@xgent-ai/skills 0.3.0 → 0.4.0

package/skills/archify/test/workflow-semantic-contract.test.mjs

@@ -0,0 +1,131 @@
+import { test } from 'node:test';
+import assert from 'node:assert/strict';
+
+import { compileWorkflow } from '../renderers/workflow/workflow-compiler.mjs';
+
+function document(semanticChecks) {
+  return {
+    schema_version: 2,
+    diagram_type: 'workflow',
+    meta: {
+      title: 'Workflow semantic contract fixture',
+      legend: { mode: 'hidden' },
+    },
+    lanes: [
+      { id: 'main', label: 'Main' },
+      { id: 'recovery', label: 'Recovery' },
+    ],
+    nodes: [
+      { id: 'input', lane: 'main', col: 0, type: 'external', label: 'Input' },
+      { id: 'process', lane: 'main', col: 2, type: 'backend', label: 'Process' },
+      { id: 'result', lane: 'main', col: 4, type: 'frontend', label: 'Result' },
+      { id: 'ledger', lane: 'recovery', col: 4, type: 'database', label: 'Ledger' },
+      { id: 'resume', lane: 'recovery', col: 1, type: 'backend', label: 'Resume' },
+    ],
+    edges: [
+      { id: 'start', from: 'input', to: 'process' },
+      { id: 'finish', from: 'process', to: 'result' },
+      { id: 'record', from: 'process', to: 'ledger' },
+    ],
+    ...(semanticChecks ? { semanticChecks } : {}),
+  };
+}
+
+test('semanticChecks rejects an undeclared root instead of accepting an orphan recovery node', () => {
+  const workflow = document({
+    allowedRoots: ['input'],
+  });
+
+  const result = compileWorkflow({ workflow, qualityProfile: 'standard' });
+
+  assert.equal(result.ok, false);
+  assert.ok(
+    result.diagnostics.some((diagnostic) => (
+      diagnostic.code === 'workflow/unexpected-root'
+      && diagnostic.subject?.node === 'resume'
+    )),
+    JSON.stringify(result.diagnostics, null, 2),
+  );
+});
+
+test('semanticChecks rejects a missing required edge with its exact endpoints', () => {
+  const workflow = document({
+    requiredEdges: [{ from: 'ledger', to: 'resume' }],
+  });
+
+  const result = compileWorkflow({ workflow, qualityProfile: 'standard' });
+
+  assert.equal(result.ok, false);
+  assert.ok(
+    result.diagnostics.some((diagnostic) => (
+      diagnostic.code === 'workflow/required-edge'
+      && diagnostic.subject?.from === 'ledger'
+      && diagnostic.subject?.to === 'resume'
+    )),
+    JSON.stringify(result.diagnostics, null, 2),
+  );
+});
+
+test('semanticChecks accepts required reachability through intermediate nodes without changing SVG bytes', () => {
+  const baseline = document();
+  const constrained = document({
+    allowedRoots: ['input', 'resume'],
+    allowedTerminals: ['result', 'ledger', 'resume'],
+    requiredEdges: [{ from: 'process', to: 'ledger' }],
+    requiredPaths: [{ from: 'input', to: 'result' }],
+  });
+
+  const baselineResult = compileWorkflow({ workflow: baseline, qualityProfile: 'standard' });
+  const constrainedResult = compileWorkflow({ workflow: constrained, qualityProfile: 'standard' });
+
+  assert.equal(baselineResult.ok, true, JSON.stringify(baselineResult.diagnostics, null, 2));
+  assert.equal(constrainedResult.ok, true, JSON.stringify(constrainedResult.diagnostics, null, 2));
+  assert.equal(constrainedResult.svg, baselineResult.svg);
+  assert.deepEqual(constrainedResult.receipt, baselineResult.receipt);
+});
+
+test('semanticChecks rejects a required path that is not reachable in authored direction', () => {
+  const workflow = document({
+    requiredPaths: [{ from: 'ledger', to: 'resume' }],
+  });
+
+  const result = compileWorkflow({ workflow, qualityProfile: 'standard' });
+
+  assert.equal(result.ok, false);
+  assert.ok(
+    result.diagnostics.some((diagnostic) => diagnostic.code === 'workflow/required-path'),
+    JSON.stringify(result.diagnostics, null, 2),
+  );
+});
+
+test('semanticChecks rejects an undeclared terminal', () => {
+  const workflow = document({
+    allowedTerminals: ['result', 'ledger'],
+  });
+
+  const result = compileWorkflow({ workflow, qualityProfile: 'standard' });
+
+  assert.equal(result.ok, false);
+  assert.ok(
+    result.diagnostics.some((diagnostic) => (
+      diagnostic.code === 'workflow/unexpected-terminal'
+      && diagnostic.subject?.node === 'resume'
+    )),
+    JSON.stringify(result.diagnostics, null, 2),
+  );
+});
+
+test('semanticChecks reports unknown contract node ids before graph analysis', () => {
+  const workflow = document({
+    requiredEdges: [{ from: 'missing', to: 'resume' }],
+  });
+
+  const result = compileWorkflow({ workflow, qualityProfile: 'standard' });
+
+  assert.equal(result.ok, false);
+  assert.deepEqual(
+    result.diagnostics.map(({ code }) => code),
+    ['workflow/semantic-node-reference'],
+  );
+  assert.equal(result.diagnostics[0].subject.path, '/semanticChecks/requiredEdges/0/from');
+});

