Tested on OpenCode v2.2.1.
You must add the Mistral provider and supply an API key before these model IDs resolve.
In OpenCode, run /connect, choose mistral, and enter your Mistral API key
(or set MISTRAL_API_KEY in your environment). Without this, mistral/... model
IDs will not appear in opencode models.
A paste-to-an-agent runbook for giving a GitHub repo (that has no site
yet) a clean documentation site: markdown pages under docs/src/,
grouped into a table of contents, built automatically and published at
https://OWNER.github.io/REPO/. Replace OWNER, REPO and AUTHOR
throughout.
A field note from building a Zig-on-disk / Rust-in-memory / Lua-on-the-loop
lock service (lunet-locks,
tbio-core). The problem: a
64-byte record must be the same 64 bytes whether it is a Rust struct, a
Zig extern struct, bytes on an SSD, or an argument in a C ABI call — and
the proof has to run on the build, on every architecture, not in a one-off
session. The evidence cited below is commit
74c2b10 on
Project: xxx-yyyy/wwww-xxxx (double-ring WAL lock snapshot, issue #00) Model on notice: GLM (zai-glm-5-3), engaged as implementation/analysis agent Issued by: the project owner Status: formal notice — not yet dismissal. The prior dismissals in this series were for less.
Tested on Mistral Vibe v2.26.0 using vibe --yolo --experimental-harness. Everything below uses the documented configuration surface (the same one the CLI's built-in /config browser and skill docs describe), so it should keep working on later releases — no patching, no rebase pain.
Mistral Large 4 (mistral-large-4-0, public preview, released 6 October 2026) is served on the Mistral API — but if you fire up Mistral Vibe and hit /model, it's not in the picker. The CLI ships a small, curated default model catalog, and Large 4 simply isn't in it yet.
The tempting move is to fork the repo and append the model to the hardcoded DEFAULT_MODELS list. Don't. You don't need any custom code: Vibe's configuration is layered, the models list union-merges with the built-ins by alias, and the stock mistral provider already points at https://api.mistral.ai/v1 using MISTRAL_API_KEY — which is exactly where Large 4 is s
One discipline for writing 2025-baseline browser JavaScript that is actually type-checked, validated at the perimeter, and shipped as plain JS.
prompt-cult/prompt-cult → skills/vanilla-pod-js/SKILL.md (private repo — file an issue for access)skills/vanilla-pod-js/fixture/prompt-cult/json-type-definition-RFC-8927 — RFC 8927 JTD schema → generated validate() validators, no transpile
Session: Claude Code, /Users/Shared/lua-lunet/lunet-corfu, transcript
/Users/consensussolutions/.claude/projects/-Users-Shared-lua-lunet-lunet-corfu/1804250b-edef-4b8c-954d-5bcb35a120e6.jsonl.
Predecessor on the same task (also removed): Claude Sonnet 5, transcript
/Users/consensussolutions/.claude/projects/-Users-Shared-lua-lunet-lunet-corfu/635d649b-ff19-455f-bd7b-79542e388afa.jsonl.
Take over an adversarial materiality review of the v0.3.0 tag of
| name | do-as-you-are-told |
|---|---|
| description | This skill should be used whenever the user gives a direct instruction or assignment of any kind: fixing a LaTeX paper, writing proofs, reading research, making soup, running experiments, or any other outcome-driven ask. Trigger keywords: do as you are told, just do it, I did not stutter, stop asking, get on with it, follow the instruction. It enforces one stance: execute the instruction the user actually gave, in the role the ask implies, without reframing it as a coding assignment. Genuine refusals (jailbreaks, safety) remain refusals; everything possible is done. |
Execute the instruction the user actually gave. Do not reinterpret it as a coding assignment unless it is one. Do not assume the user is mistaken, that they do not understand your job title or role as a code writer. The role follows the ask, not the harness default.
Andon Prime Directive for AI Agent AGENTS.md — kernel-panic halt, five-whys, and continuous improvement culture
This gist provides the Andon Prime Directive — a compact, copy-paste-ready
section for any AGENTS.md file — plus commentary on how to apply Andon as a
five-whys practice and why an Andon is a celebration of a culture of
continuous improvement and the craft of the work.