@haaaiawd/loom 2.0.0 → 2.1.0

package/docs/RELEASE_CHECKLIST.md

@@ -1,53 +1,53 @@
-# LOOM release checklist
-
-This checklist stops a documentation-complete release from becoming a runtime-incomplete release.
-
-## 1. Confirm the release surface
-
-```bash
-node cli/bin/loom.js --version
-node cli/bin/loom.js --help
-node cli/bin/loom.js prompts
-npm test
-npm pack --dry-run
-```
-
-Confirm that the package contains the CLI runtime, English and Chinese READMEs, design, prompt catalog, UX flow, Evil Eval
-protocol, changelog, license, contribution guide, and security policy. Check that it does not contain pilot
-workspaces, eval artifacts, temporary browser profiles, or local project state.
-
-## 2. Confirm metadata and registry state
-
-```bash
-npm whoami
-npm view @haaaiawd/loom version
-git status --short
-git diff --check
-```
-
-The version in `package.json`, `CHANGELOG.md`, and `loom --version` must agree. The new version must not
-already exist in the registry.
-
-## 3. Publish deliberately
-
-```bash
-git tag v2.0.0
-git push origin HEAD
-git push origin v2.0.0
-npm publish --access public
-```
-
-Run these commands only after reviewing the final diff and confirming the authenticated GitHub remote and
-npm identity. Tags and published npm versions are externally visible and should not be used as test steps.
-
-## 4. Verify from the outside
-
-In a clean temporary directory:
-
-```bash
-npm view @haaaiawd/loom version
-npx @haaaiawd/loom@2.0.0 --version
-```
-
-Then open the GitHub README and npm package page to confirm the SVG header, diagrams, links, and changelog
-render correctly. Record any unverified platform boundary instead of silently declaring it passed.
+# LOOM release checklist
+
+This checklist stops a documentation-complete release from becoming a runtime-incomplete release.
+
+## 1. Confirm the release surface
+
+```bash
+node cli/bin/loom.js --version
+node cli/bin/loom.js --help
+node cli/bin/loom.js prompts
+npm test
+npm pack --dry-run
+```
+
+Confirm that the package contains the CLI runtime, English and Chinese READMEs, design, prompt catalog, UX flow, Evil Eval
+protocol, changelog, license, contribution guide, and security policy. Check that it does not contain pilot
+workspaces, eval artifacts, temporary browser profiles, or local project state.
+
+## 2. Confirm metadata and registry state
+
+```bash
+npm whoami
+npm view @haaaiawd/loom version
+git status --short
+git diff --check
+```
+
+The version in `package.json`, `CHANGELOG.md`, and `loom --version` must agree. The new version must not
+already exist in the registry.
+
+## 3. Publish deliberately
+
+```bash
+git tag v2.0.1
+git push origin HEAD
+git push origin v2.0.1
+npm publish --access public
+```
+
+Run these commands only after reviewing the final diff and confirming the authenticated GitHub remote and
+npm identity. Tags and published npm versions are externally visible and should not be used as test steps.
+
+## 4. Verify from the outside
+
+In a clean temporary directory:
+
+```bash
+npm view @haaaiawd/loom version
+npx @haaaiawd/loom@2.0.1 --version
+```
+
+Then open the GitHub README and npm package page to confirm the SVG header, diagrams, links, and changelog
+render correctly. Record any unverified platform boundary instead of silently declaring it passed.

package/docs/UX_FLOW.md

@@ -1,171 +1,184 @@
-# LOOM 2 Complete UX and Loop Specification
-
-## Experience promise
-
-The human experiences one capable Agent who understands, asks, decides, builds, and recovers. They do not experience
-framework stages, role handoffs, status commands, or document maintenance. LOOM is the Agent's backstage continuity
-system.
-
-The system has three nested production loops and one external evaluation loop:
-
-1. Understanding loop — converge on the whole, its design-document graph, and the professional fields it needs.
-2. Readiness loop — let a fresh Keeper expose missing context and feed gaps back into understanding.
-3. Delivery loop — execute one restartable Task, test, repair or reflow, attach evidence, and continue.
