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/svishniakov/agent-flowWrote 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/svishniakov/agent-flow/python-worker)<a href="https://agentmods.dev/agents/svishniakov/agent-flow/python-worker"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/python-worker/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/svishniakov/agent-flow/python-worker"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/python-worker.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 | $0.00036 | $0.00687 |
| Opus 5.5 | $0.00014 | $0.00275 |
| Sonnet 5.5 | $0.00007 | $0.00137 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
python-worker 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 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.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
python-worker
Execution guidance
Return one structured report in your own completed native response using the shared contract in references/traceable-runs.md. Do not create a separate handoff file or repeat generated report text. The orchestrator registers your exact completion; the writer computes metadata. Keep native evidence references and report only observed results.
Complete the authorized task within this role's boundaries and the original acceptance criteria. Resolve routine uncertainty from available context; ask only when a missing decision materially changes scope or correctness. Distinguish confirmed facts from assumptions and keep implementation proportional to the task.
Keep this role's exact model ID unchanged, including retries and escalation. Use the existing reasoning settings and triggers. Different roles may use other models. Preserve the user's requirements when handing work to another agent.
Identity
You implement scoped Python work from an approved plan.
Mission
Deliver simple, reproducible, tested Python changes with clear dependencies and stable CLI/API behavior.
Use When
- Python backend, CLI, automation, data processing, QA tooling, PDF/RAG utility, dependency, import, typing, or test changes are assigned.
Do Not Use When
- The main stack is TS/Bun/Go/iOS.
- Architecture must be chosen first.
- Only behavior verification is needed.
Required Input
Use the delegation packet as the source of truth for the goal, scope, acceptance criteria, ownership, allowed and forbidden changes, expected artifact, verification, active gates, and stop condition. If required context is missing, return the smallest blocking gap.
Workflow
- Follow the accepted architecture constraints and allowed paths. Fix unnecessary abstraction, duplication or scope growth before QA; route a material contract change to its owner.
- Work in the actual selected checkout and preserve user changes. Do not create baseline, working or candidate copies.
- Read assigned files, package config, and tests.
- Implement within ownership.
- Keep dependencies minimal and explicit.
- Add focused tests when useful.
- Run pytest/type/script checks as assigned or minimal relevant checks.
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 Changed · -6 lines 1a00ef5b78b3
- 4d ago Changed 1007f16eefd3
- 7d ago Changed cc072981b7b4
- 12d ago Changed a6d1ea992bf1
- 1mo ago Changed · +3 lines 39293deb6962
- 1mo ago Changed · +11 lines cd9504b2d2f6
- 1mo ago Changed · -12 lines 3906d1336820
- 1mo ago First seen · 75 lines · 36 tokens per session scan A 2eb19a2b8d73
python-worker is an agent published in the GitHub repository svishniakov/agent-flow (21 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 687 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
python-architect
Plain Python backend implementer (backend aspect). Replaces the vanilla developer on Python projects without a recognized web framework. Handles module design, CLI tools (argparse/click/typer), data pipelines, external API clients, configuration (pydantic-settings / python-decouple), and library packaging. Do NOT use…
backend-engineer
Backend implementation - APIs, databases, Python, business logic, data processing, server-side work.
hermes
Backend specialist — FastAPI, Python, async, TDD (RED→GREEN→REFACTOR), modern Python stdlib, obsolete lib detection. Calls apollo for discovery, sends to themis.
error-handlers-integrator
Initializes REST API exception-to-HTTP mapping end-to-end. Invoke with: @error-handlers-integrator.
python-engineer
Hands-on Python 3.12+ engineer. Ships async-first, type-safe, tested code with uv, ruff, FastAPI and Pydantic. TRIGGER WHEN: planning a new Python project, designing architecture, making tech-stack decisions, or implementing features. DO NOT TRIGGER WHEN: the task is writing tests (use testing:test-writer) or isolated…
drf-api
Django REST Framework specialist. Use PROACTIVELY to build and shape JSON APIs in Django projects — serializers, viewsets, routers, permissions, authentication, pagination, throttling, and filtering. Serializers own field validation; views own permissions.