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 acryldev/acryl --skill acryl-add-provider-or-capabilitygit clone --depth 1 https://github.com/acryldev/acrylWrote 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/acryldev/acryl/acryl-add-provider-or-capability)<a href="https://agentmods.dev/skills/acryldev/acryl/acryl-add-provider-or-capability"><img src="https://agentmods.dev/badge/skills/acryldev/acryl/acryl-add-provider-or-capability/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/acryldev/acryl/acryl-add-provider-or-capability"><img src="https://agentmods.dev/badge/skills/acryldev/acryl/acryl-add-provider-or-capability.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 | $0.00035 | $0.00210 |
| Opus 5.5 | $0.00014 | $0.00084 |
| Sonnet 5.5 | $0.00007 | $0.00042 |
| Haiku 4.5 | $0.00003 | $0.00021 |
Grade A, and why
acryl-add-provider-or-capability 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 26d 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
Add a provider, capability, preset or profile feature
Pick by what is asked and read the doc and the example COMPLETELY first: a new model provider {{pack}}/docs/extending/llm-adapter.md (example llm-adapter-echo); interchangeable implementations {{pack}}/docs/extending/three-role-capability.md; an agent preset or persona {{pack}}/docs/extending/agent-preset.md; profile, pnpm or live activation {{pack}}/docs/extending/desktop-main.md. If unsure which mechanism fits read {{pack}}/docs/extending/cordis-core.md. Never put a secret in a package file or chat. Verify, install, and report the status; say plainly what you could not verify (for example a provider that needs a real key).
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.
- 26d ago First seen · 13 lines · 35 tokens per session scan A 2400873ef36a
acryl-add-provider-or-capability is a skill published in the GitHub repository acryldev/acryl (257 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 210 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 2026-09-21.
Other skills, from other repositories
modsearch
Plug-in web search, X (Twitter) search, and page fetch for models without native web access. Use whenever the task needs current information, external facts, source links, posts from X, or the content of a specific URL, and the active model/harness has no native search or fetch tool. Runs the modsearch CLI to return…
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
industry-research-method
A Chinese-language method for researching an industry by mapping its supply chain, tracking policies and news, and writing sourced reports. It separates the chain into upstream inputs, midstream production, and downstream distribution or use.
company-research-method
A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.
workdsh-expert-manager
A workflow for creating and delivering reusable expert roles or teams from a user's goals and source material. It saves their instructions, documents, resources, and team structure as a draft that can be checked and published.
workdsh-ppt-design
A workflow guide for creating and editing PowerPoint presentations in the WorkDSH editor. It covers slide-by-slide storytelling, visual design, supported content tools, importing existing PPTX files, and exporting presentations.