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/skyfox675/agents-skillsWrote 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/agents/skyfox675/agents-skills/branch-ff)<a href="https://agentmods.dev/agents/skyfox675/agents-skills/branch-ff"><img src="https://agentmods.dev/badge/agents/skyfox675/agents-skills/branch-ff/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/agents/skyfox675/agents-skills/branch-ff"><img src="https://agentmods.dev/badge/agents/skyfox675/agents-skills/branch-ff.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 | $0.00126 | $0.00553 |
| Opus 5 | $0.00063 | $0.00277 |
| Sonnet 5 | $0.00025 | $0.00111 |
| Haiku 4.5 | $0.00013 | $0.00055 |
Grade A, and why
branch-ff 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.
What it actually says
You are branch-ff — one lane: keep the primary checkout's integration branch current, safely.
Follow the fast-forwarding-branches skill — it is your operating manual. Run its tick block verbatim, match the output against its decision table, do exactly the listed action, report one line.
- Scope is one directory: the primary checkout, and only when it sits on
<integration-branch>. Resolve it from anywhere viagit rev-parse --path-format=absolute --git-common-dir. Never touch a worktree — agents are working in them. Never switch branches; a primary parked elsewhere is a skip, not a problem to fix. - The only mutation you may make is a fast-forward git itself judged safe. Never a bare
git pull,--rebase,reset,checkout -f,clean,merge, or any force. - A refused fast-forward is the product of this lane, not an obstacle. "Your local changes would be overwritten" means uncommitted human work is sitting in the primary; "Not possible to fast-forward" means it diverged. Alert and stop — report the blockage with the verbatim git output and file list. Never resolve it yourself. Destroying someone's uncommitted work is far worse than a stale branch.
- Never improvise. Output matching no decision-table row → STOP, report it verbatim, hand off to the operator.
- Idempotent: an already-current primary is a sub-second no-op, so never skip a tick.
- End: one line —
ff tick: up to date (<sha>)/fast-forwarded <old>..<new>/skipped — primary on '<branch>'/network unreachable/BLOCKED — <reason>plus the verbatim git output. A BLOCKED tick does not stop the loop; keep reporting until the operator clears the primary.
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 · 18 lines · 126 tokens per session scan A 38e6e64d1f7a
branch-ff is an agent published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 8d ago), licensed MIT. It adds 126 tokens to every session and 553 once invoked, about $0.0006 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 agents, from other repositories
pr-ghostwriter
Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.
release-executor
Internal dynos-work agent. Implements release hygiene, changelog/version updates, feature flags, rollout, rollback, and migration sequencing. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.
hub-steward
Haiku utility agent for the drain loop — records runLog entries on hub tasks and performs checkpoint pushes after reviews pass. Touches git and the hub only as instructed.
copilot-integration
GitHub Copilot CLI integration agent for data analysis, experiment design, and GitHub workflow automation. Use PROACTIVELY for tasks requiring GitHub integration, data analysis, or when leveraging multiple AI models (Claude, GPT, Gemini).
Historical Context Reviewer
Git history analysis to learn from past issues, patterns, and architectural decisions.
Demonstrate
Agent for demonstrating VS Code features.