docs(agents): rely on quest context for shared rules

.claude/rules/prompting.md

@@ -2,8 +2,7 @@
 paths:
   - "**/AGENTS.md"
   - "CONTRIBUTING.md"
-  - "PROMPTING.md"
   - ".claude/skills/**"
 ---
 
-Before editing this file, read `PROMPTING.md` at the repository root and apply it.
+Before editing this file, follow Prompting in `quest context`.

.claude/skills/quest-merge/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: quest-merge
-description: Queue a reviewed PR to land, or send it to /quest-iterate.
+description: Queue a PR to land, running /quest-iterate first when it needs work.
 ---
 
 Run `quest skill merge` and follow its output.

.claude/skills/quest-review/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: quest-review
-description: Review a PR's branch locally with the other vendor's model, then mark it ready for review.
+description: Review a PR's branch locally with a model that wrote none of it, then mark it ready for review.
 ---
 
 Run `quest skill review` and follow its output.

.claude/skills/quest-unblock/SKILL.md

@@ -0,0 +1,7 @@
+---
+name: quest-unblock
+description: Walk the maintainer through every quest and draft PR waiting on them, and clear waits that have resolved.
+---
+
+Run `quest skill unblock` and follow its output.
+If `quest` is not installed, follow https://github.com/moq-dev/quest/blob/main/SETUP.md first.

AGENTS.md

@@ -1,67 +1,24 @@
 rust2 holds Rust tools that take Rust somewhere else: to TypeScript through an own rustc driver, to any language through a fork of UniFFI, and to faster builds for a pure-Rust subset.
 Each project lives in its own top-level directory; the [quest tree](quest/README.md) says what each is doing now.
 
-# Context
-
-- Read `CONTRIBUTING.md` when dealing with PRs.
-- Read `PROMPTING.md` before instructing other agents via context, memory, plans, or reviews.
-- Before editing, read each `AGENTS.md` along the path from the root to the file. Use `rg --files -g AGENTS.md` to find them.
-
 # Required
 
-- Pull the latest origin changes before working.
-- Dig into the root cause and fix it at the source. Never work around a fixable bug with a retry, sleep, or timeout, nor pass a flaky test by loosening its assertion.
-- Fail loud and early. An unsupported construct or malformed input is a compile error with a source span, never a warning, a silent fallback, or a runtime failure. Generated code panics only where the Rust source does.
+- An unsupported construct or malformed input is a compile error with a source span, never a warning, a silent fallback, or a runtime failure. Generated code panics only where the Rust source does.
 - Generated output must match the source's semantics exactly: integer widths and overflow, drop order, laziness, and error paths. Prove it with differential tests against native Rust, not by inspection.
-- Reproduce bugs before fixing them. Tests must be worth their weight long-term: cover edge cases, not old bugs or trivial values.
-- Keep the PR to one problem: no unrelated refactors, formatting churn, or drive-by changes. Fix every instance of that problem in the same PR.
-- Land the ideal implementation now rather than a partial one plus follow-ups; split off only work that is independently landable.
-- Be adversarial: attack your own approach, reports, reviews, and other PRs as hard as anyone else's.
-- When a decision is the maintainer's (API shape, naming, scope) or you are unsure, ask with an interactive prompt of 2-3 options and a recommendation.
-- Every test runs in CI, at least nightly. The merge gate holds only fast, high-signal tests.
-- Never add or change a rule in an `AGENTS.md`, `CONTRIBUTING.md`, or skill without being prompted, and read `PROMPTING.md` first.
-- No em dashes.
-- Match the existing conventions, patterns, and naming when possible.
-- Fix any outdated docs and comments inline.
-- Add the AI marker `(Written by <model>)` to any posts on GitHub, excluding commit messages that contain `Co-Authored-By:` trailers.
-- AI comments carry no maintainer authority and may be challenged.
-- This repo is public: never mention customers, partners, or prospects, or link to private repos.
-
-# Guidelines
-
-- Prefer upstream and maintained crates over hand-rolling. Measure before claiming an improvement over them.
-- Every change needs a consumer that uses it now and is worth its cost; name it in the PR. moq is the first consumer of every project here.
 - Everything is configless, with opinionated names and defaults. Translators take stock crates as they are: no annotations, and no config beyond true platform boundaries. Each config key or source change a consumer needs is a gap to close.
 - A vanity rename, if ever supported, is opt-in and lives inline in source next to the item, never in a config file.
-- Deleting code is better than adding code.
-- Comments explain the non-obvious why, never the history.
-- New dependencies use the newest stable version. Do not bump package versions unless asked.
-- Record out-of-scope follow-ups as quests, never GitHub issues.
-- Prefer the net simpler result, and say what was dropped.
-- Say it once, in the fewest words that hold up.
-- Recognize when you're stuck or making minimal progress, and stop early.
-- Add or extend a benchmark for any performance-sensitive change, and measure optimizations instead of relying on intuition.
-
-# Public API
-
-- Report the public API impact of every change in the PR description.
-- Keep things private until a consumer needs them.
-- Never add `foo_with_x`, `foo_checked`, or a compatibility shim. Make the breaking change to `foo` instead.
-- Name by role, not today's implementation. Short names under a module namespace.
-- Document every exported symbol in one plain line.
+- moq is the first consumer of every project here.
+- Prefer upstream and maintained crates over hand-rolling. Measure before claiming an improvement over them.
 
 # Development
 
 PRs target `main`.
 
-Use the Nix dev shell so tooling matches CI.
-direnv loads it automatically, but if not: `nix develop --command ...`.
-
 ```bash
 just check   # Lint what the branch changed, including the quest tree
 just test    # Test what the branch changed
 just ci      # Both, as the merge queue runs them; run before every push
 just fix     # Auto-fix formatting
 ```
 
-Quests: before starting work, run `quest guide` and follow it.
+Quests: before any work, run `quest context` and follow it.

CONTRIBUTING.md

@@ -32,7 +32,7 @@ The admin bypass of `main`'s ruleset is for emergencies.
 
 # Reviews
 
-Review each PR locally with `/quest-review`, as the quest guide describes; merging never waits on an online reviewer, and never request one.
+Review each PR locally with `/quest-review`, as `quest context` describes; merging never waits on an online reviewer, and never request one.
 The PR body's `## Review` record counts as the required review when it names the head being merged, and so does a recorded skip of a change too trivial to review.
 Address online reviewers' findings already posted on that head before merging: fix them, or reply where you disagree.
 

flake.nix

@@ -11,7 +11,7 @@
     # The quest CLI, which also serves the quest guide and skills the stubs in
     # .claude/skills call. Bump the rev to upgrade them.
     quest = {
-      url = "github:moq-dev/quest/dc8008bc9e846a206403b1b738ede19fdd797f5e";
+      url = "github:moq-dev/quest/a3789c7bd7197089d40bb540517b1323f4d40fab";
       inputs.nixpkgs.follows = "nixpkgs";
       inputs.flake-utils.follows = "flake-utils";
     };