branch

branch is a skill for Claude Code from queelius/claude-anvil. It costs 56 tokens per session (534 once invoked), scanned A, original, MIT.

A skill that forks an active research run into a named branch with separate state, notes, and attempts. The branch can explore another strategy without changing the main run.

In plain words
What is it for?
Use it to try a different proof method, experiment design, or search strategy from the same checkpoint. Later synthesis can compare the branches.
Why use it?
It makes competing approaches safe to investigate in parallel. Shared findings remain available for later comparison.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the research-agent plugin — 4 skills, 4 commands, 1 agent shipped together

Good fit Use it to try a different proof method, experiment design, or search strategy from the same checkpoint. Later synthesis can compare the branches.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/queelius/claude-anvil/branch
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 queelius/claude-anvil --skill branch
Clone the repo
git clone --depth 1 https://github.com/queelius/claude-anvil

Made for: Claude Code.

Or install research-agent, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 1 agent.

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 branch

README.md
[![agentmods](https://agentmods.dev/badge/skills/queelius/claude-anvil/branch/github.svg)](https://agentmods.dev/skills/queelius/claude-anvil/branch)
Your own site
<a href="https://agentmods.dev/skills/queelius/claude-anvil/branch"><img src="https://agentmods.dev/badge/skills/queelius/claude-anvil/branch/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 branch

Your own site · 80×15
<a href="https://agentmods.dev/skills/queelius/claude-anvil/branch"><img src="https://agentmods.dev/badge/skills/queelius/claude-anvil/branch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 534 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 $0.00056 $0.00534
Opus 5.5 $0.00022 $0.00214
Sonnet 5.5 $0.00011 $0.00107
Haiku 4.5 $0.00006 $0.00053

Measured yesterday against content hash 091d9911feac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

branch 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.

research-agent/skills/branch/SKILL.md · 53 lines

What it actually says

Branch a Research Run

Fork the current run so a competing strategy can be explored in parallel with (or instead of) the main line, without touching the main line's state.

Step 1: Parse Arguments

Extract from the user's message:

  1. Branch name (required): kebab-case identifier, e.g. induction-proof, adversarial-search. Derive one from the stated strategy if the user did not name it explicitly, and confirm it.
  2. Branch focus (optional): one or two sentences describing what this branch should pursue differently from the main line.

Step 2: Verify the Run and the Name

  • .research/goal.md must exist (Read tool); if not, there is nothing to branch: suggest /research-agent:research.
  • .research/branches/<name>/ must NOT already exist (Glob tool). If it does, offer /research-agent:resume <name> instead, or a different name.

Step 3: Launch the Researcher in Branch Mode

Spawn the researcher agent (Agent tool, subagent_type: research-agent:researcher) with this prompt structure:

<mode>branch</mode>

<branch>{kebab-case name}</branch>

<branch-focus>
{the focus, or "explore an alternative approach to the goal"}
</branch-focus>

<working_directory>
{absolute path to current working directory}
</working_directory>

Fork the run at its current checkpoint per your branch-mode
initialization. Never write to the parent's goal.md, log.md, or
state.md; all branch work lives under .research/branches/{name}/.

Step 4: Inform the User

Branch {name} forked from the current checkpoint. It works under .research/branches/{name}/ with its own state, log, and attempts; the goal and the parent's confirmed findings are shared read-only.

  • /research-agent:status shows all branches alongside the main line
  • /research-agent:resume {name} continues this branch later
  • /research-agent:synthesize {name} concludes just this branch; a main-line /research-agent:synthesize compares all branches
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. yesterday First seen · 53 lines · 56 tokens per session scan A 091d9911feac

Subscribe to this mod's changes

branch is a skill published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 534 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-19.

Related

Other skills, from other repositories

alive:demo

Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.

alivecontext/alive · 52 tokens

karpenter

Design, install, debug, review, plan capacity, audit scaling history, migrate from Cluster Autoscaler, and upgrade Karpenter v1.x on EKS. Covers NodePool, EC2NodeClass, NodeClaim, Spot diversity, disruption strategy, Pod Identity/IRSA, interruption queue, private clusters, AMI rotation, and GitOps integration. Use…

nitinjain999/platform-skills · 131 tokens

pr-review

Comprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for…

nitinjain999/platform-skills · 81 tokens

alive:system-upgrade

Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.

alivecontext/alive · 57 tokens

azure

Azure identity (Workload Identity, OIDC, Entra ID), resource tagging, AKS platform patterns, RBAC scoping, and production-readiness review — with Terraform generation.

nitinjain999/platform-skills · 39 tokens

kubescape

Check Kubernetes manifests, Helm charts, Kustomize overlays and live clusters against NSA-CISA, MITRE ATT&CK, CIS (EKS, AKS, GKE, vanilla) and SOC2 with the Kubescape CLI. Covers framework choice, score and severity gates, PR gates that fail only on new findings (--baseline), exceptions that actually suppress…

nitinjain999/platform-skills · 217 tokens