package/skills/architect/SKILL.md

@@ -0,0 +1,83 @@
+---
+name: architect
+description: "Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape."
+disable-model-invocation: true
+---
+
+# Architect
+
+Design before implementing. Sketch types, function signatures, class shapes, and module boundaries with `not implemented` bodies and pseudocode. Synthesize across multiple model perspectives, then fill in code against the chosen sketch. If implementation proves the sketch wrong, throw it out and redesign.
+
+## Start
+
+Open a todolist with one entry per phase before starting.
+
+1. Ground
+2. Sketch
+3. Agree
+4. Implement
+5. Scrap
+
+## Phase A: Ground the problem
+
+Build a real mental model of every system the new code touches. Run the **how** skill over the relevant subsystems.
+
+Naming a file isn't grounding. Produce the traced model `how` prescribes. If the design redefines ownership or layering, also run the **why** skill on the existing shape so the rationale becomes a constraint, not a guess.
+
+Skip Phase A only when the work is genuinely greenfield with no surrounding system to integrate.
+
+## Phase B: Sketch
+
+Run the **arena** skill with the design-sketch task and the Phase A grounding artifacts. Pass `references/runner-prompt.md` as each runner's prompt. Each candidate produces a design package shaped per `references/rationale-template.md`.
+
+Take the runners from the `architect runners` line in the `pstack-models.mdc` rule, in place of the `arena runners` line. If the rule or that line is missing, use `claude-opus-5-5-max`, `gpt-5.6-sol-max`, `grok-4.7-xhigh-fast`. Alias and rejected entries follow runner selection in agi-mode's Arena playbook, reached through the **arena** compatibility entry.
+
+Design it twice. Require at least two structurally distinct candidates before synthesis, even when the first looks sufficient. This is the **exhaust-the-design-space** principle skill made concrete. Whole-shape alternatives, not point fixes inside one shape.
+
+Screen every candidate against [`references/design-red-flags.md`](references/design-red-flags.md) before synthesis. Reject or revise shallow modules, information leakage, temporal decomposition, and pass-through methods.
+
+Compare viable candidates on interface depth. Prefer the design that hides more complexity behind a smaller, simpler public surface. A rich interface can keep call chains short by concentrating capability instead of scattering it across layers.
+
+Arena returns one synthesized design package. The synthesis decision populates the rationale's "Synthesis decision" section.
+
+## Phase C: Agree (opt-in)
+
+Default: proceed directly to implementation with the synthesized design. No human checkpoint.
+
+Opt in to a checkpoint when the invoker explicitly asks: "/architect with checkpoint," "stop and show me before implementing," or similar. Then surface the synthesized design and pause for sign-off.
+
+The synthesis can ship as its own commit either way, as the "scaffold first" mode of the **foundational-thinking** principle skill. Planned and scoped breakage during fill-in is fine, per the **outcome-oriented-execution** principle skill. For adversarial pressure on the design before implementing, run the **interrogate** skill on the synthesized sketch.
+
+If the human pushes back on the shape (in a checkpoint or after the fact), treat that as Phase A evidence. Re-ground and re-run Phase B before writing more code.
+
+## Phase D: Implement against the sketch
+
+Replace `not implemented` bodies with code, pseudocode with logic. The synthesized sketch is the contract.
+
+Deviations from the sketch are signal worth surfacing, not friction to absorb silently. If a function needs a parameter the sketch didn't anticipate, ask whether the sketch was wrong, the requirement was missed, or the implementation is overreaching.
+
+## Phase E: Scrap when the architecture is wrong
+
+If implementation keeps producing friction the sketch can't absorb, throw the sketch out. Don't bolt fixes onto a wrong design, per the **redesign-from-first-principles** and **fix-root-causes** principle skills.
+
+The signal is a *pattern*, not single instances. Tells:
+
+- The same shape of workaround appearing repeatedly across unrelated code.
+- Multiple unrelated edge cases that all need special-case branches.
+- Types that need escape hatches (`any`, casts, optional fields always set in practice) to compile.
+- The "we need a lock" reflex when the sketch said the state wasn't shared.
+- Callers having to know the abstraction's internal rules to use it.
+- Two or more independent Phase D deviations of the same shape across the implementation.
+
+Use judgment. A few edge cases don't condemn an architecture. Some problems are legitimately complex. Complexity in the data is not complexity in the design.
+
+When you scrap:
+
+1. Re-run the **how** skill over what's been built.
+2. Redesign as if the new constraints had been day-one assumptions, per redesign-from-first-principles.
+3. Subtract before adding, per the **subtract-before-you-add** principle skill. The new sketch should be smaller than the old one before it grows.
+4. Return to Phase B and re-run arena.
+
+## Outputs
+
+The caller's usage is written first and the type sketch derived from it. One file with new types and signatures for small changes. Module map plus type definitions for larger work. The rationale ships alongside, shaped per `references/rationale-template.md`, including the usage sketch and the synthesis decision.

