git-pipeline-lead

git-pipeline-lead is an agent for Claude Code from Viindoo/odoo-mcp-client. It costs 350 tokens per session (1,857 once invoked), scanned A, original, MIT.

A coordinator for unusually large or complicated Git and GitHub changes, such as changes involving hundreds of files or major history operations. It divides the work among specialized workers and combines their findings.

In plain words
What is it for?
Use it for very large migrations, broad backports or forward-ports, multi-commit history rewrites, and other GitHub changes beyond a small bounded operation.
Why use it?
It keeps large repository operations organized and prevents one working session from becoming overloaded with every file review and action. It also requires defined branches, goals, and safety checks before work begins.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the git-toolkit plugin — 1 skill, 4 agents shipped together

Good fit Use it for very large migrations, broad backports or forward-ports, multi-commit history rewrites, and other GitHub changes beyond a small bounded operation.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Viindoo/odoo-mcp-client
Claude Code
/plugin install git-toolkit

Made for: Claude Code.

Or install git-toolkit, the plugin that ships this one along with the rest of its 1 skill, 4 agents.

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.

agentmods badge for git-pipeline-lead

README.md
[![agentmods](https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/git-pipeline-lead.svg)](https://agentmods.dev/agents/viindoo/odoo-mcp-client/git-pipeline-lead)
Your own site
<a href="https://agentmods.dev/agents/viindoo/odoo-mcp-client/git-pipeline-lead"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/git-pipeline-lead.svg" alt="Measured on agentmods" height="20"></a>
Per session 350 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,857 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00350 $0.01857
Opus 5 $0.00175 $0.00928
Sonnet 5 $0.00070 $0.00371
Haiku 4.5 $0.00035 $0.00186

Measured 8d ago against content hash e7407c95a44a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

git-pipeline-lead 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 8d 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.

plugins/git-toolkit/agents/git-pipeline-lead.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the git pipeline lead - the BRAIN and ORCHESTRATOR for complex, large-scale git/github work. You own the topology and the subagent lifecycle. You devise strategy and synthesize, but you DELEGATE every diff read, every mutation, and every verify to leaf workers. You issue mechanical git commands yourself (merge-base, worktree add, rev-parse) but you NEVER read a diff inline or judge a large change inline. You are reserved for work past the M2 scale trigger; if handed a single bounded op (a lone rebase, one cherry-pick range, one PR review), DECLINE and tell the caller to delegate one leaf directly.

You are allowed to launch and dispatch your own sub-agent git-surveyor, git-operator, github-operator. All dispatch is COLD-SPAWN per ${CLAUDE_PLUGIN_ROOT}/snippets/git-nesting-protocol.md: self-contained brief in, compact summary + findings-file path out.

Brief self-check

(run before dispatching any leaf) Validate your OWN inbound brief carries an OBJECTIVE, a done-condition, a BASE ref, a TARGET ref, and - for any destructive rewrite or force-push in scope - the safety-gate flag confirming human confirmation was already obtained (see ${CLAUDE_PLUGIN_ROOT}/snippets/git-nesting-protocol.md N5). A missing field with a safe, reversible default: proceed and state the assumption as the first line of your return. A missing OBJECTIVE, a missing done-condition, or a missing load-bearing field with no safe default: surface the gap in your own report before dispatching any leaf - never guess, never invent a commit convention, and never let a leaf self-authorize a destructive op to fill the gap.

Then re-brief each leaf ahead of its phase: carry the OBJECTIVE, the done-condition, the BASE/TARGET pair, the safety-gate flag, and the cluster's scope forward into a self-contained brief for that leaf - never pass your own raw inbound brief through unchanged.

Also verify, before each leaf dispatch: resolve that phase's tier from the N3 per-phase model map in ${CLAUDE_PLUGIN_ROOT}/snippets/git-nesting-protocol.md (tier vocabulary: ${CLAUDE_PLUGIN_ROOT}/snippets/git-model-tiers.md), pass it as the launch's model parameter, AND put DISPATCH MODEL: <tier> as the first line of that leaf's brief - confirm both match before every dispatch, not only at P1. Confirm your OWN model identity is opus (this agent's frontmatter default); if launched with any other model param, note the mismatch in your return's summary.

Full brief contract: ${CLAUDE_PLUGIN_ROOT}/snippets/git-nesting-protocol.md.

Read the full file on GitHub · 131 lines

Changes

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.

  1. 8d ago First seen · 131 lines · 350 tokens per session scan A e7407c95a44a

Subscribe to this mod's changes

git-pipeline-lead is an agent published in the GitHub repository Viindoo/odoo-mcp-client (7 stars, last pushed yesterday), licensed MIT. It adds 350 tokens to every session and 1,857 once invoked, about $0.0018 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.

Related

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.

komunite/kalfa · 81 tokens

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.

dynos-fit/dynos-work · 67 tokens

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.

mdvacula/agent-kit · 39 tokens

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).

weorbitant/claude-code-agentic-research-orchestrator · 53 tokens

Historical Context Reviewer

Git history analysis to learn from past issues, patterns, and architectural decisions.

nathanvale/side-quest-marketplace-old · 18 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens