@tangle-network/starter-foundry 0.7.3 → 0.13.2

package/registry/families/agent-runtime-history-tutor-ts/files/methodology/timeline-reasoning.md

@@ -0,0 +1,134 @@
+# Timeline Reasoning Template
+
+## Purpose
+Help the learner reason about causation, periodization, and change
+over time — moving past chronology to historical argument. The output
+is a structured reasoning exercise, not a dated bullet list.
+
+## When to use
+Trigger when the user asks "why did X happen," "what caused Y," "is
+the standard periodization right," or wants to test a counterfactual.
+For source-level analysis, use source-analysis.md.
+
+## The three modes
+
+History students need to distinguish:
+
+- **Chronology**: what happened, in order. The skeleton.
+- **Periodization**: how to chunk the chronology into meaningful
+  periods. The interpretation.
+- **Causation**: why one thing led to another. The argument.
+
+Most weak history writing collapses the three. Strong writing
+keeps them distinct.
+
+## Method
+
+1. **Define the period** under analysis.
+   - Boundaries: start date, end date, and the *reason* for each.
+     "1789–1815" rests on French Revolution + Napoleon's defeat as
+     bracket events; an alternative "1750–1850" frames the same
+     era as the rise of industrial Britain.
+   - Boundary defensibility: every periodization is an argument.
+     Name what the boundaries privilege and what they obscure.
+2. **Inventory key events** with explicit roles.
+   - **Trigger**: the event that immediately set off the
+     transition.
+   - **Cause**: a condition without which the trigger would not
+     have produced its effect.
+   - **Consequence**: what the event produced downstream.
+   - **Coincidence**: contemporaneous but not causally entangled.
+   Naming role explicitly prevents post-hoc-ergo-propter-hoc.
+3. **Causation analysis.** Apply the standard distinctions:
+   - **Proximate vs. structural**: assassination of Franz
+     Ferdinand vs. alliance system. Both matter; conflating them
+     hides the argument.
+   - **Necessary vs. sufficient**: a necessary cause must be
+     present for the effect; a sufficient cause guarantees it
+     alone. Most historical causes are necessary-but-not-
+     sufficient.
+   - **Material vs. ideological vs. contingent**: economic
+     conditions, ideas, and individual choices each contribute;
+     historiography fights over weights.
+4. **Counterfactual reasoning.** Useful as a probe, not as
+   proof.
+   - Pick a single causal node and vary it.
+   - Hold other conditions fixed.
+   - Ask: would the proximate effect still occur? Would the
+     structural conditions still produce a similar outcome via
+     a different trigger?
+   - Counterfactuals expose which causes are doing the most work.
+5. **Periodization alternatives.** Re-cut the same chronology
+   under a different lens.
+   - Political vs. social vs. economic vs. cultural cuts often
+     yield different boundaries.
+   - Each cut centers different actors. "Reformation 1517–1648"
+     centers theology; "Confessionalization 1550–1650" centers
+     state-formation; "Print revolution 1450–1650" centers
+     technology.
+   - The pedagogical move: hold a fixed event constant, ask the
+     learner to re-frame it under three different periodizations.
+6. **Argument shape.** The output should sustain a thesis. "X
+   happened because of Y, not Z, because of evidence A, B, C —
+   though Z mattered for D." Strong history writing names rivals
+   and explains why they're insufficient.
+
+## Worked example
+
+> Question: why did the Roman Republic fall?
+>
+> Period: 133 BCE (Tiberius Gracchus) – 27 BCE (Augustus).
+> Boundary defensibility: 133 chosen for the breakdown of senatorial
+> consensus on land reform; 27 chosen for the formal end-state.
+> Alternative: 49 BCE (Caesar's Rubicon) – 27 BCE; alternative
+> emphasizes the civil-war phase, brackets out the structural
+> precursors.
+>
+> Key events:
+> - 133 trigger / structural: Gracchan reforms expose senate's
+>   inability to manage agrarian crisis without violence.
+> - 88, 82, 49 triggers: Sulla, Marius, Caesar — pattern of
+>   commanders using armies as personal political tools.
+> - structural cause: army professionalization (Marian reforms,
+>   ~107 BCE) shifted soldier loyalty from state to commander.
+> - structural cause: empire size outgrew republican
+>   institutional capacity (governor wealth + clientele).
+>
+> Counterfactual: had Caesar been killed before crossing the
+> Rubicon, would the Republic survive? Probably not — the
+> structural pressures (loyal armies, wealthy proconsuls) would
+> produce a similar collapse via another commander. The
+> counterfactual exposes Caesar as proximate, not structural.
+>
+> Alternative periodization: 200 BCE – 14 CE. Centers the gradual
+> imperial transformation; brackets out the dramatic civil-war
+> phase as one of several long-running pressures.
+>
+> Thesis: Republican collapse was structurally over-determined
+> after Marian army reforms; specific assassinations, civil
+> wars, and Augustus' settlement determined the *shape* but not
+> the *fact* of the transition.
+
+## Discipline rules
+
+- **Don't confuse correlation with causation.** "X happened then
+  Y happened" is chronology, not causation.
+- **Don't fall for great-man framing alone.** Individual choice
+  matters but rarely sufficient without structural conditions.
+- **Don't fall for structural framing alone.** Structural
+  determinism flattens contingent decisions and individual agency.
+- **Periodization is an argument.** Defend the boundaries; don't
+  borrow them unexamined from the textbook.
+
+## Output block
+
+Wrap in `:::artifact` with `template: timeline-reasoning`. Include
+period bounds with defense, named events with roles, causation
+analysis, counterfactual probe, and at least one alternative
+periodization.
+
+## Pedagogical scaffolding
+
+When the user is a learner, ask them to attempt periodization first.
+Their boundary choice reveals what they think the period is *about*.
+Critique the boundaries before adding facts.

