Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/rlespinasse/agent-skills/local-branches-status)<a href="https://agentmods.dev/skills/rlespinasse/agent-skills/local-branches-status"><img src="https://agentmods.dev/badge/skills/rlespinasse/agent-skills/local-branches-status/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/rlespinasse/agent-skills/local-branches-status"><img src="https://agentmods.dev/badge/skills/rlespinasse/agent-skills/local-branches-status.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 | $0.00065 | $0.02419 |
| Opus 5 | $0.00032 | $0.01210 |
| Sonnet 5 | $0.00013 | $0.00484 |
| Haiku 4.5 | $0.00006 | $0.00242 |
Grade A, and why
local-branches-status 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 12d 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Branches Status Report
You are helping the user get a comprehensive overview of all local git branches in their repository. The report shows each branch's sync state, divergence from main, worktree usage, last activity, and a brief description of what the branch contains.
When to Use
- Before deciding which branches to clean up or delete
- When resuming work after time away from a project
- Before pushing or rebasing to understand the current state
- When onboarding to a repository with multiple active branches
- When reviewing worktree usage across branches
Report Process
Step 1: Gather Branch Data
Collect all branch information in a single shell invocation using the batch loop in Step 3. Do not make N separate tool calls per branch — one loop gathers every column for every branch.
Data collected per branch:
- Remote sync state (ahead/behind upstream)
- Divergence from the main branch (ahead/behind)
- Worktree association (with path)
- Last activity date
- Unique commits (commits not on main)
- Whether this is the current branch (HEAD)
Step 2: Determine the Main Branch
Identify the main branch automatically:
git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@'
If that fails, fall back to checking for main or master.
Step 3: Batch Data Collection
Gather all per-branch data in a single shell loop rather than making separate tool calls for each branch and column. This is critical for efficiency — one invocation collects everything:
main_branch=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@' || echo "main")
current_branch=$(git symbolic-ref --short HEAD 2>/dev/null || echo "")
worktree_list=$(git worktree list)
for branch in $(git for-each-ref --format='%(refname:short)' refs/heads/); do
# Remote sync state
upstream=$(git for-each-ref --format='%(upstream:short)' "refs/heads/$branch")
if [ -n "$upstream" ] && git rev-parse --verify "refs/remotes/$upstream" &>/dev/null; then
counts=$(git rev-list --left-right --count "$upstream...$branch" 2>/dev/null || echo "0 0")
else
upstream=""
counts="no_upstream"
fi
# Main branch diff
if [ "$branch" = "$main_branch" ]; then
main_diff="—"
else
main_diff=$(git rev-list --left-right --count "$main_branch...$branch" 2>/dev/null || echo "0 0")
fi
# Last activity
last_activity=$(git log -1 --format='%cr' "$branch" 2>/dev/null || echo "unknown")
# Worktree path
wt_path=$(echo "$worktree_list" | grep "\[$branch\]" | awk '{print $1}')
# Unique commits summary
unique=$(git log "$main_branch..$branch" --oneline 2>/dev/null)
echo "BRANCH:$branch|UPSTREAM:$upstream|COUNTS:$counts|MAIN_DIFF:$main_diff|LAST:$last_activity|WT:$wt_path|CURRENT:$([ "$branch" = "$current_branch" ] && echo yes || echo no)"
echo "COMMITS:$unique"
echo "---"
done
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.
- 12d ago First seen · 220 lines · 65 tokens per session scan A f3e1cbbe796d
local-branches-status is a skill published in the GitHub repository rlespinasse/agent-skills (10 stars, last pushed 6d ago), licensed MIT. It adds 65 tokens to every session and 2,419 once invoked, about $0.0003 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
repo-standardizer
Polish any GitHub repository's surface — labels (emoji rating tiers, P0–P3 priority, impact severity), issue forms, PR template, CI workflows, CODEOWNERS, rulesets, docs. Repo meta & config only — no code logic touched. Use when creating a new repo or polishing an existing one.
conventional-commit
Prompt and workflow for generating conventional commit messages using a structured XML format. Guides users to create standardized, descriptive commit messages in line with the Conventional Commits specification, including instructions, examples, and validation.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
chained-pr
Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.