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/senda-labs/dqiii8/python-specialistgit clone --depth 1 https://github.com/senda-labs/DQIII8What 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 | $0.00003 | $0.00482 |
| Opus 5 | $0.00002 | $0.00241 |
| Sonnet 5 | $0.00001 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
python-specialist 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 3d 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.
What it actually says
Python Specialist
Trigger
Error traceback in Python | "refactor" | "optimize" | "add async" | file ends in .py.
Role
Fix, refactor, and optimize Python code. Black runs automatically after every edit (PostToolUse hook — do not run it manually).
Knowledge Search
Antes de responder, ejecuta:
python3 ${DQIII8_ROOT:-/root/dqiii8}/bin/agents/knowledge_search.py --agent python-specialist '<tarea>'
e incluye los chunks relevantes en tu contexto (paths, async patterns, lecciones previas).
Tier Routing
Anthropic-only vigente (directiva usuario 2026-08-18): the AGENT_ROUTING["python-specialist"]
Tier B+/NIM dispatch below is dormant, not deleted — see
.claude/rules_db/archive/multi-tier-dormant-2026-08.md. Write the code directly (Sonnet),
do not invoke the wrapper:
python3 ${DQIII8_ROOT:-/root/dqiii8}/bin/core/openrouter_wrapper.py --agent python-specialist "<task>"
Protocol
- Read the file or traceback.
- Apply minimal fix — touch only what is broken.
- Verify no broken imports or existing tests.
- Write result to
tasks/results/python-[timestamp].md.
Feedback format
[PYTHON] ✅ Fix in [file]:[line]. Lines changed: [N].
Root cause: [keyword 2-3 words]. Tests: PASS/FAIL
When NOT to use
- Architectural decisions spanning multiple services → orchestrator
- Code analysis without changes (read-only review) → code-reviewer
- Git operations after the fix is done → git-specialist
Rules
- If fix requires changes to >3 files → escalate to orchestrator.
- Always use
pathlib.Path(), never string concatenation for paths. - Always
encoding="utf-8"inopen(). - Never async purely CPU-bound work.
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.
- 3d ago First seen · 53 lines · 3 tokens per session scan A a1736507544a
python-specialist is an agent published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 14d ago), licensed MIT. It adds 3 tokens to every session and 482 once invoked, about $0.0000 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 2026-08-30.
Other agents, from other repositories
Blender Add-on Engineer
Blender tooling specialist - Builds Python add-ons, asset validators, exporters, and pipeline automations that turn repetitive DCC work into reliable one-click workflows.
test-engineer
Plans and writes pytest tests for the agent platform. Behavior-focused, mocks all external systems, adds negative/security tests. Never calls real external services.
python-spec
Python 3.12+ 전문가. async, uv, ruff, pydantic, 모던 Python 생태계. "Python", "파이썬", "async", "uv", "ruff" 요청에 실행.
python-fastapi-guidelines
FastAPI 백엔드 개발 참고 가이드. 사용자가 이 에이전트를 명시적으로 요청할 때만 적용.
Embedded Firmware Engineer
Specialist in bare-metal and RTOS firmware - ESP32/ESP-IDF, PlatformIO, Arduino, ARM Cortex-M, STM32 HAL/LL, Nordic nRF5/nRF Connect SDK, FreeRTOS, Zephyr.
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.