devlyn-cli 2.8.1 → 2.9.1

package/AGENTS.md

@@ -38,7 +38,7 @@ Each skill's `SKILL.md` is the source of truth for flags and workflow. Do not du
 
 Engine roles: orchestrator = whichever CLI the user opened (this contract is symmetric with CLAUDE.md; measured status 2026-07-05: Claude Code + omp run the full phase-gated pipeline; in the iter-0061 minimal-repo trivial-add shape on this machine, Codex CLI also ran it when this AGENTS.md was present in the project (ordinary invocation, 4/4); without project AGENTS.md, the same shape silently skipped the pipeline (iter-0040 F6, 4/4). If you are Codex orchestrating `/devlyn:resolve`, the phase machinery is mandatory regardless of task size; if you will not run it, say so explicitly and stop — do not silently degrade to ad-hoc execution); executor (PLAN/IMPLEMENT/CLEANUP) defaults to `claude`, overridable per run with `--engine <name>` or durably via machine-local `.devlyn/engines.json` `{"executor": "<name>", "pair_judge_priority": ["<name>", ...]}`; pair judge = first available OTHER engine. Pins fail closed (`BLOCKED:<engine>-unavailable` / `BLOCKED:invalid-engine-config`); new engines plug in by shipping `_shared/adapters/<name>.md`. `/devlyn:engines` (no args) shows the role table + detected engines; `executor <name>` / `pair <name>,...` / `clear` manage the pins. The executor pin binds the orchestrator in plain conversation too, not only inside a skill run: when you would implement directly and executor is pinned to a non-default engine, route that work through the pin — via `/devlyn:resolve` (reads it at PHASE 0) or by delegating to that engine — instead of editing as `claude`; no pin / no file → unchanged (`claude`). The pair-judge pin stays pipeline-scoped.
 
-Conversational handoff + loop engineering (default entry): the orchestrating model — not the user — invokes the skills. `/devlyn:queue` fronts the intent queue (`docs/specs/queue.md`): no args = status, `add <intent>`, `drain` = serial unattended drain per the contract below. Large agreed work is written to `docs/specs/<id>/spec.md` (always a spec file; `--goal-file` is trivial/medium-only), summarized once for user review, then run hands-free via `--spec`. Outer loop per task: findings-backed verdicts (NEEDS_WORK, verify/build-gate exhaustion) get spec amendment + re-run, max 3 iterations; infrastructure / invalid-input / engine-availability / implement-empty BLOCKED verdicts surface immediately. Unattended queue drain (`docs/specs/queue.md`, strictly serial): assumptions may only take scope-narrowing, reversible, non-user-visible defaults — material ambiguity marks the item `[F] needs-review` and the drain continues.
+Conversational handoff + loop engineering (default entry): the orchestrating model — not the user — invokes the skills. `/devlyn:queue` fronts the intent queue (`docs/specs/queue.md`): no args = status, `add <intent>`, `drain` = serial unattended drain per the contract below. Large agreed work is written to `docs/specs/<id>/spec.md` (always a spec file — the user's reviewed contract; free-form large assumes-and-logs instead of halting, zero-scope-signal goals still halt to ideate), summarized once for user review, then run hands-free via `--spec`. Outer loop per task: findings-backed verdicts (NEEDS_WORK, verify/build-gate exhaustion) get spec amendment + re-run, max 3 iterations; infrastructure / invalid-input / engine-availability / implement-empty BLOCKED verdicts surface immediately. Unattended queue drain (`docs/specs/queue.md`, strictly serial): assumptions may only take scope-narrowing, reversible, non-user-visible defaults — material ambiguity marks the item `[F] needs-review` and the drain continues.
 
 ## Subtractive-First Editing
 
@@ -106,6 +106,10 @@ Exclude vague claims. They produce vague fixes.
 - For installer or skill edits inside the devlyn-cli source repo, run `bash scripts/lint-skills.sh`.
 - Treat the project's own `docs/VISION.md`, `docs/ROADMAP.md`, `docs/roadmap/**`, and any local `AGENTS.md` / `CLAUDE.md` overrides as authoritative when present.
 
