linear-flow

linear-flow is a skill for Claude Code from bengous/claude-code-plugins. It costs 46 tokens per session (685 once invoked), scanned A, original, MIT.

A Git workflow for keeping development and release branches on one signed, merge-free line of history. It uses fast-forward updates so the release branch always points to an earlier point in development.

In plain words
What is it for?
It helps configure a repository for linear history, land branches by rebasing them, and promote development to a release branch with a fast-forward push.
Why use it?
It prevents merge commits and unsigned history from breaking the repository’s rules. It also makes it clear how larger changes and releases should move through the repository.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md.

Part of the git-tools plugin — 6 skills, 2 commands shipped together

Good fit It helps configure a repository for linear history, land branches by rebasing them, and promote development to a release branch with a fast-forward push.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bengous/claude-code-plugins/linear-flow
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 bengous/claude-code-plugins --skill linear-flow
Clone the repo
git clone --depth 1 https://github.com/bengous/claude-code-plugins

Made for: Claude Code.

Or install git-tools, the plugin that ships this one along with the rest of its 6 skills, 2 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.

agentmods badge for linear-flow

README.md
[![agentmods](https://agentmods.dev/badge/skills/bengous/claude-code-plugins/linear-flow/github.svg)](https://agentmods.dev/skills/bengous/claude-code-plugins/linear-flow)
Your own site
<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/linear-flow"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/linear-flow/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.

agentmods 80×15 button for linear-flow

Your own site · 80×15
<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/linear-flow"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/linear-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 685 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 $0.00046 $0.00685
Opus 5 $0.00023 $0.00342
Sonnet 5 $0.00009 $0.00137
Haiku 4.5 $0.00005 $0.00068

Measured 5d ago against content hash 029236a6c4e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

linear-flow 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 5d 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.

git-tools/skills/linear-flow/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Linear Flow

Doctrine for repos on the linear model. One linear signed history. dev is the working trunk. main is the release channel consumers use: a delayed pointer on dev's history, moved only by fast-forward. No merge commits anywhere; the server refuses them (required_linear_history).

dev   ──●──●──●──●──●──●──●──►   the only line of history
                    ↑
main ───────────────┘            release = git push origin dev:main

main is always an ancestor of dev. If a repo has no release channel, main alone is the trunk and every dev rule below applies to main.

Rules

  1. Threshold. Small single-concern change: commit directly on dev, atomic and curated. Big work (large feature, large skill), several concerns, or parallel agents: branch or PR stack targeting dev.
  2. Landing. Rebase the branch on dev, then git push origin <branch>:dev. The identical SHAs reaching the base marks the PR merged. Never use the GitHub merge button: server-side merge or rebase re-creates commits unsigned and breaks required_signatures.
  3. Release. git push origin dev:main when dev has soaked long enough. Nothing else ever touches main.
  4. Force-push. Only on feature branches, only --force-with-lease. Never on dev or main.
  5. Review. Agents review other agents' PRs in fresh context. The human reviews contracts and runs tests at the end of a chantier and before each release; the human does not re-read details.
  6. History is authored. Curate commits before landing: atomic, conventional messages. Messy exploration gets squashed or reworded during the pre-land rebase, not after.

Recovery

Symptom Fix
Push to dev/main rejected non-fast-forward Rebase on the current remote tip, push again. Never force.
Push rejected required_linear_history A merge commit slipped in; rebase to flatten it, push again.
PR not marked merged after landing The pushed SHAs differ from the PR head. Push the rebased branch to the PR first, then push it to dev.
main no longer ancestor of dev Someone moved main off the line. Fast-forward the lagging ref onto the other; if truly diverged, stop and ask the user which line wins.
git pull refused on dev Pull with rebase; the ruleset rejects merge commits from pulls too.

Read the full file on GitHub · 41 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. 5d ago First seen · 41 lines · 46 tokens per session scan A 029236a6c4e7

Subscribe to this mod's changes

linear-flow is a skill published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 685 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 2026-09-03.