-4. Evil Eval — compare the same Agent with no LOOM against the Agent using LOOM under equal conditions.
-
-## Surfaces and responsibilities
-
-| Surface | Human visible | Responsibility |
-|---|---:|---|
-| Natural conversation | Yes | Desired result, meaningful questions, delegated decisions, risk authority, progress and delivery |
-| Workspace and product artifacts | When useful | The real code, files, commands, reports, or operational result |
-| PROJECT.md, design docs, capability dossiers | Optional | Human-editable whole, detailed system decisions, and separate professional judgments |
-| `loom context` and structured state | No | Agent continuity after compression or a new session |
-| Work Map and active Task | Normally no | Broad coverage, current outcome, boundaries, relevant context, progress and evidence |
-| Keeper prompt and attempts | Only if a new window is required | One readiness handoff, with revision loops before execution |
-| Evil Eval harness | No during normal work | Controlled evidence about whether LOOM itself helps |
-
-## 0. Resume or receive a request
-
-The Agent runs `loom context` when LOOM exists. It then interprets the current request normally. Existing workspace
-inspection is conditional: inspect only when the request depends on the existing project, not because LOOM demands a scan.
-
-Human UX: nothing framework-specific appears.
-
-## 1. Form the emerging whole
-
-The Agent explains what it currently believes the finished result should be. This is conversational, not a mandatory
-template recital. It is most useful initially, after a consequential correction, and before material execution.
-
-The Agent identifies the current uncertainty frontier: decisions whose answers could materially change outcome,
-experience, boundaries, architecture, risk, cost, or proof of completion.
-
-## 2. Ask one dense, adaptive round
-
-The Agent asks all currently visible high-value questions in a coherent round. It may group by a natural decision cluster,
-but it does not follow a fixed domain list or question count.
-
-It does not ask facts reliably discoverable from tools, professional decisions it can responsibly make, speculative future
-details that do not affect the current whole, or framework questions whose only purpose is filling a schema.
-
-| Human response | Agent behavior |
-|---|---|
-| Direct answer | Record confirmed fact and update current truth |
-| Correction | Update PROJECT.md and affected design docs; append a superseding decision with impact |
-| `You decide` | Make the best reversible Agent decision, explain the important tradeoff, and record it |
-| `I don't know` | Research or decide when safe; ask again only if the human owns the missing preference or authority |
-| `Skip questions and continue` | Name the concrete quality or risk loss, record skipped uncertainty, then proceed |
-
+# LOOM 2 Complete UX and Loop Specification
+
+## Experience promise
+
+The human experiences one capable Agent who understands, asks, decides, builds, and recovers. They do not experience
+framework stages, role handoffs, status commands, or document maintenance. LOOM is the Agent's backstage continuity
+system.
+
+The system has three nested production loops and one external evaluation loop:
+
+1. Understanding loop — converge on the whole, its design-document graph, and the professional fields it needs.
+2. Readiness loop — let a fresh Keeper expose missing context and feed gaps back into understanding.
+3. Delivery loop — execute one restartable Task, test, repair or reflow, attach evidence, and continue.
+4. Evil Eval — compare the same Agent with no LOOM against the Agent using LOOM under equal conditions.
+
+## Surfaces and responsibilities
+
+| Surface | Human visible | Responsibility |
+|---|---:|---|
+| Natural conversation | Yes | Desired result, meaningful questions, delegated decisions, risk authority, progress and delivery |
+| Workspace and product artifacts | When useful | The real code, files, commands, reports, or operational result |
+| PROJECT.md, design docs, capability dossiers | Optional | Human-editable whole, detailed system decisions, and separate professional judgments |
+| `loom context` and structured state | No | Agent continuity after compression or a new session |
+| Work Map and active Task | Normally no | Broad coverage, current outcome, boundaries, relevant context, progress and evidence |
+| Keeper prompt and attempts | Only if a new window is required | One readiness handoff, with revision loops before execution |
+| Evil Eval harness | No during normal work | Controlled evidence about whether LOOM itself helps |
+
+## 0. Resume or receive a request
+
+The Agent runs `loom context` when LOOM exists. It then interprets the current request normally. Existing workspace
+inspection is conditional: inspect only when the request depends on the existing project, not because LOOM demands a scan.
