What is dym-cti-expert-contributor-develop-and-gate?

A contribution guide for developing and checking changes to the cti-expert project. It describes required setup, audit rules, hooks, and tests that changes must pass.

Use it when installing the development environment, enabling the Git pre-commit hook, running the audit script, and validating changes with the project's tests.

It helps catch repository-rule violations and silent failures before a change is accepted.

dym-cti-expert-contributor-develop-and-gate

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-cti-expert-contributor-develop-and-gate

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-cti-expert-contributor-develop-and-gate/github.svg)](https://agentmods.dev/skills/rheinmir/setup/dym-cti-expert-contributor-develop-and-gate)

Your own site

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

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,635 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	$0.00054	$0.03635
Opus 5.5	$0.00022	$0.01454
Sonnet 5.5	$0.00011	$0.00727
Haiku 4.5	$0.00005	$0.00364

Measured yesterday against content hash ee7829059471, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dym-cti-expert-contributor-develop-and-gate 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| `smoke.yml` | clone→install→run trên container ubuntu tối giản (root, không sudo, không sẵn git/curl/python) + macOS/ubuntu runner thường; gate bằng `scripts/smoke-test.sh` |

.overstack/doyourmagic/cti-expert/skills/dym-cti-expert-contributor-develop-and-gate/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: dym-cti-expert-contributor-develop-and-gate — Nhánh đóng góp: sửa chính cti-expert

Vì sao dùng: repo có 6 luật cứng và một engine vendored; vi phạm chúng thường hỏng im lặng chứ không đỏ test. Sinh ra cái gì: một thay đổi đi qua được scripts/audit.sh và toàn bộ test, không làm tụt rào an toàn.

File này độc lập với 01–08. Nhưng đọc 04 trước sẽ giúp — bảng DISPATCH mà bạn phải cập nhật ở đây chính là thứ file đó mô tả.

Cài môi trường dev

git clone https://github.com/7onez/cti-expert.git && cd cti-expert
bash scripts/install-hooks.sh          # hook git pre-commit → leakcheck.sh (BẮT BUỘC mỗi clone)
uv venv && uv pip install -r requirements.txt    # cho §9 của audit + engine test cần SDK

.git/hooks/ không được track, nên install-hooks.sh phải chạy lại ở mỗi clone mới. Không có nó thì RULE 1 chỉ còn một lớp.

Cổng duy nhất: `scripts/audit.sh`

bash scripts/audit.sh

Chạy thật không có .venv → AUDIT: clean, rc=0. Nó gate 9 mục:

§	Kiểm gì
1	leak check RULE 1, hai lượt: diff (cái commit này THÊM vào) + tree (mọi file text đã track)
2	mọi op `DISPATCH` giải được ra một script có thật (RULE 3)
3–4	shim collector vẫn là re-export, chưa bị biến ngược thành bản sao (RULE 4)
5	số `@tool` khớp con số ghi trong `CLAUDE.md`
6	`py_compile` + test ở repo root
7	mọi đường dẫn hook mà `hooks.json` đăng ký còn tồn tại
8	test engine vendored, tập stdlib-only (15 file)
9	test engine cần `claude_agent_sdk` — SKIP nếu không có `.venv`

§1 có hai lượt vì chúng trả lời hai câu khác nhau. Lượt diff chỉ thấy dòng ai đó vừa chạm; một giá trị rò rỉ nằm sẵn trong file không ai mở sẽ sống mãi — đã có 4 giá trị sống sót nhiều tháng đúng theo cách đó. Lượt diff cũng chỉ soi dòng thêm vào: từ chối cả dòng - từng làm cổng tự khoá (cách duy nhất để gỡ một giá trị đã rò là --no-verify, tức cổng đẩy bạn về đúng lối tắt nó sinh ra để chặn).

Read the full file on GitHub · 193 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 · 193 lines · 54 tokens per session scan A ee7829059471

Subscribe to this mod's changes

dym-cti-expert-contributor-develop-and-gate is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 54 tokens to every session and 3,635 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-07.

Git and workflow Testing

dym-cti-expert-contributor-develop-and-gate next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dym-cti-expert-contributor-develop-and-gateRheinmir/setup	Skill	11	20d ago	MIT	A	54	Claude Code
merge-batchdiegosouzapw/OmniRoute	Skill	85k	today	MIT	A	46	Claude Code
prowler-commitprowler-cloud/prowler	Skill	15k	yesterday	Apache-2.0	A	44	Claude Code, Codex
gh-auth-isolationgithub/gh-aw	Skill	5.6k	today	MIT	A	20	Claude Code, Codex
comet-githubrpamis/comet	Skill	3.3k	today	MIT	A	72	Claude Code, Codex
github-skillzeenie-ai/OpenCompany	Skill	1.1k	3d ago	MIT	A	51	Claude Code
re0-mergeLilMGenius/paperthin	Skill	1.4k	today	MIT	A	70	Claude Code