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.
npx skills add liatrio-labs/ai-prompts --skill branch-surgery-pr-splitgit clone --depth 1 https://github.com/liatrio-labs/ai-promptsWrote 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.
[](https://agentmods.dev/skills/liatrio-labs/ai-prompts/branch-surgery-pr-split)<a href="https://agentmods.dev/skills/liatrio-labs/ai-prompts/branch-surgery-pr-split"><img src="https://agentmods.dev/badge/skills/liatrio-labs/ai-prompts/branch-surgery-pr-split/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.
<a href="https://agentmods.dev/skills/liatrio-labs/ai-prompts/branch-surgery-pr-split"><img src="https://agentmods.dev/badge/skills/liatrio-labs/ai-prompts/branch-surgery-pr-split.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00068 | $0.00825 |
| Opus 5 | $0.00034 | $0.00413 |
| Sonnet 5 | $0.00014 | $0.00165 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
branch-surgery-pr-split 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Branch Surgery PR Split
Overview
Use this skill to turn a risky monolithic branch into a safe, auditable set of scoped PRs. Treat topology as a decision, not a default recipe, and collaborate with the user before executing branch surgery.
Workflow
- Quantify branch shape before proposing solutions.
- Always present the top two topology options with explicit tradeoffs.
- Collaborate with the user to select one topology.
- Produce a decision-complete split plan.
- Execute with safety refs and strict scope boundaries.
- Run parity and completeness audits.
- Remediate drift and generate PR metadata.
Step 1: Quantify Branch Shape
Collect objective signals first:
- Commit count and net churn versus base.
- Number of changed files and hotspot files.
- Mixed-commit prevalence (single commit touching unrelated concerns).
- Dependency density between concerns.
- Expected review risk and conflict risk.
If signals are incomplete, gather more evidence before recommending topology.
Step 2: Generate Topology Options
Always provide the top two options with tradeoffs and a recommendation.
Use references/topology-patterns.md to select options.
For each option, include:
- Topology name.
- Why it fits this branch shape.
- Review ergonomics, merge complexity, and conflict risk.
- Failure modes and mitigations.
- Cost of execution (low/medium/high).
Do not skip tradeoffs.
Step 3: Collaborate on Topology Selection
Use targeted discovery questions from references/facilitated-discovery-questions.md.
Confirm constraints before surgery:
- Must-merge-first dependencies.
- Parallel review goals.
- Tolerance for stacked PR depth.
- Documentation isolation preference.
- Release timing constraints.
If the user is unsure, recommend one option and explain what would change with the second option.
Step 4: Produce a Decision-Complete Split Plan
Produce:
- Branch inventory with base branch mapping.
- Commit disposition map (keep, split, drop-as-superseded).
- Execution order.
- Merge order.
- Validation gates.
- Risk register and mitigations.
What ships with it
5 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.
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.
- 11d ago First seen · 124 lines · 68 tokens per session scan A 5ef5406cf1b0
branch-surgery-pr-split is a skill published in the GitHub repository liatrio-labs/ai-prompts (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 68 tokens to every session and 825 once invoked, about $0.0003 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.
Other skills, from other repositories
lov-rename-project
A project-renaming workflow that updates a product or repository name across source files, configuration, and documentation. It produces a reviewable plan and preserves compatibility-sensitive names and references where needed.
lov-gh-tidy
Interactive GitHub repo hygiene skill. Lists all open issues, PRs, stale branches, and orphan labels, shows a summary of each with analysis, then asks the user how to handle each item (close, merge, comment, delete, keep). Executes all chosen actions via gh CLI. Use when the user says "清理 GitHub", "tidy repo", "clean…
lov-checkpoint
A project checkpoint tool that records what changed, what was verified, unresolved work, and the next steps using Git status and history. Git is the system that tracks changes to project files.
project
Clone, index, and orchestrate multi-repo work via agent-toolkit project — symlinks, quick access, and swarm workspaces.
jira-developer-integration
Git and developer workflow integration. TRIGGERS: 'generate branch name', 'create branch name', 'branch name for', 'write PR description', 'PR description for', 'link PR', 'link pull request', 'parse commit', 'extract issue from commit', 'smart commit', 'development panel'. Use for Git, GitHub, GitLab, Bitbucket…
dsh-plugin-publisher
A release tool for DSH plugins, where DSH is the DeepSeek Harness used to load these add-ons. It validates an existing plugin package, publishes it through npm, Git, or a tarball, and checks that the harness can load it.