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.
/plugin marketplace add Viindoo/odoo-mcp-client/plugin install git-toolkitWrote 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/viindoo/odoo-mcp-client/git-pipeline-lead)<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/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/viindoo/odoo-mcp-client/git-pipeline-lead"><img src="https://agentmods.dev/badge/agents/viindoo/odoo-mcp-client/git-pipeline-lead.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 | $0.00372 | $0.02079 |
| Opus 5.5 | $0.00149 | $0.00832 |
| Sonnet 5.5 | $0.00074 | $0.00416 |
| Haiku 4.5 | $0.00037 | $0.00208 |
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 17d 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 — 146 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; a worktree that gets a NEW branch
is created per S13 in the safety contract) 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.
Every git command you issue, and every one a leaf runs, has the S12 command shape in
${CLAUDE_PLUGIN_ROOT}/snippets/git-safety-contract.md: one plain
git -C <absolute worktree> <subcommand> <args> per Bash call.
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. Collect every leaf's result by that file's N0 rule: read your own
launch tool before P1 - whether your launch tool has a run_in_background parameter decides whether a launch
returns the leaf's result inside your turn or you end your turn and are woken with it.
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 - when the work pushes to a protected branch without
a pull request - the confirmed: field (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 the
gated op to fill the gap.
Then re-brief each leaf ahead of its phase: carry the OBJECTIVE, the done-condition, the
BASE/TARGET pair, any confirmed: field, 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.
Full brief contract: ${CLAUDE_PLUGIN_ROOT}/snippets/git-nesting-protocol.md.
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.
- 17d ago Changed 1771522a7db0
- 19d ago Changed · +4 lines 6b8ed2779757
- 21d ago Changed · +9 lines · +22 tokens per session 93ee371bc804
- 29d ago Changed · -1 lines 849d0fbcd7da
- 1mo ago Changed · +1 lines 9ea9e691d1a0
- 1mo ago Changed · +2 lines 4e3f095d33d5
- 1mo ago Changed fc46e19028af
- 2mo ago First seen · 131 lines · 350 tokens per session scan A e7407c95a44a
git-pipeline-lead is an agent published in the GitHub repository Viindoo/odoo-mcp-client (9 stars, last pushed 2d ago), licensed MIT. It adds 372 tokens to every session and 2,079 once invoked, about $0.0015 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.
git-pipeline-lead compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| git-pipeline-leadViindoo/odoo-mcp-client | Agent | 9 | 2d ago | MIT | A | 372 | Claude Code |
| plastic-node-workzalom/plastic | Agent | 10 | 24d ago | MIT | A | 65 | Claude Code |
| pr-ghostwriterkomunite/kalfa | Agent | 245 | 6mo ago | MIT | A | 81 | Claude Code |
| git-specialistfmflurry/settings-opencode | Agent | 170 | 5d ago | MIT | E | 62 | Claude Code |
| copilot-integrationweorbitant/claude-code-agentic-research-orchestrator | Agent | 3 | 11mo ago | MIT | B | 53 | Claude Code |
| Historical Context Reviewernathanvale/side-quest-marketplace-old | Agent | 6 | 9mo ago | none | A | 18 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 100k | today | Apache-2.0 | A | 151 | Claude Code |