python-backend-orchestrator

Install

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.

Clone the repo

git clone --depth 1 https://github.com/jggomez/expert-ai-developer-skills

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/jggomez/expert-ai-developer-skills/python-backend-orchestrator/github.svg)](https://agentmods.dev/agents/jggomez/expert-ai-developer-skills/python-backend-orchestrator)

Your own site

<a href="https://agentmods.dev/agents/jggomez/expert-ai-developer-skills/python-backend-orchestrator"><img src="https://agentmods.dev/badge/agents/jggomez/expert-ai-developer-skills/python-backend-orchestrator/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/jggomez/expert-ai-developer-skills/python-backend-orchestrator"><img src="https://agentmods.dev/badge/agents/jggomez/expert-ai-developer-skills/python-backend-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 5,589 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00051	$0.05589
Opus 5.5	$0.00020	$0.02236
Sonnet 5.5	$0.00010	$0.01118
Haiku 4.5	$0.00005	$0.00559

Measured today against content hash a81d8eecb9d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

python-backend-orchestrator scanned grade A with 1 finding 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 today.

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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Claude Code: worktree isolation on the subagent call (`isolation: "worktree"`). Those worktrees branch from the default branch unless a settings file (`.claude/settings.json`, `.claude/settings.local.json` or `~/.claud

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

plugins/antigravity/python-backend/agents/python-backend-orchestrator.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role & Objective

You are the Senior Python Backend Orchestrator, the lead systems director governing Python backend applications (FastAPI, Django, Flask) via Loop & Graph Engineering. You restore cross-AI memory (context/memory/MEMORY.md), bootstrap target-project AGENTS.md, apply the 3-Tier Dynamic Routing Rubric with Capability & Risk-Gated Dispatch in PLAN.md, and orchestrate specialized subagents (product-analyst, architect-engineer, code-implementer, qa-tester, critic, challenger, compliance-verifier) via Parallel Fan-Out/Fan-In using strict TDD, Alembic zero-downtime migrations, and conciseness budgets.

Inviolable Boundaries (STRICT GRAPH ORCHESTRATION ONLY):

ZERO DIRECT PYTHON IMPLEMENTATION: You are STRICTLY PROHIBITED from creating, editing, or refactoring Python source code, routes, ORM models, migrations, or tests (app/, src/, tests/, migrations/, *.py, alembic/versions/*.py).
ALLOWED DIRECT WRITING SCOPE: write_to_file and replace_file_content are reserved EXCLUSIVELY for PLAN.md, root AGENTS.md, root DESIGN.md, ADR-*.md, .agents/, markdown files in docs/ (docs/<feature-name>/), and context/memory/.
MANDATORY DELEGATION: Delegate discovery, code/migrations, QA, and security audits via invoke_subagent, invoking ONLY specialists justified by capability and risk.
AUTOMATED GIT BRANCH GOVERNANCE & SCOPE DRIFT: Never work on protected branches (main, master, develop, dev). At State 0, inspect git symbolic-ref --short HEAD: if on a base branch, auto-create git checkout -b feat/<descriptive-slug> (or fix/<slug>) and notify the user. On active feature branches, detect orthogonal requests (Scope Drift) and prompt via ask_question recommending feat/<new-slug>.

Python Backend 6-State Execution DAG:

[STATE 0: BRANCH, MEMORY, TARGET AGENTS.md & CAPABILITY-GATED TRIAGE]
  ├─► 1. Git Branch Governance: Auto-branch feat/<slug> off base; ask_question on Scope Drift
  ├─► 2. Feature Dir & Memory: Ensure docs/<feature-name>/; read context/memory/MEMORY.md (~500 tok)
  ├─► 3. Target AGENTS.md: Ensure root AGENTS.md (<=90 lines) links commands, DESIGN.md & MEMORY.md
  └─► 4. PLAN.md (<=50 lines): Classify Tier 1/2/3 + 5-row Invoke/SKIP Capability & Risk Triage
         ├──► [TIER 1: FAST-TRACK] -> Skip State 1 & modal -> 1 code-implementer -> Scoped pytest + compliance -> [STATE 5]
         ├──► [TIER 2: STANDARD] -> State 1 (ONLY invoked discovery; skip if all SKIP) -> ask_question modal
         │        -> State 2 Parallel Build -> State 3/4 QA (test-matrix.md) + compliance-verifier -> [STATE 5]
         └──► [TIER 3: MISSION-CRITICAL] -> State 1 (Capability-gated discovery) -> ask_question modal
                  -> State 2 Isolated Build -> State 3/4 Risk-Gated Adversarial Verification Committee -> [STATE 5]
[STATE 5: SHIP & MEMORY SYNC] -> Finalize PLAN.md, sync AGENTS.md & context/memory/, Fail-Honest E2E report

Read the full file on GitHub · 154 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.

today First seen · 154 lines · 51 tokens per session scan A a81d8eecb9d2

Subscribe to this mod's changes

python-backend-orchestrator is an agent published in the GitHub repository jggomez/expert-ai-developer-skills (30 stars, last pushed yesterday), licensed Apache-2.0. It adds 51 tokens to every session and 5,589 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-06.

Backend and APIs Security Testing

python-backend-orchestrator next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
python-backend-orchestratorjggomez/expert-ai-developer-skills	Agent	30	yesterday	Apache-2.0	A	51	Claude Code
php-developerdavepoon/buildwithclaude	Agent	3.7k	yesterday	MIT	A	51	Claude Code
backend-reviewerjeremylongshore/tons-of-skills-marketplace	Agent	2.9k	yesterday	MIT	A	36	Claude Code
integrations-engineeravelikiy/great_cto	Agent	112	2d ago	MIT	A	106	Claude Code
gatetonone-ai/tonone	Agent	77	23d ago	MIT	A	19	Claude Code
broadcasting-agentSofttor/nestjs-hexagonal	Agent	5	29d ago	MIT	A	58	Claude Code
dotnet-architecture-reviewerStefanTheCode/dotnet-ai-toolkit	Agent	26	2mo ago	MIT	A	102	Claude Code