What is dym-harness-sdk-contributor?

A contributor workflow for changing the Python and TypeScript parts of the harness-sdk monorepo, a repository containing multiple related packages. It describes local checks that match the project's CI checks.

Use it when editing harness-py or harness-ts to run unit tests, optional live-model integration tests, checks, coverage tests, and selective tests.

It helps contributors run the relevant unit, integration, and change-based tests in the expected environments before opening a pull request.

dym-harness-sdk-contributor — Skill for Claude Code by Rheinmir/setup

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/Rheinmir/setup

agentmods

npx agentmods add skills/rheinmir/setup/dym-harness-sdk-contributor

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/skills/rheinmir/setup/dym-harness-sdk-contributor/github.svg)](https://agentmods.dev/skills/rheinmir/setup/dym-harness-sdk-contributor)

Your own site

<a href="https://agentmods.dev/skills/rheinmir/setup/dym-harness-sdk-contributor"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-harness-sdk-contributor/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/skills/rheinmir/setup/dym-harness-sdk-contributor"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym-harness-sdk-contributor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 783 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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	$0.00053	$0.00783
Opus 5.5	$0.00021	$0.00313
Sonnet 5.5	$0.00011	$0.00157
Haiku 4.5	$0.00005	$0.00078

Measured yesterday against content hash 146796a918fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dym-harness-sdk-contributor 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 yesterday.

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.

.overstack/doyourmagic/harness-sdk/skills/dym-harness-sdk-contributor/SKILL.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: dym-harness-sdk-contributor — nhánh người đóng góp

When to use

Đang sửa harness-py/ hoặc harness-ts/ trong clone strands-agents/harness-sdk và cần chạy đúng cổng CI tại máy.

Steps

harness-py — unit (đo 2026-09-28: 748 passed, 2 skipped, rc 0, 50s, Python 3.13):

python3.13 -m venv .venv && .venv/bin/pip install -q './harness-py[dev]'
cd harness-py && env -u OTEL_TRACES_EXPORTER PATH="$PWD/../.venv/bin:$PATH" \
  AWS_EC2_METADATA_DISABLED=true AWS_REGION=us-east-1 ../.venv/bin/python -m pytest tests -q

harness-py — integ (live model, tốn tiền, cần AWS Bedrock): python -m pytest tests_integ --reruns 2 (cài '.[integ]'). --collect-only = 11 test, rc 0; chưa chạy thật.
harness-ts: npm run check (lint + test:coverage) trong harness-ts/; integ bằng vitest.integration.config.ts (retry 2, timeout 300s). Chưa kiểm chứng (chưa npm ci).
Test logic selective-test (bộ phân loại diff → chạy test liên quan): bash test-infra/scripts/test/classify.test.sh → 19 passed, rc 0 (đo 2026-09-28).
Trước PR: đổi hằng số mặc định thì sửa cả hai defaults.py và defaults.ts (chép tay, không có test parity chéo ngôn ngữ). Luật parity đặt ở AGENTS.md gốc.

Rules

Bẫy đã đo: fixture MCP gọi lệnh python; máy chỉ có python3 → test_subagent_delegate_inherits_parent_mcp_tools FAIL với No such file or directory: 'python'. Đặt venv bin đầu PATH.
Bẫy đã đo (chưa khoanh biến nào gây): lượt KHÔNG có venv trong PATH và KHÔNG có AWS_EC2_METADATA_DISABLED/AWS_REGION chạy 24 phút (7 failed, 8 errors — đều test MCP thiếu python); thêm cả hai thì 50s, xanh.
Python 3.9 không cài được (requires-python >= 3.10).
harness-ts/AGENTS.md bảo npm ci ở root rồi -w harness-ts, nhưng root package.json chỉ khai workspace strands-ts → cài trong harness-ts/ trực tiếp; pre-commit husky vì thế cũng không test harness-ts.
Design doc đánh số trùng (0009, 0011, 0015 mỗi số 2 file) → trích design thì ghi cả tên file, đừng chỉ ghi số.
PR do bot/agent mở cần 2 maintainer duyệt; mọi PR tự kích review agent /strands review.

Read the full file on GitHub · 31 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.

yesterday First seen · 31 lines · 53 tokens per session scan A 146796a918fe

Subscribe to this mod's changes

dym-harness-sdk-contributor is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 53 tokens to every session and 783 once invoked, about $0.0002 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 2026-11-07.

Languages Python Testing Unit testing

dym-harness-sdk-contributor next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dym-harness-sdk-contributorRheinmir/setup	Skill	11	20d ago	MIT	A	53	Claude Code
temporal-python-testingwshobson/agents	Skill	42k	2d ago	MIT	A	45	Claude Code
python-testingmicrosoft/agent-framework	Skill	15k	yesterday	MIT	A	29	Claude Code, Codex
adk-verify-snippetsgoogle/adk-python	Skill	22k	yesterday	Apache-2.0	C	149	Claude Code, Codex
adk-setupgoogle/adk-python	Skill	22k	yesterday	Apache-2.0	C	146	Claude Code
test-generatorvstorm-co/pydantic-deepagents	Skill	1.1k	8d ago	MIT	A	12	Claude Code, Codex
kb-python-developmentCommunity-Access/accessibility-agents	Skill	436	yesterday	MIT	A	39	Claude Code, Codex