+
+Human UX: nothing framework-specific appears.
+
+## 1. Form the emerging whole
+
+The Agent explains what it currently believes the finished result should be. This is conversational, not a mandatory
+template recital. It is most useful initially, after a consequential correction, and before material execution.
+
+The Agent identifies the current uncertainty frontier: decisions whose answers could materially change outcome,
+experience, boundaries, architecture, risk, cost, or proof of completion.
+
+## 2. Ask one dense, adaptive round
+
+The Agent asks all currently visible high-value questions in a coherent round. It may group by a natural decision cluster,
+but it does not follow a fixed domain list or question count.
+
+It does not ask facts reliably discoverable from tools, professional decisions it can responsibly make, speculative future
+details that do not affect the current whole, or framework questions whose only purpose is filling a schema.
+
+| Human response | Agent behavior |
+|---|---|
+| Direct answer | Record confirmed fact and update current truth |
+| Correction | Update PROJECT.md and affected design docs; append a superseding decision with impact |
+| `You decide` | Make the best reversible Agent decision, explain the important tradeoff, and record it |
+| `I don't know` | Research or decide when safe; ask again only if the human owns the missing preference or authority |
+| `Skip questions and continue` | Name the concrete quality or risk loss, record skipped uncertainty, then proceed |
+
 After every answer round, the Agent re-evaluates the whole. If material uncertainty remains, it loops to another adaptive
 round. If only reversible local uncertainty remains, it continues.
 
-## 3. Build project-specific capability
-
-The Agent maps which established professional fields could change questions, design, implementation, risk, or verification.
-It creates one dossier per recognizable field. UI/UX design, visual art direction, game design, psychology, biology, security,
-and other fields remain separate when their evidence or judgments differ. Task techniques such as triage, ranking, parsing,
-or caching are design mechanisms, not replacements for the capability map. Cross-field synthesis belongs in the affected
-design document.
-
-A useful dossier changes action. It contains its field boundary, specialist evidence, a falsifiable project stance,
-deliberate refusals, decision-changing questions, implementation consequences, failure modes, verification signals, sources,
-and tensions. Generic summaries and expert roleplay fail this step.
-
-Research can be quiet. A natural update is enough: `I need to strengthen the privacy, cognitive-load and information-architecture judgment; I will bring the consequences back into the design.`
-
-## 4. Shape the project corpus and Work Map
-
-PROJECT.md is the concise entry point and map. DECISIONS.md holds only consequential supersession. The actual product,
-experience, independent systems, contracts, verification, research, and operations decisions live under `.loom/design/`.
-A document is split when its subject has independent responsibilities, interfaces, failure modes, or proof. Document count
-therefore scales with project complexity: neither a fixed checklist nor an artificial one-file minimum.
-
-The Agent creates a broad initial Work Map early. It may be thousands of lines because it remains on disk. Only the active
-horizon receives detailed actions. Every Task states outcome, done conditions, boundaries, dependencies, relevant reads,
-affected paths, progress, next action, and evidence.
-
-## 5. Transition to readiness
-
-Before engineering or other material execution, the Agent tells the human what is about to happen and which important
-assumptions remain. Ordinary reversible work does not require another approval. Irreversible, high-risk, or materially costly
-action requires explicit authority.
-
-`loom project ready` verifies structural readiness and freezes a digest of the project map, design documents, capability dossiers, and Task
-definitions for the next Keeper attempt.
-
-## 6. Keeper readiness loop
-
-A fresh Agent thread runs `loom keeper prompt` and `loom context --keeper`. It receives no prior conversation. Each attempt has
-a unique `run_id`, attempt number, and prepared digest.
-
-Keeper tests whether it can explain the whole, navigate every necessary design system, locate distinct professional capabilities, select the correct first Task, find all context,
-name the first concrete action, and reproduce completion evidence.
-
-### Passed
-
-State becomes `build_ready`. Keeper leaves the normal workflow permanently; Task evidence now carries delivery quality.
-
-### Needs revision or blocked
-
-The result records summary, evidence, and exact gaps. State returns to `shaping`. The next `loom context` injects this feedback
-as the highest-priority uncertainty.
-
-The main Agent decides where the gap belongs, repairs everything it can, asks the human only for decisions they genuinely own,
-changes the relevant disk truth, runs `loom project ready` again, and opens a new Keeper run with a new run_id and digest.
-
-LOOM refuses an unchanged revision, a duplicate run_id, a result for the wrong digest, and a result written before ready.
-
-If the host has no subagents, the human sees one short request: `Please open a new window in this project, run loom keeper prompt, and follow it.`
-
-## 7. Delivery loop
-
-The Agent selects `loom task next`, starts it, and runs `loom context`. Context contains the current whole, current Task, and the
-exact design, capability, source, contract, and fixture files in `reads`—not the full Work Map or history.
-
-- A local failure keeps the Task active. Update progress and evidence, repair, and test again.
-- A missing permission, dependency, or upper-level contradiction uses `task block` with a reason and recovery conditions.
-- After the condition is repaired, use `task reopen`, then start it again. A prior `done` may also be
-  reopened with a concrete reason when its evidence is disproven.
-- `task done` requires a check quoting every exact `done_when` criterion and mapping it to concrete evidence.
-- Generic update cannot modify status, and imported Tasks must begin open.
-
-When a Task is done, the Agent chooses the next dependency-ready Task. When every Task is done, project status becomes complete
-and the Agent delivers the real result, evidence, remaining tradeoffs, and any user-owned follow-up.
-
-## 8. Mid-build change
-
-New user information is first evaluated for impact. A local reversible implementation detail updates the active Task. A change
-to the desired whole updates PROJECT.md and affected design documents, records a superseding decision, revises affected Task definitions, and blocks or reopens
-the active Task as needed. The one-time Keeper does not return after initial build-readiness; implementation evidence and explicit
-human authority govern later changes.
-
-## Recovery matrix
-
-| Failure | Recovery |
-|---|---|
-| Context compressed | `loom context` compiles current truth and active horizon |
-| User contradicts earlier answer | Update PROJECT.md and affected design docs; append superseding decision; revise affected Tasks |
-| Important answer unavailable | Agent decides reversibly or records open or skipped uncertainty |
-| Capability is generic or hybrid | Split into recognizable fields; move synthesis to design docs; add stance, consequences and proof |
-| Keeper cannot start | Feedback returns to shaping; change disk truth; new digest and fresh run |
-| Project changes after ready | Old Keeper result rejected as stale |
-| Same Keeper identity reused | Duplicate run_id rejected |
-| Local implementation test fails | Keep Task active, record observation, repair and repeat |
-| Dependency or authority missing | Block Task with recovery conditions, then reopen |
-| Attempt to mark done without evidence | CLI rejects it |
-| Evidence disproves an earlier done state | Reopen with a reason, then repair, re-verify, or block |
-| Host cannot spawn Keeper | Ask the human to open a new window with one short prompt |
-
-## Flow diagrams
-
-- [Production loops](loom-production-loop.drawio) — editable Draw.io source; [SVG](loom-production-loop.svg).
-- [Evil Eval](loom-eval-loop.drawio) — editable Draw.io source; [SVG](loom-eval-loop.svg).
-
-## Primary evaluation question
-
+### When no human response channel exists
+
+Some unattended, sandboxed, or benchmark runs have no human to answer. The host invokes
+`loom context --human-channel unavailable`; this does not create a synthetic user. The Agent first inspects
+discoverable workspace facts and permitted tools, researches only objective external facts when the task permits it,
+and never treats web research as a substitute for user intent, preference, or authority. It records a bounded
+assumption and selects a safe reversible action, or blocks if the missing answer controls irreversible, high-risk,
+or materially costly work.
+
+## 3. Build project-specific capability
+
+The Agent maps which established professional fields could change questions, design, implementation, risk, or verification.
+It creates one dossier per recognizable field. UI/UX design, visual art direction, game design, psychology, biology, security,
+and other fields remain separate when their evidence or judgments differ. Task techniques such as triage, ranking, parsing,
+or caching are design mechanisms, not replacements for the capability map. Cross-field synthesis belongs in the affected
+design document.
+
+A useful dossier changes action. It contains its field boundary, specialist evidence, a falsifiable project stance,
+deliberate refusals, decision-changing questions, implementation consequences, failure modes, verification signals, sources,
+and tensions. Generic summaries and expert roleplay fail this step.
+
+Research can be quiet. A natural update is enough: `I need to strengthen the privacy, cognitive-load and information-architecture judgment; I will bring the consequences back into the design.`
+
+## 4. Shape the project corpus and Work Map
+
+PROJECT.md is the concise entry point and map. DECISIONS.md holds only consequential supersession. The actual product,
+experience, independent systems, contracts, verification, research, and operations decisions live under `.loom/design/`.
+A document is split when its subject has independent responsibilities, interfaces, failure modes, or proof. Document count
+therefore scales with project complexity: neither a fixed checklist nor an artificial one-file minimum.
+
+The Agent creates a broad initial Work Map early. It may be thousands of lines because it remains on disk. Only the active
+horizon receives detailed actions. Every Task states outcome, done conditions, boundaries, dependencies, relevant reads,
+affected paths, progress, next action, and evidence.
+
+## 5. Transition to readiness
+
+Before engineering or other material execution, the Agent tells the human what is about to happen and which important
+assumptions remain. Ordinary reversible work does not require another approval. Irreversible, high-risk, or materially costly
+action requires explicit authority.
+
+`loom project ready` verifies structural readiness and freezes a digest of the project map, design documents, capability dossiers, and Task
+definitions for the next Keeper attempt.
+
+## 6. Keeper readiness loop
+
+A fresh Agent thread runs `loom keeper prompt` and `loom context --keeper`. It receives no prior conversation. Each attempt has
+a unique `run_id`, attempt number, and prepared digest.
+
+Keeper tests whether it can explain the whole, navigate every necessary design system, locate distinct professional capabilities, select the correct first Task, find all context,
+name the first concrete action, and reproduce completion evidence.
+
+### Passed
+
+State becomes `build_ready`. Keeper leaves the normal workflow permanently; Task evidence now carries delivery quality.
+
+### Needs revision or blocked
+
+The result records summary, evidence, and exact gaps. State returns to `shaping`. The next `loom context` injects this feedback
+as the highest-priority uncertainty.
+
+The main Agent decides where the gap belongs, repairs everything it can, asks the human only for decisions they genuinely own,
+changes the relevant disk truth, runs `loom project ready` again, and opens a new Keeper run with a new run_id and digest.
+
+LOOM refuses an unchanged revision, a duplicate run_id, a result for the wrong digest, and a result written before ready.
+
+If the host has no subagents, the human sees one short request: `Please open a new window in this project, run loom keeper prompt, and follow it.`
+
+## 7. Delivery loop
+
+The Agent selects `loom task next`, starts it, and runs `loom context`. Context contains the current whole, current Task, and the
+exact design, capability, source, contract, and fixture files in `reads`—not the full Work Map or history.
+
+- A local failure keeps the Task active. Update progress and evidence, repair, and test again.
+- A missing permission, dependency, or upper-level contradiction uses `task block` with a reason and recovery conditions.
+- After the condition is repaired, use `task reopen`, then start it again. A prior `done` may also be
+  reopened with a concrete reason when its evidence is disproven.
+- `task done` requires a check quoting every exact `done_when` criterion and mapping it to concrete evidence.
+- Generic update cannot modify status, and imported Tasks must begin open.
+
+When a Task is done, the Agent chooses the next dependency-ready Task. When every Task is done, project status becomes complete
+and the Agent delivers the real result, evidence, remaining tradeoffs, and any user-owned follow-up.
+
+## 8. Mid-build change
+
+New user information is first evaluated for impact. A local reversible implementation detail updates the active Task. A change
+to the desired whole updates PROJECT.md and affected design documents, records a superseding decision, revises affected Task definitions, and blocks or reopens
+the active Task as needed. The one-time Keeper does not return after initial build-readiness; implementation evidence and explicit
+human authority govern later changes.
+
+## Recovery matrix
+
+| Failure | Recovery |
+|---|---|
+| Context compressed | `loom context` compiles current truth and active horizon |
+| User contradicts earlier answer | Update PROJECT.md and affected design docs; append superseding decision; revise affected Tasks |
+| Important answer unavailable | Agent decides reversibly or records open or skipped uncertainty |
+| Capability is generic or hybrid | Split into recognizable fields; move synthesis to design docs; add stance, consequences and proof |
+| Keeper cannot start | Feedback returns to shaping; change disk truth; new digest and fresh run |
+| Project changes after ready | Old Keeper result rejected as stale |
+| Same Keeper identity reused | Duplicate run_id rejected |
+| Local implementation test fails | Keep Task active, record observation, repair and repeat |
+| Dependency or authority missing | Block Task with recovery conditions, then reopen |
+| Attempt to mark done without evidence | CLI rejects it |
+| Evidence disproves an earlier done state | Reopen with a reason, then repair, re-verify, or block |
+| Host cannot spawn Keeper | Ask the human to open a new window with one short prompt |
+
+## Flow diagrams
+
+- [Production loops](loom-production-loop.drawio) — editable Draw.io source; [SVG](loom-production-loop.svg).
+- [Evil Eval](loom-eval-loop.drawio) — editable Draw.io source; [SVG](loom-eval-loop.svg).
+
+## Primary evaluation question
+
 The causal baseline is a normal capable Agent with no LOOM—not LOOM v1. Both conditions receive the same raw brief, model,
-tools, workspace, user oracle, budget, and reset schedule. LOOM v1 may be added as a secondary regression condition, but it does
+tools, workspace, human-channel availability, user oracle when one exists, budget, and reset schedule. LOOM v1 may be added as a secondary regression condition, but it does
 not answer whether the framework itself creates value over no framework.
 
-The anonymization harness must preserve runnable relative layout, record a file/digest manifest, and rerun each condition's
-declared tests and smoke command before judging. Packet-construction failures are eval failures, never evidence against a run.
+For an unattended external benchmark, both conditions receive `human_channel: unavailable` and no fabricated user
+oracle. A fresh LOOM sidecar sits outside the scored workspace and is passed through `--state-dir` on every LOOM
+command, so framework state cannot alter task files or hidden-test behavior.
+
+The anonymization harness must preserve runnable relative layout, record a file/digest manifest, and rerun each condition's
+declared tests and smoke command before judging. Packet-construction failures are eval failures, never evidence against a run.

package/docs/brand/loom-mark.svg

@@ -1,18 +1,18 @@
-<svg xmlns="http://www.w3.org/2000/svg" width="256" height="256" viewBox="0 0 256 256" role="img" aria-labelledby="title desc">
-  <title id="title">LOOM mark</title>
-  <desc id="desc">A continuous thread passes through four frames, resumes after a gap, and loops forward.</desc>
-  <rect width="256" height="256" rx="52" fill="#F5F2EA"/>
-  <g fill="none" stroke="#17212B" stroke-width="6">
-    <rect x="38" y="61" width="42" height="88" rx="9"/>
-    <rect x="88" y="61" width="42" height="88" rx="9"/>
-    <rect x="138" y="61" width="42" height="88" rx="9"/>
-    <rect x="188" y="61" width="30" height="88" rx="9"/>
-  </g>
-  <path d="M24 105H50C61 105 61 82 72 82S83 128 94 128s11-46 22-46 11 46 22 46 11-46 22-46 11 46 22 46"