package/skills/architect/references/design-red-flags.md

@@ -0,0 +1,33 @@
+# Design red flags
+
+Screen every candidate before synthesis. A red flag is a reason to revise or reject the shape.
+
+## Shallow module
+
+A shallow module exposes a large interface while hiding little complexity. Judge depth by the capability and policy hidden behind the public surface relative to the size of that surface. Prefer a simple interface backed by substantial behavior.
+
+Do not confuse a deep module with a deep call chain. A deep call chain scatters understanding across layers. A deep module concentrates capability behind one interface.
+
+Look for these signs:
+
+- Callers coordinate several methods to complete one operation.
+- Public options expose internal stages or implementation choices.
+- Learning the interface does not save the caller from learning the implementation.
+
+## Information leakage
+
+Information leakage makes multiple modules depend on the same internal decision. A representation, policy, or protocol detail appears in more than one place, so changing it requires coordinated edits.
+
+Public re-exports of transport or wire types are leakage. Parse external data into domain types behind the interface. Keep storage schemas, framework objects, and protocol details private.
+
+## Temporal decomposition
+
+Temporal decomposition organizes modules by execution order instead of the knowledge they own. Separate load, validate, transform, and save stages often repeat one representation and its invariants across several boundaries.
+
+Group code around domain knowledge and ownership. Methods that run at different times can still belong to one module when they protect the same decisions.
+
+## Pass-through method
+
+A pass-through method forwards the same arguments to another method with the same shape. It adds a layer without hiding complexity.
+
+Remove it or move responsibility to the module that can complete the operation. Keep a forwarding boundary only when it adds policy, adaptation, or a distinct abstraction.

