5	$0.00003	$0.00076
Haiku 4.5	$0.00002	$0.00038

Measured yesterday against content hash 554996fdc367, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

absorb 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 yesterday.

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.

plugins/graphite/commands/absorb.md · 29 lines

What it actually says

When the working tree contains hunks that logically belong to several different downstack branches, gt absorb figures out which branch each hunk should amend into and applies them. User input: $ARGUMENTS.

When to prefer absorb over modify

The diff fixes things touched by multiple ancestors (e.g. typo in branch A and unrelated bug in branch B).
You want to land review feedback that spans multiple PRs at once.
For changes that all belong on the current branch, use /graphite:modify instead — it's simpler.

Steps

Run git status --short so the user sees the working-tree state.
Run gt ls to show which branches are candidates downstack.
Run a dry run first: gt absorb -a -d (or gt absorb -p -d for hunk selection). Show the user the proposed branch-per-hunk assignment.
If the user approves, run without -d to apply. Each affected branch is amended, then everything upstack is auto-restacked.
Resolve any restack conflicts the usual way: gt add . → gt continue -a, or gt abort.
Run gt ls and consider gt submit --stack -u to update PRs.

Key flags

-a, --all — consider all modified files (default is staged only)
-p, --patch — interactive hunk selection
-d, --dry-run — show the plan without amending

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.

yesterday First seen · 29 lines · 15 tokens per session scan A 554996fdc367

Subscribe to this mod's changes

absorb is a command published in the GitHub repository pleaseai/claude-code-plugins (13 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 379 once invoked, about $0.0001 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 2026-09-07.

Code review Git and workflow

absorb

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

When to prefer absorb over modify

Steps

Key flags

What this file has done since we first saw it

Other commands, from other repositories

devkit.github.review-pr

speckit.spex.submit

git

merge-conflict-analysis

code-review

repo-audit