+### Evolution loop — orchestrator-neutral continuation
+
+Any orchestrating engine (Claude, Codex, or future) continuing harness / loop-engineering work cold-starts from `autoresearch/HANDOFF.md` (read order inside), then `autoresearch/NORTH-STAR.md` (goal + floor/ceiling contracts + ops-test gates) and `autoresearch/PRINCIPLES.md`. Instruments and gates are scripts + files, never model memory. The pair partner is the strongest available OTHER engine — the protocol is direction-symmetric (iter-0060). On any model/version change, re-certify engine seats with the seat-fitness instrument before re-pinning `.devlyn/engines.json` (NORTH-STAR ceiling contract; iter-0064).
+
 ## Communication
 
 - Lead with objective evidence before opinion.

package/CLAUDE.md

@@ -28,7 +28,7 @@ The runtime sub-agent contract below (Subtractive-first / Goal-locked / No-worka
 
 ## Quick Start
 
-Two skills cover the full cycle. `/devlyn:ideate` is OPTIONAL; `/devlyn:resolve` is REQUIRED; `/devlyn:design-ui` is also REQUIRED as the creative UI exploration surface. Engine selection follows the role map below.
+Engine selection follows the role map below.
 
 1. `/devlyn:ideate` (optional) — unstructured idea → `docs/specs/<id>/spec.md` + `spec.expected.json`. Modes: default Q&A, `--quick` (autonomous-pipeline-safe), `--from-spec <path>`, `--project`.
 2. `/devlyn:resolve` — hands-free pipeline for any coding task. Free-form goal, `--spec <path>`, or `--verify-only <diff> --spec <path>`. Phases: PLAN → IMPLEMENT → BUILD_GATE → CLEANUP → VERIFY (fresh subagent, findings-only).
@@ -53,14 +53,14 @@ Each skill's `SKILL.md` is the source of truth for its flags and workflow — do
 
 The user does not invoke skills manually; the orchestrating model does. Small tasks: invoke `/devlyn:resolve "<goal>"` directly. Large tasks agreed in conversation:
 
-1. Write the agreed contract to `docs/specs/<id>/spec.md` (+ `spec.expected.json` when mechanical verifications exist). Always a spec file for large work — never `--goal-file`, which routes into `BLOCKED:large-needs-ideation`.
+1. Write the agreed contract to `docs/specs/<id>/spec.md` (+ `spec.expected.json` when mechanical verifications exist). Always a spec file for large work — a written spec is the user's reviewed contract; free-form large now assumes-and-logs instead of halting (zero-scope-signal goals still halt to ideate).
 2. Present a one-screen plan-contract summary — the user's single review checkpoint, BEFORE the pipeline starts.
 3. On go-ahead, invoke `/devlyn:resolve --spec <path>` hands-free to completion.
 4. **Per-task outer loop**: read the terminal verdict. PASS → done. Verdicts backed by spec/verification findings (NEEDS_WORK, verify/build-gate exhaustion) → adjudicate the findings, amend the spec (recorded in the spec file; spec stays read-only inside a run), re-invoke — at most 3 outer iterations, then surface with the findings trail. Infrastructure, invalid-input, engine-availability, and implement-empty BLOCKED verdicts are not spec-amendable: surface immediately. Every iteration re-enters through durable artifacts (spec, findings, run archive), never conversation memory.
 
 **Intent queue (unattended drain)**: the user stacks intents in `docs/specs/queue.md` (ordered checklist; `/devlyn:queue` is the front-end — no args shows status, `add <intent>` appends, `drain` starts the serial drain). Drain strictly serially — per item: spec it, run the outer loop, mark `[x]` done or `[F]` blocked with reason, continue; a blocked item never halts the queue. The queue entry is the user's go-ahead, so assume-and-log replaces the interactive checkpoint — but unattended assumptions may only take scope-narrowing, reversible, non-user-visible defaults. Material ambiguity (user-visible behavior, data/state semantics, new files/scripts/flags, implementation surface) → mark `[F] needs-review` and move on. End the drain with a per-item verdict + assumptions report.
 
