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 skills add Rheinmir/setup --skill dymgit clone --depth 1 https://github.com/Rheinmir/setupWrote 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/skills/rheinmir/setup/dym)<a href="https://agentmods.dev/skills/rheinmir/setup/dym"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym/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/skills/rheinmir/setup/dym"><img src="https://agentmods.dev/badge/skills/rheinmir/setup/dym.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 | $0.00110 | $0.01257 |
| Opus 5.5 | $0.00044 | $0.00503 |
| Sonnet 5.5 | $0.00022 | $0.00251 |
| Haiku 4.5 | $0.00011 | $0.00126 |
Grade A, and why
dym 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: dym — định tuyến domain → bundle tool ngoài
Sinh bởi harness/scripts/dym-sync.py index từ domains: trong hub của từng bundle. Không sửa tay — sửa domains: ở hub rồi chạy lại.
Steps
- Xác định domain của việc đang làm (bảng 1). Nhiều hub cùng domain → đọc bảng 2, chọn theo slug khớp việc; vẫn phân vân → hỏi user một câu.
- Đọc ĐÚNG MỘT hub:
.overstack/doyourmagic/<bundle>/skills/<hub>/SKILL.md, rồi làm theo nó (hub sẽ chỉ tới sub-skill). - Frontend/UI:
hallmarkvẫn là SÀN, bundle chỉ là flavour bên trên.
Bảng 1 — domain → hub
| domain | hub |
|---|---|
| agent | dym-arex-skill · dym-nuwa-skill · dym-ruflo |
| architecture | dym-archify |
| browser | dym-browser-use |
| chart | dym-lieflat-charts |
| computer-use | dym-agent-desktop |
| copy | dym-humanizer |
| design-audit | dym-impeccable |
| desktop | dym-agent-desktop |
| diagram | dym-archify · dym-diagram-design |
| frontend | dym-diagram-design · dym-impeccable |
| macos | dym-agent-desktop |
| orchestration | dym-ruflo |
| playwright | dym-browser-use |
| qa | dym-browser-use |
| report | dym-lieflat-charts |
| research | dym-scientific-agent-skills |
| science | dym-scientific-agent-skills |
| security | dym-cti-expert |
| skill-authoring | dym-arex-skill · dym-nuwa-skill |
| swarm | dym-ruflo |
| threat-intel | dym-cti-expert |
| writing | dym-humanizer |
Bảng 2 — hub → slug
| hub | bundle | domains | slugs |
|---|---|---|---|
dym-agent-desktop |
agent-desktop | computer-use, desktop, macos | drive · install · route · session |
dym-archify |
archify | diagram, architecture | agent-chat-authoring · ci-diagram-gate · cli-authoring-loop · compare-architecture-delta · contributor-build-and-test · install-and-verify · migrate-workflow-v2 · repository-evidence · visual-check-and-preview |
dym-arex-skill |
arex-skill | skill-authoring, agent | cai-dat-disco · cai-thu-vien-skill · chay-viec-researcher · contributor-dong-gop-skill · contributor-phat-trien-cli · creator-paper-to-skills · creator-tao-repo-skill · lenh-chat-trong-tui · tich-hop-ci · xuat-skill-sang-agent-khac |
dym-browser-use |
browser-use | browser, qa, playwright | cloud · qa · repl |
dym-cti-expert |
cti-expert | security, threat-intel | api-keys-and-capabilities · case-pipeline-and-kb · ci-monitoring · cli-dispatcher · contributor-develop-and-gate · install-and-register · investigate-in-claude-code · reports-and-iocs · safety-gates |
dym-diagram-design |
diagram-design | diagram, frontend | authoring-in-chat · brand-onboarding-and-profiles · contributor-gates · import-export-slash-commands · import-extractors-shell · install-and-verify · selfcheck-and-your-ci |
dym-humanizer |
humanizer | writing, copy | contributor-validate-and-release · humanize-files-and-embedded · humanize-pasted-text · install-claude-plugin · install-shell · tune-false-positives |
dym-impeccable |
impeccable | frontend, design-audit | browser-extension-build · chat-commands · ci-integration · contributor-build-and-test · detect-cli-scan · install-into-your-project · tune-detector-ignores |
dym-lieflat-charts |
lieflat-charts | chart, report | browse-templates · chart-request · ci-example · contributor-checks · install · report-request |
dym-nuwa-skill |
nuwa-skill | skill-authoring, agent | contributor-repo-itself · diagnose-then-distill · distill-a-person · fidelity-scorecard · helper-scripts-cli · install · publish-and-get-listed · use-and-update-persona |
dym-ruflo |
ruflo | orchestration, agent, swarm | init · install · route |
dym-scientific-agent-skills |
scientific-agent-skills | science, research | cai-dat-skills · chay-script-bundled-tu-shell · dong-gop-them-sua-skill · dong-gop-validate-test-scan · dung-skill-trong-agent · gate-trong-ci-cua-ban · pin-va-cap-nhat · tham-dinh-truoc-khi-cai |
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 · 56 lines · 110 tokens per session scan A 12b3520230bb
dym is a skill published in the GitHub repository Rheinmir/setup (11 stars, last pushed 20d ago), licensed MIT. It adds 110 tokens to every session and 1,257 once invoked, about $0.0004 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.
dym compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dymRheinmir/setup | Skill | 11 | 20d ago | MIT | A | 110 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |