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 5.5 | $0.00011 | $0.00279 |
| Sonnet 5.5 | $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 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 — 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.
- 1mo 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 (21 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 697 once invoked, about $0.0001 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 2026-08-30.
Other cursor rules, from other repositories
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…
sync-repos
Manage public/private repository pairs. Verify parity, detect drift, run sync scripts, and validate no sensitive data leaks to the public repo. Use for projects that maintain separate dev and public 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.
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.