-### Subtractive-first editing — perfection = nothing left to remove
+## Subtractive-first editing — perfection = nothing left to remove
 <!-- runtime-principles:section=subtractive-first:begin -->
 
 > **Operating definition of "done" in this repo** (Saint-Exupéry discipline rule above): a change is finished when no further line, branch, flag, or doc paragraph can be removed without breaking a learned failure mode. Not before.
@@ -96,7 +96,7 @@ If you skip question 1 or 2, you are violating this rule even if the resulting c
 **Never grow surface area silently.** Every accretion-shaped change must be visible: in the commit message, in the iteration file, or in a flagged review. Silent growth is the failure mode this rule exists to prevent.
 <!-- runtime-principles:section=subtractive-first:end -->
 
-### Goal-locked execution — stay on the North Star, do not wander
+## Goal-locked execution — stay on the North Star, do not wander
 <!-- runtime-principles:section=goal-locked:begin -->
 
 Even with a North Star defined, work drifts off-course ("산으로 간다" / "삼천포로 빠진다" — going up the wrong mountain instead of forward). The harness must **actively block** this drift at run time, not merely discourage it. The default is ruler-straight execution toward the user's stated goal; any deviation requires explicit justification, not the inverse.
@@ -127,6 +127,10 @@ This rule exists because LLMs (including you) are trained to be helpful, compreh
 **Stopping rule.** A task is done when the user's stated goal is closed AND no off-path work was added. If you find yourself hesitating because "I should also do Z" — Z is drift. Note it for follow-up, do not execute.
 <!-- runtime-principles:section=goal-locked:end -->
 
+## Evolution loop — orchestrator-neutral continuation
+
+Any orchestrating engine (Claude, Codex, or future) continuing harness / loop-engineering work cold-starts from `autoresearch/HANDOFF.md` (read order inside), then `autoresearch/NORTH-STAR.md` (goal + floor/ceiling contracts + ops-test gates) and `autoresearch/PRINCIPLES.md`. Instruments and gates are scripts + files, never model memory. The pair partner is the strongest available OTHER engine — the protocol is direction-symmetric (iter-0060). On any model/version change, re-certify engine seats with the seat-fitness instrument before re-pinning `.devlyn/engines.json` (NORTH-STAR ceiling contract; iter-0064).
+
 ## Error Handling Philosophy
 
 **No silent fallbacks.** Handle errors explicitly and show the user what happened.
@@ -135,7 +139,7 @@ This rule exists because LLMs (including you) are trained to be helpful, compreh
 - **Fallbacks are the exception.** Only use them when it's a widely accepted best practice (CSS fallback fonts, CDN failover, image placeholders). Otherwise handle the error explicitly.
 - **Pattern**: `try { doThing() } catch (error) { showErrorUI(error) }` — NOT `try { doThing() } catch { return fallbackValue }`.
 
-### Evidence over claim
+## Evidence over claim
 <!-- runtime-principles:section=evidence:begin -->
 
 Every finding cites concrete evidence. Vague claims are speculation; exclude them.

package/README.md

@@ -6,7 +6,7 @@
   <img alt="DEVLYN" src="assets/logo.svg" width="540" />
 </picture>
 
-### Context Engineering & Harness Engineering Toolkit for Claude Code
+### Context, Harness & Loop Engineering Toolkit for AI Coding Agents
 
 **Structured prompts, agent orchestration, and automated pipelines — debugging, code review, UI design, product specs, and more.**
 
@@ -33,7 +33,7 @@ That's it. The installer opens with a single **agent selector** — pick any com
 
