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 tonyghiani/ai-essentials --skill branch-refactor-plannergit clone --depth 1 https://github.com/tonyghiani/ai-essentialsWrote 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/tonyghiani/ai-essentials/branch-refactor-planner)<a href="https://agentmods.dev/skills/tonyghiani/ai-essentials/branch-refactor-planner"><img src="https://agentmods.dev/badge/skills/tonyghiani/ai-essentials/branch-refactor-planner/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/tonyghiani/ai-essentials/branch-refactor-planner"><img src="https://agentmods.dev/badge/skills/tonyghiani/ai-essentials/branch-refactor-planner.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 | $0.00104 | $0.00820 |
| Opus 5.5 | $0.00042 | $0.00328 |
| Sonnet 5.5 | $0.00021 | $0.00164 |
| Haiku 4.5 | $0.00010 | $0.00082 |
Grade A, and why
branch-refactor-planner 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 1mo 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Branch Refactor Planner
Systematically review every file changed on the current branch, apply the quality checklist below, and produce a prioritized refactoring plan.
Investigation workflow
- Determine base branch
git merge-base HEAD main(fall back tomasteror the branch the user specifies).
- Gather the changeset
git diff --name-only <base>...HEADfor the file list.git diff <base>...HEADfor the full diff.
- Read changed files in full -- not just diff hunks. Surrounding context reveals duplication, naming drift, and missing edge-case handling that hunks alone hide.
- Cross-reference related files -- look for shared patterns, duplicated logic across the changeset, and opportunities to extract helpers or reuse existing project utilities.
- Consult project rules -- if the repo contains
AGENTS.md,CLAUDE.md, a rules directory, or other project-level agent instructions, incorporate them into the review. - Produce the plan using the output format below.
Quality dimensions
Walk through every dimension for each changed file:
| Dimension | What to look for |
|---|---|
| Naming | Variables, functions, types, and files convey intent and follow project conventions |
| Helper utils | Hand-rolled logic replaceable by standard library, lodash, or project-shared code |
| Declarative style | Imperative loops/mutation replaceable by map/filter/reduce, config objects, or declarative patterns |
| Self-documenting code | Code reads clearly without comments; flag redundant comments and missing non-obvious ones |
| Edge cases | Null/undefined, empty collections, boundary values, error paths |
| Testing | Tests are meaningful and non-redundant; flag no-op assertions, duplicate coverage, and missing coverage |
| DRY | Duplicated logic across or within files |
| KISS | Over-engineered abstractions, unnecessary indirection |
| YAGNI | Code, config, or types added speculatively without current need |
| Control flow | Early returns, positive conditions, flat nesting |
| Type safety | any/unknown usage, non-null assertions, missing return types |
| Error handling | Explicit and typed; no swallowed errors |
| Consistency | Patterns within the changeset are internally consistent |
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.
- 1mo ago First seen · 75 lines · 104 tokens per session scan A 3a9a39916775
branch-refactor-planner is a skill published in the GitHub repository tonyghiani/ai-essentials (7 stars, last pushed 19d ago), licensed MIT. It adds 104 tokens to every session and 820 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…