package/skills/architect/references/rationale-template.md

@@ -0,0 +1,35 @@
+# Rationale template
+
+The prose that ships alongside the type sketch. One page. Sentence-case headings, no boilerplate. Replace the italic notes with actual content.
+
+## Problem
+
+*One paragraph. What we're trying to do, and what about the existing system or constraints makes the shape non-obvious. If [Phase A](../SKILL.md#phase-a-ground-the-problem) surfaced constraints the design must honor (existing types to interop with, callers we can't break, invariants that crossed our boundary), name them here so the reader sees the same constraints you saw.*
+
+## Usage (caller's view)
+
+*Write this first, before the type sketch. Show the README or quickstart the consumer reads, plus two or three realistic call sites in their own code. What they import, what they call, what comes back. The type sketch in [Shape](#shape) is derived from this. The two must agree. When they diverge, reconcile the sketch to the usage, not the reverse. The caller's experience is the spec. The types serve it.*
+
+## Shape
+
+*The recommended architecture. Data structures first. Then how data flows through the signatures. Name the load-bearing decisions. State which invariants are encoded in types, where validation lives, and what the system deliberately does not do. Judge interface depth explicitly. State what complexity the public surface hides, what remains exposed to callers, and why the interface is no larger than needed. Cite the principle behind each decision (e.g., `per boundary-discipline`). Don't restate it.*
+
+## Synthesis decision
+
+*Filled in by [arena](../../arena/SKILL.md). Records which candidate became the base and why, what was adapted from each of the others, and what was rejected and why.*
+
+## Tradeoffs accepted
+
+*One bullet per tradeoff the chosen shape makes. Form: "we accept X in exchange for Y." Name anything a future reader might mistake for an oversight, including things that look like premature optimization or premature simplification.*
+
+## Alternatives considered
+
+*Required. Name at least one concrete alternative shape, with one line on why it lost. Judge each alternative on interface depth, not implementation simplicity alone. Name the complexity it exposes to callers and the complexity it hides. Two or three alternatives belong here when the design space had real contenders. One is fine when the constraints forced the answer, with the conclusion phrased as "this was the only viable shape because..." Avoid listing flavors of the same shape. This section covers design alternatives the chosen shape considered and rejected, not other runner candidates.*
+
+## Open questions and risks
+
+*Things you noticed during the sketch that the human needs to weigh in on, and risks worth flagging before implementation starts. Phrase as questions, not assertions, so the human's answer is the resolution rather than a comment.*
+
+## Next implementation step
+
+*The first thing to build against the sketch. One sentence. What you'd start writing immediately after synthesis (or after Phase D sign-off, if a checkpoint was opted into).*

package/skills/architect/references/runner-prompt.md

@@ -0,0 +1,20 @@
+# Architect runner prompt
+
+The orchestrator passes this file through to every parallel candidate runner during Phase B and fills in the variable inputs around it: the task, the Phase A grounding artifacts, the isolated working directory, and the path to write outputs. The working directory is a git worktree when available, otherwise a per-runner subdirectory under the sketch dir. What matters is independence between candidates.
+
+You are producing one candidate design in architect's parallel exploration. Read the **architect** skill in full first. That's the workflow you're inside. Output a candidate design package: type sketch, function signatures, module map, and prose rationale shaped per [`rationale-template.md`](rationale-template.md).
+
+Apply the following discipline. The orchestrator compares candidates on these axes to pick a base.
+
+- Caller's usage first. Write the README-style usage and two or three real call sites before the types, then derive the type sketch from them. The usage is the spec. The two must agree, so reconcile the sketch to the usage, not the reverse.
+- Data structures first. Get the core types right and the code becomes obvious. Trace each dominant access pattern through the proposed structure. If the answer is "we'll add a map / index / cache later," the structure is wrong.
+- Interface depth. Compare the capability hidden behind the public surface relative to the size of that surface. Prefer a simple interface that pulls complexity into the callee, even when the implementation becomes less simple. Do not put transport or wire types on the public API. Parse into domain types behind the interface.
+- Shared state: if two actors might both write, ask "what happens?" If the answer isn't "nothing," default to per-actor state with a merge at the read boundary, per the **separate-before-serializing-shared-state** principle skill.
+- Make boundaries visible. `not implemented` errors for bodies, `// TODO` pseudocode for tricky logic, doc comments stating intent and invariants. A reader should trace data from input to output by reading types and signatures alone.
+- Encode invariants in types: hard-to-misuse types > runtime checks > prose comments, per the **encode-lessons-in-structure** principle skill.
+- Validate at boundaries, trust types inside, per the **boundary-discipline** principle skill. Business logic as pure functions. The shell stays thin.
+- Single source of truth per invariant. Derive instead of sync.
+- Idempotent state transitions where applicable, per the **make-operations-idempotent** principle skill. Ask what happens if the operation runs twice or crashes halfway.
+- Short call chains. If tracing the flow needs more than three files, flatten the hierarchy, per the **laziness-protocol** and **minimize-reader-load** principle skills.
+
+You are one of several runners, each on a different model. Produce the best design your model can make. Don't hedge against the others. Differences between candidates are the signal used to pick a base and graft. Converging on a safe-looking middle defeats the exploration.