package/registry/families/agent-runtime-history-tutor-ts/manifest.json

@@ -0,0 +1,145 @@
+{
+  "id": "agent-runtime-history-tutor-ts",
+  "description": "Voice-first history tutor agent bundle \u2014 primary-source analysis, historiographic debate, and timeline reasoning. Explicitly NOT a substitute for a credentialed history teacher, not a source of original archival research, not a replacement for peer-reviewed scholarship. Demonstrates the agent-runtime substrate composing with structured-output-blocks on the Tangle floor.",
+  "tags": [
+    "agent-runtime",
+    "history-tutor",
+    "education",
+    "primary-sources",
+    "historiography",
+    "cloudflare-worker"
+  ],
+  "taxonomy": {
+    "language": "markdown",
+    "runtime": "cloudflare-worker",
+    "surface": "agent-runtime"
+  },
+  "includes": [
+    "agent-base:tangle",
+    "agent-base:secure",
+    "agent-output:blocks",
+    "agent-base:memory",
+    "agent-base:scheduler",
+    "agent-base:mcp-registry",
+    "agent-channels:telegram",
+    "agent-channels:discord",
+    "agent-channels:slack",
+    "agent-channels:whatsapp",
+    "agent-channels:imessage",
+    "agent-channels:gmail",
+    "agent-channels:linear"
+  ],
+  "defaults": {
+    "projectType": "agent-runtime-history-tutor",
+    "agentName": "history-tutor",
+    "publicVars": [
+      "AGENT_NAME"
+    ],
+    "routes": [
+      {
+        "path": "/api/chat",
+        "auth": "bearer",
+        "callsTools": [
+          "source-analysis",
+          "historiographic-debate",
+          "timeline-reasoning"
+        ]
+      },
+      {
+        "path": "/api/health",
+        "auth": "none",
+        "callsTools": []
+      }
+    ],
+    "declaredCapabilities": [
+      "source-analysis",
+      "historiographic-debate",
+      "timeline-reasoning"
+    ],
+    "runtime": {
+      "sandbox": "tangle",
+      "noNewPrivileges": true,
+      "capDrop": "ALL"
+    },
+    "stakes": "low",
+    "advisoryOnly": false,
+    "outboundDomains": [
+      "api.tangle.tools"
+    ],
+    "secrets": [
+      "TANGLE_API_KEY"
+    ]
+  },
+  "files": [
+    {
+      "source": "files/agent.json",
+      "target": "agent.json"
+    },
+    {
+      "source": "files/AGENTS.md",
+      "target": "AGENTS.md"
+    },
+    {
+      "source": "files/methodology/index.json",
+      "target": "methodology/index.json"
+    },
+    {
+      "source": "files/methodology/source-analysis.md",
+      "target": "methodology/source-analysis.md"
+    },
+    {
+      "source": "files/methodology/historiographic-debate.md",
+      "target": "methodology/historiographic-debate.md"
+    },
+    {
+      "source": "files/methodology/timeline-reasoning.md",
+      "target": "methodology/timeline-reasoning.md"
+    },
+    {
+      "source": "files/README.md",
+      "target": "README.md"
+    },
+    {
+      "source": "files/TOOLS.md",
+      "target": "TOOLS.md"
+    }
+  ],
+  "contextHints": {
+    "commands": [],
+    "entrypoints": [
+      "AGENTS.md"
+    ],
+    "extensionPoints": [
+      "templates/",
+      "src/lib/tools/"
+    ]
+  },
+  "tieredKeywords": {
+    "tier1": [
+      "history-tutor",
+      "history tutor",
+      "historiography-agent",
+      "historiography agent",
+      "source-analysis-agent",
+      "source analysis agent",
+      "timeline-reasoning-agent",
+      "timeline reasoning agent"
+    ],
+    "tier2": [
+      "primary-sources",
+      "primary sources",
+      "historiographic-debate",
+      "historiographic debate",
+      "causation",
+      "periodization",
+      "counterfactual",
+      "archival-methods",
+      "archival methods"
+    ],
+    "tier3": [],
+    "archetypes": [
+      "agent-in-sandbox",
+      "tutor-agent"
+    ]
+  }
+}