-        fill="none" stroke="#4169E1" stroke-width="10" stroke-linecap="round" stroke-linejoin="round"/>
-  <circle cx="198" cy="128" r="5" fill="#4169E1"/>
-  <circle cx="214" cy="128" r="5" fill="#4169E1" opacity=".55"/>
-  <path d="M226 128c14 0 17 12 17 23 0 23-18 42-42 42H79"
-        fill="none" stroke="#4169E1" stroke-width="10" stroke-linecap="round"/>
-  <path d="M92 180 75 193l17 13" fill="none" stroke="#4169E1" stroke-width="10" stroke-linecap="round" stroke-linejoin="round"/>
-</svg>
+<svg xmlns="http://www.w3.org/2000/svg" width="256" height="256" viewBox="0 0 256 256" role="img" aria-labelledby="title desc">
+  <title id="title">LOOM mark</title>
+  <desc id="desc">A continuous thread passes through four frames, resumes after a gap, and loops forward.</desc>
+  <rect width="256" height="256" rx="52" fill="#F5F2EA"/>
+  <g fill="none" stroke="#17212B" stroke-width="6">
+    <rect x="38" y="61" width="42" height="88" rx="9"/>
+    <rect x="88" y="61" width="42" height="88" rx="9"/>
+    <rect x="138" y="61" width="42" height="88" rx="9"/>
+    <rect x="188" y="61" width="30" height="88" rx="9"/>
+  </g>
+  <path d="M24 105H50C61 105 61 82 72 82S83 128 94 128s11-46 22-46 11 46 22 46 11-46 22-46 11 46 22 46"
+        fill="none" stroke="#4169E1" stroke-width="10" stroke-linecap="round" stroke-linejoin="round"/>
+  <circle cx="198" cy="128" r="5" fill="#4169E1"/>
+  <circle cx="214" cy="128" r="5" fill="#4169E1" opacity=".55"/>
+  <path d="M226 128c14 0 17 12 17 23 0 23-18 42-42 42H79"
+        fill="none" stroke="#4169E1" stroke-width="10" stroke-linecap="round"/>
+  <path d="M92 180 75 193l17 13" fill="none" stroke="#4169E1" stroke-width="10" stroke-linecap="round" stroke-linejoin="round"/>
+</svg>

package/docs/brand/loom-readme-header.svg

@@ -1,34 +1,34 @@
-<svg xmlns="http://www.w3.org/2000/svg" width="1280" height="360" viewBox="0 0 1280 360" role="img" aria-labelledby="title desc">
-  <title id="title">LOOM — Keep the whole. Continue the work.</title>
-  <desc id="desc">A flat minimal header showing a continuous thread moving through project understanding, expertise, verification, and delivery.</desc>
-  <rect width="1280" height="360" rx="28" fill="#F5F2EA"/>
-  <path d="M0 304H1280" stroke="#D8D3C8"/>
-  <g transform="translate(84 70)">
-    <g fill="none" stroke="#17212B" stroke-width="4">
-      <rect x="0" y="16" width="38" height="76" rx="8"/>
-      <rect x="47" y="16" width="38" height="76" rx="8"/>
-      <rect x="94" y="16" width="38" height="76" rx="8"/>
-      <rect x="141" y="16" width="30" height="76" rx="8"/>
-    </g>
-    <path d="M-14 54H10c10 0 10-20 20-20s10 40 20 40 10-40 20-40 10 40 20 40 10-40 20-40 10 40 20 40"
-          fill="none" stroke="#4169E1" stroke-width="8" stroke-linecap="round" stroke-linejoin="round"/>
-    <circle cx="145" cy="74" r="4" fill="#4169E1"/><circle cx="158" cy="74" r="4" fill="#4169E1" opacity=".5"/>
-    <path d="M171 74c20 0 27 13 27 28 0 23-18 42-42 42H59" fill="none" stroke="#4169E1" stroke-width="8" stroke-linecap="round"/>
-    <path d="M72 132 56 144l16 12" fill="none" stroke="#4169E1" stroke-width="8" stroke-linecap="round" stroke-linejoin="round"/>
-  </g>
-  <g font-family="Inter,Segoe UI,Arial,sans-serif" fill="#17212B">
-    <text x="350" y="142" font-size="94" font-weight="750" letter-spacing="12">LOOM</text>
-    <text x="355" y="190" font-size="24" font-weight="560">Keep the whole. Continue the work.</text>
-    <text x="355" y="228" font-size="17" fill="#58636D">Invisible project understanding and continuity for AI Agents.</text>
