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/FunkyOz/funkyoz-pluginsWrote 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/commands/funkyoz/funkyoz-plugins/git)<a href="https://agentmods.dev/commands/funkyoz/funkyoz-plugins/git"><img src="https://agentmods.dev/badge/commands/funkyoz/funkyoz-plugins/git/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/commands/funkyoz/funkyoz-plugins/git"><img src="https://agentmods.dev/badge/commands/funkyoz/funkyoz-plugins/git.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 | $0.00009 | $0.01805 |
| Opus 5.5 | $0.00004 | $0.00722 |
| Sonnet 5.5 | $0.00002 | $0.00361 |
| Haiku 4.5 | $0.00001 | $0.00180 |
Grade A, and why
git 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 2mo 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Integration Command
You are managing git workflow in alignment with the task-based development process.
Input
-
Action: {{1}}
branch- Create a branch for a taskcommit- Commit changes for current taskfinish- Complete task branch (commit, optionally merge)status- Show git status relative to taskssync- Sync task branches with main/develop
-
Task Number: {{2}} (optional, defaults to current in-progress task)
Prerequisites
Verify git is initialized:
git rev-parse --is-inside-work-tree
If not a git repository, ask if user wants to initialize one.
Actions
branch - Create Task Branch
Create a new branch for working on a specific task.
Process:
- Identify the task (from argument or first
progresstask) - Read task file to get title
- Generate branch name:
task/XX-task-slug- Example:
task/05-lexer-tokenizer
- Example:
- Check if branch already exists
- Create and checkout the branch:
git checkout -b task/XX-task-slug - Confirm to user:
"Created and switched to branch
task/05-lexer-tokenizerReady to work on Task 05: Lexer/Tokenizer"
Branch Naming Convention:
- Prefix:
task/ - Task number: Zero-padded (01, 02, etc.)
- Slug: Lowercase, hyphenated task title
- Example:
task/07-stream-reader-base
commit - Commit Task Progress
Create a comprehensive commit for the current task work.
Process:
- Check for uncommitted changes
- Identify current task (from branch name or in-progress task)
- Analyze changed files and diffs to understand what was modified
- Stage all changes (or ask user what to stage)
- Auto-generate comprehensive commit message:
- Descriptive title (max 50 characters)
- Detailed description (3-4 lines max) based on actual code changes
- NEVER add acceptance criteria in message body
- NEVER add author information in message body
- NEVER add generated with/by in message body
- Show generated commit message to user for approval
- Create the commit after user approval
- Confirm to user
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.
- 2mo ago First seen · 246 lines · 9 tokens per session scan A 56b1cb9971cd
git is a command published in the GitHub repository FunkyOz/funkyoz-plugins (2 stars, last pushed 10mo ago), licensed MIT. It adds 9 tokens to every session and 1,805 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
standup
Review my git commits from the past workday and generate a standup summary.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
git-workflow
Run review, tests, and commit steps, then prepare a pull request.
commit
Context-aware Git commit assistant with smart pre-commit checks.