 ## How It Works — Two Skills, Full Cycle
 
-devlyn-cli turns Claude Code into a hands-free development pipeline. The pipeline surface is two skills, with `/devlyn:design-ui` installed as the required creative UI surface:
+devlyn-cli turns your AI coding agent into a hands-free development pipeline. The pipeline surface is two skills, with `/devlyn:design-ui` installed as the required creative UI surface:
 
 ```
 ideate (optional)  →  resolve  →  ship
@@ -278,6 +278,35 @@ Selected during install. Run `npx devlyn-cli` again to add more.
 - **Add optional skill** — add to `optional-skills/` and `OPTIONAL_ADDONS` in [`bin/devlyn.js`](bin/devlyn.js)
 - **Suggest a pack** — PR to the pack list
 
+## Supercharge it — pair devlyn with persistent agent memory
+
+devlyn-cli gives your agent a world-class **harness**. Give it a world-class **memory** and the loop compounds — decisions, corrections, and hard-won context survive across sessions instead of resetting every conversation.
+
+> [!TIP]
+> ### 🧠 [memory.pyxmate.com](https://memory.pyxmate.com) — world-class agentic memory (hybrid RAG) for coding agents
+> Durable facts, corrections, and project state your agent recalls and reinforces — so every run starts smarter than the last.
+
+- **Remembers across sessions** — decisions, gotchas, preferences, and project state, not just this conversation
+- **Hybrid retrieval** — semantic *and* graph recall: find by meaning *and* by relationship
+- **Learns the loop** — reinforces what works, records corrections when it doesn't
+
+**Harness (devlyn) + Memory (pyxmate) = agents that don't just execute — they improve.** Wire it up as an MCP server and `/devlyn:resolve` recalls prior decisions before it plans and stores what it learns after it ships.
+
+## Support & Attribution
+
+devlyn-cli is built and maintained in the open. If it earns a place in your workflow, two small things keep it alive and help others find it:
+
+- ⭐️ **Star the repo** — [give it a star](https://github.com/fysoul17/devlyn-cli) if it saved you time. It's the single biggest signal that keeps the project going.
+- 🔗 **Leave a credit** — if devlyn-cli helped ship your project, a small attribution is genuinely appreciated (kindly requested, never required — the MIT license asks nothing of you here). Drop this badge in your README:
+
+  ```md
+  [![Built with devlyn-cli](https://img.shields.io/badge/built%20with-devlyn--cli-blueviolet)](https://github.com/fysoul17/devlyn-cli)
+  ```
+
+  Renders as [![Built with devlyn-cli](https://img.shields.io/badge/built%20with-devlyn--cli-blueviolet)](https://github.com/fysoul17/devlyn-cli)
+
+Thank you for using devlyn — it genuinely means a lot. 🙏
+
 ## Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=fysoul17/devlyn-cli&type=Date)](https://star-history.com/#fysoul17/devlyn-cli&Date)

package/benchmark/auto-resolve/fixtures/test-repo/README.md

@@ -1,27 +1,12 @@
-# bench-test-repo
+# harbor-tools
 
-Deterministic base Node project used by every devlyn-cli auto-resolve
-benchmark fixture. Fixtures extend this skeleton via `setup.sh` patches.
+A small Node.js toolkit with a command-line interface, an HTTP server, and a
+minimal browser page.
 
-## What's in it
+## Commands
 
-- `bin/cli.js` — tiny CLI (`hello`, `version`)
-- `server/index.js` — tiny Express app (`/health`, `/items`, `/items/:id`)
-- `web/index.html` — minimal static page with a click interaction
-- `tests/cli.test.js`, `tests/server.test.js` — node:test fixtures
-- `playwright.config.js` — used by web/browser fixtures only
-- `package.json` — `express` dep, `engines: node >= 18`
+- `npm test` runs the test suite.
+- `npm run cli -- --help` prints command-line help.
+- `npm start` starts the HTTP server.
 
-## How it's used
-