-  </g>
-  <g transform="translate(82 311)" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="13" font-weight="650" letter-spacing="1.1" fill="#17212B">
-    <circle cx="4" cy="-1" r="4" fill="#4169E1"/><text x="18" y="4">UNDERSTAND</text>
-    <path d="M126-1h42" stroke="#9AD8C2" stroke-width="3"/>
-    <circle cx="181" cy="-1" r="4" fill="#9AD8C2"/><text x="195" y="4">REMEMBER</text>
-    <path d="M306-1h42" stroke="#E88773" stroke-width="3"/>
-    <circle cx="361" cy="-1" r="4" fill="#E88773"/><text x="375" y="4">VERIFY</text>
-    <path d="M452-1h42" stroke="#4169E1" stroke-width="3"/>
-    <circle cx="507" cy="-1" r="4" fill="#4169E1"/><text x="521" y="4">CONTINUE</text>
-  </g>
-  <text x="1198" y="322" text-anchor="end" font-family="ui-monospace,SFMono-Regular,Consolas,monospace" font-size="13" fill="#58636D">npm i -g @haaaiawd/loom</text>
-</svg>
+<svg xmlns="http://www.w3.org/2000/svg" width="1280" height="360" viewBox="0 0 1280 360" role="img" aria-labelledby="title desc">
+  <title id="title">LOOM — Keep the whole. Continue the work.</title>
+  <desc id="desc">A flat minimal header showing a continuous thread moving through project understanding, expertise, verification, and delivery.</desc>
+  <rect width="1280" height="360" rx="28" fill="#F5F2EA"/>
+  <path d="M0 304H1280" stroke="#D8D3C8"/>
+  <g transform="translate(84 70)">
+    <g fill="none" stroke="#17212B" stroke-width="4">
+      <rect x="0" y="16" width="38" height="76" rx="8"/>
+      <rect x="47" y="16" width="38" height="76" rx="8"/>
+      <rect x="94" y="16" width="38" height="76" rx="8"/>
+      <rect x="141" y="16" width="30" height="76" rx="8"/>
+    </g>
+    <path d="M-14 54H10c10 0 10-20 20-20s10 40 20 40 10-40 20-40 10 40 20 40 10-40 20-40 10 40 20 40"
+          fill="none" stroke="#4169E1" stroke-width="8" stroke-linecap="round" stroke-linejoin="round"/>
+    <circle cx="145" cy="74" r="4" fill="#4169E1"/><circle cx="158" cy="74" r="4" fill="#4169E1" opacity=".5"/>
+    <path d="M171 74c20 0 27 13 27 28 0 23-18 42-42 42H59" fill="none" stroke="#4169E1" stroke-width="8" stroke-linecap="round"/>
+    <path d="M72 132 56 144l16 12" fill="none" stroke="#4169E1" stroke-width="8" stroke-linecap="round" stroke-linejoin="round"/>
+  </g>
+  <g font-family="Inter,Segoe UI,Arial,sans-serif" fill="#17212B">
+    <text x="350" y="142" font-size="94" font-weight="750" letter-spacing="12">LOOM</text>
+    <text x="355" y="190" font-size="24" font-weight="560">Keep the whole. Continue the work.</text>
+    <text x="355" y="228" font-size="17" fill="#58636D">Invisible project understanding and continuity for AI Agents.</text>
+  </g>
+  <g transform="translate(82 311)" font-family="Inter,Segoe UI,Arial,sans-serif" font-size="13" font-weight="650" letter-spacing="1.1" fill="#17212B">
+    <circle cx="4" cy="-1" r="4" fill="#4169E1"/><text x="18" y="4">UNDERSTAND</text>
+    <path d="M126-1h42" stroke="#9AD8C2" stroke-width="3"/>
+    <circle cx="181" cy="-1" r="4" fill="#9AD8C2"/><text x="195" y="4">REMEMBER</text>
+    <path d="M306-1h42" stroke="#E88773" stroke-width="3"/>
+    <circle cx="361" cy="-1" r="4" fill="#E88773"/><text x="375" y="4">VERIFY</text>
+    <path d="M452-1h42" stroke="#4169E1" stroke-width="3"/>
+    <circle cx="507" cy="-1" r="4" fill="#4169E1"/><text x="521" y="4">CONTINUE</text>
+  </g>
+  <text x="1198" y="322" text-anchor="end" font-family="ui-monospace,SFMono-Regular,Consolas,monospace" font-size="13" fill="#58636D">npm i -g @haaaiawd/loom</text>
+</svg>