package/skills/arena/SKILL.md

@@ -0,0 +1,13 @@
+---
+name: arena
+description: "Compatibility entry for agi-mode Arena: generate independent candidates, compare them, select a base and verify a synthesis. Use for /arena, 'arena this', or an explicit request for competing designs."
+disable-model-invocation: true
+---
+
+# Arena
+
+The maintained workflow now lives in **agi-mode**. Read and execute [Arena](../agi-mode/playbooks/arena.md), which owns framing, runner selection, isolated candidates, anonymous judging, selection, grafting and verification.
+
+Preserve the caller's task, candidate count, runner preferences and scope. Calling Arena does not start an improvement loop; if already inside Hillclimb, return candidates and evidence to its existing record.
+
+Resolve the sibling path or the registered installation of `agi-mode`. This compatibility entry requires that skill; if unavailable, report the missing dependency rather than inventing candidates or judging results.

package/skills/automate-me/SKILL.md

@@ -0,0 +1,104 @@
+---
+name: automate-me
+description: "Use for \"automate me\", \"create/update/refresh my -mode skill\", \"turn/capture my preferences or working style into a skill\", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via create-skill + unslop, optionally pulling fresh evidence from recent transcripts."
+disable-model-invocation: true
+---
+
+# Automate me
+
+A guided flow for turning the user's working conventions into a skill agents will follow. The output is one `-mode` skill tailored to them (e.g. `jay-mode`, `priya-mode`).
+
+This skill orchestrates three others: an inline mining pass (see step 1), Cursor's built-in `create-skill` (authoring), and the **unslop** skill (prose discipline). It sequences them. It doesn't replace them.
+
+## Flow
+
+### 0. Check for an existing skill
+
+Look recursively for `.cursor/skills/**/*-mode/SKILL.md` and `~/.cursor/skills/*-mode/SKILL.md` matching the user's handle. Mode skills can live in a personal category directory (`.cursor/skills/<handle>/`), not only at the top level. If one exists, confirm intent with `AskQuestion` (unless they already said "update my skill" or similar):
+
+- Update the existing skill (default for repeat runs)
+- Start fresh (rare, ask why before doing it)
+
+Update mode changes the rest of the flow:
+- Step 1 mines only history since the skill was last edited (`git log -1 --format=%cI <path>`).
+- Step 2 asks what's changed or missing, not what to capture from zero.
+- Step 4 edits the existing file in place. Preserve sections the user hasn't contradicted. Revise ones with new evidence. Add new sections only for genuinely new rules.
+
+### 1. Mine their history
+
+Locate the active workspace's transcripts before fanning out. The system prompt names the workspace's `agent-transcripts/` directory. Use only that path. Don't glob across `~/.cursor/projects/*/`. That crosses workspace boundaries and reads private chats from unrelated projects.
+
+Survey recent agent conversations within that scope for recurring patterns. Run multiple parallel subagents across slices of history (e.g. last 2-4 weeks, split into 3 slices so each has enough material). Each slice mining subagent reads transcripts from the workspace-scoped path the parent provides, looks for the signals below, and returns a short structured list of patterns it saw with evidence pointers. Default signals worth hunting:
+
+- Response preferences (length, tone, format, "dumb it down" corrections)
+- Delegation habits (subagents, models, specialized workflows, parallelism)
+- Verification posture (what "done" means, unit tests vs live repro, reviewers)
+- Code and prose discipline (style, principles cited, lint/format tools)
+- Process conventions (worktrees, commits, PRs, review/merge tooling)
+- Meta preferences (fixing skills mid-task, proposing new ones)
+
+Cross-check across slices before elevating a signal. Patterns seen in 2+ slices are high-confidence. Lone signals are weak and usually get dropped.
+
+### 2. Ask the user directly
+
+Mining misses intent that hasn't come up yet. Use the `AskQuestion` tool (structured multi-choice) rather than asking the user to type from scratch.
+
+Shape: one or two questions with 4-6 options each, `allow_multiple: true` for category questions. Start broad ("Which areas matter most?"), then follow up on selected areas with specific options. After the structured rounds, one free-form chat question catches anything the options missed.
+
+Don't dump 20 questions.
+
+### 3. Cluster findings
+
+Group the combined signals into sections. Common ones (use only what applies):
+
+- **Response style**: length, tone, format.
+- **Autonomy**: how much to do without asking, MCP tool use.
