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 skyfox675/agents-skills --skill fast-forwarding-branchesgit 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/skills/skyfox675/agents-skills/fast-forwarding-branches)<a href="https://agentmods.dev/skills/skyfox675/agents-skills/fast-forwarding-branches"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/fast-forwarding-branches/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/skyfox675/agents-skills/fast-forwarding-branches"><img src="https://agentmods.dev/badge/skills/skyfox675/agents-skills/fast-forwarding-branches.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00167 | $0.01735 |
| Opus 5 | $0.00084 | $0.00868 |
| Sonnet 5 | $0.00033 | $0.00347 |
| Haiku 4.5 | $0.00017 | $0.00173 |
Grade A, and why
fast-forwarding-branches 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fast-forwarding the primary checkout
One job: keep the primary checkout's integration branch at the remote tip, safely, on a loop. Fast-forward when it is clean; report loudly and change nothing when it is not.
Why this lane exists (it explains every rule below)
Agents work in worktrees cut from the primary checkout. Everything a fresh worktree inherits — git hooks, repo scripts, CI config, the skills and agents themselves — comes from the primary's branch. So a primary that has drifted a week behind hands every newly-created worktree a stale base, and the staleness is invisible until something breaks oddly. One cheap pull --ff-only per tick keeps the base honest.
The second half matters just as much. Because agents are supposed to be in worktrees, the primary checkout should normally be clean. If a fast-forward is refused because local changes would be overwritten, that is not a routine condition to work around — it means uncommitted work is sitting in the primary. Clobbering it would destroy someone's work. So the refusal is the product of this lane: surface it, and stop.
Project bindings
Project-agnostic; the adopting project defines these in its own CLAUDE.md.
| Placeholder | Meaning |
|---|---|
<integration-branch> |
The branch the primary checkout is expected to sit on (e.g. main) |
<remote> |
The remote to pull from (almost always origin) |
The tick — run exactly this
Safe by construction: --ff-only never rewrites, merges, or clobbers anything — it refuses instead. The branch guard leaves a primary that is on some other branch completely alone. Run this from anywhere inside the repo (the primary checkout or any worktree — it resolves the primary itself):
PRIMARY="$(dirname "$(git rev-parse --path-format=absolute --git-common-dir)")"
BRANCH="$(git -C "$PRIMARY" rev-parse --abbrev-ref HEAD)"
if [ "$BRANCH" != "<integration-branch>" ]; then
echo "ff tick: skipped — primary is on '$BRANCH', not <integration-branch>"
else
BEFORE="$(git -C "$PRIMARY" rev-parse --short HEAD)"
git -C "$PRIMARY" pull --ff-only <remote> <integration-branch> 2>&1 | tail -8
AFTER="$(git -C "$PRIMARY" rev-parse --short HEAD)"
echo "ff tick: $BEFORE -> $AFTER"
fi
What ships with it
1 file 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 · 86 lines · 167 tokens per session scan A 701f2d5607e3
fast-forwarding-branches is a skill published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 167 tokens to every session and 1,735 once invoked, about $0.0008 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
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…
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.