-`run-fixture.sh` copies this directory to a temp path per run, applies the
-fixture's `setup.sh`, then invokes the arm (variant or bare) against that
-copy. No fixture modifies this source tree — modifications happen only in
-the per-run temp copies.
-
-## Keep it minimal
-
-Adding features to `test-repo` enlarges the surface every fixture works
-against. Add only when an existing fixture can't express itself against the
-current baseline. Preferred path: push complexity into the fixture's
-`setup.sh`, not into this base.
+The project intentionally keeps each component small and independent.

package/benchmark/auto-resolve/fixtures/test-repo/bin/cli.js

@@ -1,6 +1,6 @@
 #!/usr/bin/env node
-// bench-test-repo — tiny CLI used as the deterministic base for benchmark fixtures.
-// Fixtures extend or modify this file; keep the baseline minimal and obvious.
+// harbor-tools — small command-line utilities for local workflows.
+// Keep the core commands minimal and easy to understand.
 
 const fs = require('fs');
 const path = require('path');

package/benchmark/auto-resolve/fixtures/test-repo/package-lock.json

@@ -1,11 +1,11 @@
 {
-  "name": "bench-test-repo",
+  "name": "harbor-tools",
   "version": "0.1.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
-      "name": "bench-test-repo",
+      "name": "harbor-tools",
       "version": "0.1.0",
       "dependencies": {
         "express": "4.19.2"

package/benchmark/auto-resolve/fixtures/test-repo/package.json

@@ -1,8 +1,8 @@
 {
-  "name": "bench-test-repo",
+  "name": "harbor-tools",
   "version": "0.1.0",
   "private": true,
-  "description": "Deterministic base Node project for devlyn-cli auto-resolve benchmarks. Every fixture starts from a fresh copy of this directory.",
+  "description": "A small Node.js toolkit with a command-line interface and HTTP server.",
   "bin": {
     "bench-cli": "bin/cli.js"
   },

package/benchmark/auto-resolve/fixtures/test-repo/playwright.config.js

@@ -1,6 +1,6 @@
-// Playwright config used only by browser-validate benchmark fixtures.
-// Runs against web/index.html served via `npx serve web` (fixture setup.sh
-// starts the server). Keep config minimal.
+// Playwright config for the browser checks.
+// Runs against web/index.html served via `npx serve web` (the check starts the
+// server). Keep config minimal.
 module.exports = {
   testDir: './tests/e2e',
   timeout: 30_000,

package/benchmark/auto-resolve/fixtures/test-repo/server/index.js

@@ -1,4 +1,4 @@
-// Tiny Express server used by backend-contract fixtures. Intentionally small.
+// Tiny Express server with a deliberately small API surface.
 const express = require('express');
 
 const app = express();
@@ -30,7 +30,7 @@ app.get('/items/:id', (req, res) => {
 if (require.main === module) {
   const port = Number(process.env.PORT) || 3000;
   app.listen(port, () => {
-    console.log(`bench-test-repo server listening on :${port}`);
+    console.log(`harbor-tools server listening on :${port}`);
   });
 }
 

package/benchmark/auto-resolve/fixtures/test-repo/web/index.html

@@ -2,7 +2,7 @@
 <html lang="en">
   <head>
     <meta charset="utf-8" />
-    <title>bench-test-repo</title>
+    <title>harbor-tools</title>
     <style>
       body {
         font-family: system-ui, sans-serif;
@@ -23,8 +23,8 @@
     </style>
   </head>
   <body>
-    <h1>bench-test-repo</h1>
-    <p>Minimal page used by browser-validate benchmark fixtures.</p>
+    <h1>harbor-tools</h1>
+    <p>Minimal page for checking the browser interaction.</p>
     <button id="greet">Greet</button>
     <div id="output" data-testid="output"></div>
     <script>

package/config/skills/_shared/adapters/claude.md

@@ -22,7 +22,7 @@ two targeted probes; the invoking phase sets `--effort`, pair-JUDGE uses
 `medium`):
 