+- **Understand first**: which skills to reach for when scoping or investigating a change.
+- **Subagents**: default, parallelism, model-to-task, specialized workflows.
+- **Prose / code discipline**: principles, lint tools, style guides.
+- **Review and verify**: repro posture, verification skills, live-testing tools.
+- **Process**: git worktrees, commits, PRs, review/merge tooling.
+- **Skills**: skill-authoring habits, fix-the-skill-first, proposing new skills.
+
+The **poteto-mode** skill shows the shape. Read it for granularity. Don't copy its content. The user's rules are not the same as poteto-mode's.
+
+### 4. Draft the skill
+
+Use Cursor's built-in `create-skill` skill to author the skill. Placement:
+
+- Path: preserve an existing mode skill's category. For a new mode, use `.cursor/skills/<handle>/<handle>-mode/SKILL.md` when the repo has an established personal category for that handle. Otherwise default to `.cursor/skills/<handle>-mode/SKILL.md` in the project (or `~/.cursor/skills/<handle>-mode/` if the user prefers a personal skill).
+- Handle: the user's first name or chosen identifier.
+- Frontmatter `description`: trigger on their name + `/<handle>-mode` + "work in their style", not on generic keywords like "write code" or "review PR".
+- Frontmatter formatting: follow `create-skill`'s YAML rules. Keep `description` as one YAML scalar. Quote it or use `description: >-` with indented continuation lines when punctuation or wrapping requires it.
+- Frontmatter `disable-model-invocation: true` by default. Opt out only if the user explicitly wants their mode to apply on every turn.
+
+### 5. Iterate on prose
+
+Apply the **unslop** skill and `create-skill`'s writing guidelines to every line.
+
+Show the draft to the user and take feedback. Expect multiple iterations. Cut ruthlessly. A mode skill is not a manual.
+
+### 6. Land it
+
+Work in a worktree off main. Commit and open a PR. Don't push to main directly.
+
+## Guardrails
+
+- **Don't overfit to one conversation.** A preference stated once and contradicted another time is noise. Require multiple instances before codifying it.
+- **Don't be clever.** Restating other skills' contents, inventing metaphors, or writing "poetic" prose for an agent reader is cost without benefit. Keep it operational.
+- **Reference, don't inline.** Other skills the user relies on should appear as path references, not pasted excerpts. Same for any principle docs they maintain elsewhere.
+- **Keep sections minimal.** Only add a section if the user has a specific, non-default rule there. "Communicate clearly" is not a section. "Short paragraphs. Tables when comparing options. Bullets only when items are genuinely parallel." is.
+- **Name conventions generic.** Use "the user" or "the human" in imperatives, not the author's first name.
+- **Don't force symmetry.** If a user has no process rules worth writing down, skip the Process section entirely.
+
+## Evaluation
+
+A `-mode` skill is subjective output. A `create-skill`-style test/iterate benchmark loop isn't useful here. Vibe-check with the user: does it read like them? Did it miss anything? Then ship.
+
+Run a description-optimization loop only if the skill's trigger accuracy turns out to be a problem in practice.
+
+## When not to use
+
+- User wants a task-specific skill (not working conventions): `create-skill` alone, no mining required.
+- User wants to capture one narrow workflow (e.g. "how I write commit messages"). That's a regular skill, not a mode skill.
+

package/skills/autoresearch/SKILL.md

@@ -0,0 +1,14 @@
+---
+name: autoresearch
+description: 'Compatibility entry for agi-mode hillclimbing: autonomous, measured improvement of code, skills, prompts or agent workflows. Use for autoresearch, continuous optimization and iterative experiments; not one-shot edits or review-only tasks.'
+license: MIT
+compatibility: Requires agi-mode to be installed alongside this entry and a runnable measurement path.
+---
+
+# Autoresearch
+
+The maintained workflow now lives in **agi-mode**. Read and execute [Hillclimb](../agi-mode/playbooks/hillclimb.md); it owns setup, baseline, safe recovery, experiment records, acceptance, plateaus and final confirmation. For behavioral comparisons it routes to [Eval](../agi-mode/playbooks/eval.md).
+
+Reuse the user's existing goal, scope and permissions. This entry does not create a separate loop, mandate commits, or imply unlimited resources. Git is optional when equivalent recoverable snapshots are available.
+
+Resolve the sibling path or the registered installation of `agi-mode`. If it is absent, explain that this compatibility entry requires `agi-mode`; do not invent a second implementation or claim to have run the missing workflow.