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.
git clone --depth 1 https://github.com/sordi-ai/skill-everythingWrote 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/rules/sordi-ai/skill-everything/branch-finishing)<a href="https://agentmods.dev/rules/sordi-ai/skill-everything/branch-finishing"><img src="https://agentmods.dev/badge/rules/sordi-ai/skill-everything/branch-finishing/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/rules/sordi-ai/skill-everything/branch-finishing"><img src="https://agentmods.dev/badge/rules/sordi-ai/skill-everything/branch-finishing.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 | $0.00027 | $0.00697 |
| Opus 5 | $0.00014 | $0.00349 |
| Sonnet 5 | $0.00005 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
branch-finishing 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 9d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sub-Skill: Branch Finishing
Purpose: Ensures every feature branch is cleanly rebased, reviewed, and merged without introducing regressions or leaving stale local state behind.
Rules
Pre-Merge Preparation
- Rebase before merge. Always rebase onto the target branch immediately before requesting merge to catch regressions introduced since the branch was cut. Reference: ERR-2026-024
- Resolve conflicts locally. Before pushing a rebase, resolve every conflict locally and run the full test suite; never push a branch with unresolved markers.
- CI green before review. Ensure all CI checks pass on the latest push before requesting a human review; do not ask reviewers to look at a red branch.
- Self-review diff. Before opening a PR, run
git diff main...HEADand read every changed line; catch debug prints, commented-out code, and accidental file inclusions yourself first.
Commit Hygiene
- Squash fixup commits. Before merge, squash or fixup any
wip:,fixup!, ortmp:commits so the branch history is clean; usegit rebase -ito consolidate. - Issue closing keywords. Use
Closes #NNNorFixes #NNNin the PR body so the linked issue auto-closes on merge; never leave issues open manually after a successful merge. - Changelog update. After any user-visible change, add an entry to
CHANGELOG.md(or the project's equivalent) before marking the PR ready for review. - Version bump. If the project uses semantic versioning, bump the version in the appropriate manifest file as part of the branch before merge, not as a follow-up commit.
Draft → Ready Transition
- Draft until CI passes. Keep the PR in draft state until all CI checks are green and the self-review is complete; convert to ready-for-review only when the branch is genuinely merge-ready.
- Remove draft status explicitly. Use
gh pr ready <number>to convert from draft; do not rely on reviewers noticing a draft PR that was silently updated.
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.
- 9d ago First seen · 49 lines · 27 tokens per session scan A 9d656dce2aa0
branch-finishing is a cursor rule published in the GitHub repository sordi-ai/skill-everything (20 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 697 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 2026-08-30.
Other cursor rules, from other repositories
release-notes
Generate changelog entries and GitHub releases from git history. Categorizes commits into features, fixes, breaking changes, and docs. Supports conventional commits, PR-based grouping, and semantic versioning. Creates formatted CHANGELOG.md entries and GitHub releases.
github
GitHub repository operations: PRs, issues, releases, branch protection, CODEOWNERS, Dependabot, and repo settings audits. Use when user says 'review my PR', 'create a release', 'cut a release', 'tag a release', 'set up branch protection', 'add CODEOWNERS', 'audit repo settings', 'is Dependabot configured', or asks…
gitops
Argo CD and Flux review and scaffolding: mutable source refs, AppProject wildcard grants, unguarded auto-prune, sync waves and dependency ordering, selfHeal drift enforcement, and per-environment separation. Use when user says 'review my argocd', 'review my Application', 'check my flux config', 'set up gitops', 'why…
safe-push
Pre-push hygiene check for GitHub repositories. Scans for PII, secrets, and sensitive data before pushing. Audits commit messages, enforces repo-specific blocklists, and rate-limits pushes to avoid GitHub abuse detection. Use before any git push, especially to public repos.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.