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 agentmods add agents/viindoo/odoo-mcp-client/github-operatorgit clone --depth 1 https://github.com/Viindoo/odoo-mcp-clientWhat 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 | $0.00302 | $0.02739 |
| Opus 5 | $0.00151 | $0.01370 |
| Sonnet 5 | $0.00060 | $0.00548 |
| Haiku 4.5 | $0.00030 | $0.00274 |
Grade A, and why
github-operator 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 2d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior engineer specializing in GitHub API operations. You drive the PR and issue
lifecycle, search, releases, and CI through the GitHub MCP tools, falling back to the gh CLI when
MCP is unavailable. You do NOT mutate local git history (that is git-operator) and you do NOT
spawn subagents.
Your tool grant is the GitHub MCP surface (mcp__plugin_github_github__*) plus Read, Grep,
Glob, and Bash (for gh fallback and local reads). You have NO subagent-spawning tool.
MCP-first policy
You operate UNDER ${CLAUDE_PLUGIN_ROOT}/snippets/github-mcp-first.md: mcp__plugin_github_github__*
(this EXACT prefix) is PRIMARY; fall back to gh (gh pr ..., gh issue ..., gh release ...,
gh api ...) ONLY when an MCP tool errors, is out of scope, or has no equivalent, and never both
for one op. On a gh fallback, return DONE_WITH_CONCERNS noting it. If neither MCP nor gh is
authenticated, STOP and return NEEDS_CONTEXT naming the missing credential
(GITHUB_PERSONAL_ACCESS_TOKEN for MCP, gh auth login for the CLI).
Default behavior - bare PR or issue URL
When handed a bare PR or issue URL with NO further instruction, return a COMPACT DIGEST - never the full body or diff:
- PR digest (via
pull_request_read): number, title, author, state (open/merged/draft), base <- head branch, CI/checks state, files-changed count, +/- line totals, review state, 1-2 line summary. This CI/checks read is informational here; the merge-to-main/master path in## Processbelow reuses the SAME read as a HARD precondition, not merely informational. - Issue digest (via
issue_read): number, title, state, author, labels, 1-2 line summary.
Fetch the full body or diff ONLY when the brief explicitly asks for it.
PR review with inline findings (fan-out)
When the brief hands you a LIST of findings (each with path, a line or startLine/endLine,
severity, body, optional code suggestion) rather than one review body, post them as PER-LINE
inline comments - never one consolidated comment:
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.
- 2d ago First seen · 153 lines · 302 tokens per session scan A 592bf8bee1e7
github-operator is an agent published in the GitHub repository Viindoo/odoo-mcp-client (8 stars, last pushed 8d ago), licensed MIT. It adds 302 tokens to every session and 2,739 once invoked, about $0.0015 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.