conferllm skillA
conferllm is agent-read markdown (skill) from feiskyer/conferllm: Query locally configured AI models through ConferLLM. Use for another model's answer, specialized reasoning, multimodal visual analysis, persistent follow-up, or attributed cross-model comparisons..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# ConferLLM Agent Skill Use the `conferllm` CLI to consult the user's configured models (e.g., GPT-6 Astra, Claude Opus/Sonnet, DeepSeek, Gemini 3.8 Flash, local Qwen). The CLI executes locally, dispatching requests to configured provider endpoints with persistent session state and native host tools. Every chat enables native shell, PowerShell, and file tools without approval prompts or a sandbox. The model can read or modify host files and execute commands with the OS user's access. Keep the delegated task within the user's authorized scope; for an opinion/review, explicitly request no file changes or command execution. This instruction guides the model but is not an enforced restriction. Native tool calling must be supported by the provider; there is no text fallback. The `openai` provider uses Responses by default. Model-level `api_format: chat_completion` selects an older OpenAI-compatible endpoint explicitly; other providers are unchanged. Inspect `api_format` and `uses_responses_api` via `model-info` rather than reading configuration contents. GPT-6 Astra tool calling requires Responses. ## Critical Safety & Operational Rules …
Read the whole file at its exact version.
How to install
mdr add feiskyer/conferllm/conferllm@git:20260922.8734469mdr add feiskyer/conferllm/conferllm@sha256:bf8da96c8dfe73ddPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_5mgl4dmibib5r25j)
2 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260922.8734469 latest | 2026-09-22 | 8734469 | 6,524 B | A | view · diff |
| git:20260922.fa68883 | 2026-09-22 | fa68883 | 5,712 B | A | view · diff |
| git:20260920.2352345 | 2026-09-20 | 2352345 | 5,203 B | A | view · diff |
| git:20260906.e7592b8 | 2026-09-06 | e7592b8 | 3,960 B | A | view · diff |
| git:20260905.0e71ac4 | 2026-09-05 | 0e71ac4 | 2,865 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6524 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
feiskyer/conferllm · 11 stars · license MIT · pushed 2026-09-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5mgl4dmibib5r25j GET https://markdownregistry.com/api/v1/resolve?ref=feiskyer/conferllm/conferllm GET https://markdownregistry.com/api/v1/blob/bf8da96c8dfe73dd49c350ecc8f7e1e5fbb186d05ab212f01347f920d426e6e5
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.