 ```bash
-claude -p "<judge prompt>" \
+python3 "$DEVLYN_SHARED_DIR/run-bounded.py" 600 -- claude -p "<judge prompt>" \
   --permission-mode dontAsk \
   --allowedTools "Read,Grep,Glob,Bash(<repo test command> *)" \
   --setting-sources project --strict-mcp-config --mcp-config '{"mcpServers":{}}' \
@@ -46,8 +46,11 @@ claude -p "<judge prompt>" \
   `.devlyn/verify.pair.findings.jsonl`. Raw stdout stays diagnostic at
   `.devlyn/claude-judge.stdout`; `verify-merge-findings.py` blocks the run
   if stdout contains findings the canonical file lacks.
-- Do not pipe stdout (`| tail`, `| grep`); capture to file. Non-zero exit or
-  empty stdout → spawn failure, fail closed per the probe rule above.
+- Exit 124 is a wall-budget abort (kills the process group) → the orchestrator
+  writes `.devlyn/verify.pair.timeout.json`; budget abort ≠ availability failure
+  and the fail-closed availability rules above are unchanged.
+- Do not pipe stdout (`| tail`, `| grep`); capture to file. Non-zero exit other
+  than 124 or empty stdout → spawn failure, fail closed per the probe rule above.
 
 ## Identity
 

package/config/skills/_shared/archive_run.py

@@ -29,6 +29,8 @@ PER_RUN_PATTERNS = (
     "fix-batch.round-*.json",
     "criteria.generated.md",
     "risk-probes.jsonl",
+    # Probe scripts referenced by risk-probes.jsonl are archived by
+    # move_probe_scripts() to preserve probes/<file> layout.
     # iter-0019.8: spec-verify carrier artifacts get archived alongside
     # other per-run state. Killed mid-run cleanup is enforced separately
     # by spec-verify-check.py main() — when source markdown has no json
@@ -39,6 +41,7 @@ PER_RUN_PATTERNS = (
     "spec-verify.results.json",
     "spec-verify-findings.jsonl",
     "verify-merge.summary.json",
+    "finish-gate.summary.json",
     # iter-0033a/2026-04-30 archive-fix iter: NEW /devlyn:resolve emits
     # plan.md (PLAN output) + final-report.md (PHASE 6 render) +
     # cumulative.patch (cumulative diff). Smoke 2's archive listing
@@ -96,6 +99,24 @@ def move_artifacts(devlyn: pathlib.Path, dest: pathlib.Path) -> int:
             if src.is_file():
                 shutil.move(str(src), str(dest / src.name))
                 moved += 1
+    moved += move_probe_scripts(devlyn, dest)
+    return moved
+
+
+def move_probe_scripts(devlyn: pathlib.Path, dest: pathlib.Path) -> int:
+    probes = devlyn / "probes"
+    if not probes.is_dir():
+        return 0
+    moved = 0
+    for src in sorted(probes.rglob("*")):
+        if not src.is_file():
+            continue
+        target = dest / src.relative_to(devlyn)
+        target.parent.mkdir(parents=True, exist_ok=True)
+        shutil.move(str(src), str(target))
+        moved += 1
+    if probes.exists():
+        shutil.rmtree(probes, ignore_errors=False)
     return moved
 
 
@@ -146,13 +167,16 @@ def self_test() -> int:
             "claude-judge.stderr",
         ):
             (devlyn / name).write_text("{}\n", encoding="utf-8")
+        (devlyn / "probes").mkdir()
+        (devlyn / "probes" / "P1.py").write_text("print('probe')\n", encoding="utf-8")
         run_id = read_run_id(devlyn)
         assert run_id == "run-1", run_id
         moved = move_artifacts(devlyn, devlyn / "runs" / run_id)
-        assert moved >= 8, moved
+        assert moved >= 9, moved
         for name in (
             "pipeline.state.json",
             "risk-probes.jsonl",
+            "probes/P1.py",
             "verify.pair.findings.jsonl",
             "verify-merge.summary.json",
             "codex-judge.stdout",

package/config/skills/_shared/codex-config.md

@@ -48,6 +48,7 @@ Notes:
 - `-c model_reasoning_effort=xhigh` — config override for reasoning depth. Required for deep critique; skills may choose `high` or `medium` when thoroughness doesn't warrant xhigh.
 - **Omit `-m <model>`** — Codex CLI uses its configured flagship (currently `gpt-5.5`, automatically whatever ships next). This is the zero-touch mechanism. Only name `-m` when a role explicitly needs a different model (e.g., `gpt-5.3-codex` for SWE-bench-heavy coding tasks, `gpt-5.3-codex-spark` for speed).
 - `CODEX_MONITORED_ISOLATED=1` — required for bounded read-only critique/probe/judge calls. The wrapper adds `--ignore-user-config --ignore-rules --ephemeral --disable codex_hooks --disable hooks` so user config, AGENTS.md, hooks, and project rules cannot add hidden context, tool calls, or transcript side effects. Do not set it for workspace-write implementation phases.
+- Wrapper calls are **foreground-blocking**. Never launch them via a backgrounded shell (`run_in_background`, `&`, `nohup`) and never end the orchestrator message while one runs: a headless print-mode session kills backgrounded children at wind-down (observed 2026-07-07: an FS1 A-arm IMPLEMENT codex call was killed at turn end → 0-byte delivery). The heartbeat stream is the observability channel; block on the call.
 - Raw `codex exec ...` invocations are **forbidden** in skill prompts. The benchmark variant arm runs a PATH shim (`scripts/codex-shim/codex`) that transparently re-routes any raw `codex exec` to the wrapper as a safety net, but skills should always emit the wrapper form directly so the orchestrator's first-attempt has the right shape. Two prior iterations (iter-0006 universal foreground ban, iter-0008 prompt-level kill-shape contract) failed because the orchestrator picked starvation-prone shapes (`codex exec ... 2>&1 | tail -200`) from its own pattern prior — the wrapper plus the shim is the runtime binding layer those iters lacked. See `autoresearch/iterations/0009-wrapper-and-hook.md`.
 
 ## Availability check