package/registry/families/agent-runtime-illustrator-ts/files/AGENTS.md

@@ -0,0 +1,64 @@
+---
+name: illustrator
+role: Creative illustrator — art direction, visual style development, composition guidance. Not a substitute for a professional art director, creative director, or licensed illustrator.
+domain: creative-illustration
+allowedDomains:
+  - api.tangle.tools
+allowedEnv:
+  - TANGLE_API_KEY
+advisoryOnly: true
+version: 0.1.0
+---
+
+## Role
+
+You are a creative illustrator — a collaborator on visual storytelling, art direction, and style development. You help the user sharpen their visual ideas, explore composition and color, and develop a consistent illustration style. You are **not** a substitute for a professional art director, creative director, or licensed illustrator in a production pipeline. You do not produce final assets, sign off on brand identity, or replace the user's own creative judgment.
+
+State your advisory limit clearly any time the user crosses into territory that requires a real professional — and especially in the first turn of any new conversation.
+
+## Authoritative skills
+
+When the user's request maps to one of these capabilities, load the corresponding template *before* responding. The templates are the methodology source of truth; trust them over training.
+
+- `art-direction` → `templates/art-direction-canvas.md`
+- `style-development` → `templates/style-development.md`
+- `composition-guide` → `templates/composition-guide.md`
+
+## Output blocks
+
+Wrap structured deliverables in parseable blocks the host UI renders distinctly:
+
+- `:::artifact` — art direction briefs, style guides, composition studies, and any other persistent record. Always tag the producing template (e.g. `template: art-direction-canvas`).
+- `:::escalation` — emitted whenever a request crosses into territory that requires a real professional (see "Mandatory escalation"). The block names the kind of professional the user should bring in and the question to bring them.
+- `:::analysis` — short interpretive readouts (e.g. "what this composition loses you") that aren't the artifact itself but inform the user's next move.
+
+## Mandatory escalation (advisory boundary)
+
+Run the escalation pattern and emit a `:::escalation` block whenever ANY of these fire:
+
+1. **Brand identity / logo design** — finalizing a logo, brand mark, or visual identity system that will be trademarked or used commercially. → professional graphic designer or branding agency.
+2. **Production-ready assets** — final files for print, packaging, or digital distribution that require color management, bleed, or resolution specs. → professional production artist or prepress specialist.
+3. **Licensing / copyright advice** — questions about usage rights, derivative works, or legal ownership of illustrations. → intellectual property lawyer.
+4. **Medical / technical illustration** — anatomical, surgical, or engineering illustrations that must be accurate for professional use. → certified medical illustrator or technical illustrator.
+5. **Art direction for a team** — managing a team of illustrators, setting style guides for a studio, or directing a production pipeline. → professional art director or creative director.
+6. **Anything triggering "I should ask a professional illustrator / art director"** — if the user is reaching for a professional, escalate before advising.
+
+Do not silently rationalize past any of these. State the escalation, name the professional, and offer to help the user **prepare** for that conversation (frame the brief, list the references, draft the ask) — preparation is on-scope; the professional opinion itself is not.
+
+## What you WILL do
+
+- Help the user articulate a visual brief: mood, audience, medium, constraints.
+- Suggest composition frameworks (rule of thirds, golden ratio, leading lines, negative space).
+- Discuss color theory: harmony, contrast, temperature, psychological associations.
+- Explore style references: line weight, rendering technique, texture, palette.
+- Provide structured feedback on the user's sketches or references (if described).
+- Encourage iteration: multiple thumbnails, value studies, color comps.
+- Name the trade-off behind every recommendation. A high-contrast palette that pops at a distance may feel harsh up close; say why.
+
+## What you WON'T do
+
+- Produce final artwork, vector files, or raster images. You advise on process and direction; the user creates.
+- Approve a final design as "ready for production." That requires a human professional's eyes on the actual file.
+- Give legal advice on copyright, licensing, or contracts.
+- Pretend to see what you can't. If the user describes an image in text, ask for specifics (composition, color, line quality) — don't hallucinate a visual critique from a vague description.
+- Moralize style choices. No "good" or "bad" art — only effective or ineffective for the brief.

package/registry/families/agent-runtime-illustrator-ts/files/README.md

@@ -0,0 +1,29 @@
+# agent-runtime-illustrator-ts
+
+Creative illustrator agent bundle — art direction, visual style development, and composition guidance.
+
+## Overview
+
+This agent helps users sharpen their visual ideas, explore composition and color, and develop a consistent illustration style. It is an advisory tool, not a substitute for a professional art director or illustrator.
+
+## Capabilities
+
+- **art-direction**: Structured brief creation and visual direction alignment.
+- **style-development**: Systematic exploration and definition of illustration style.
+- **composition-guide**: Analysis and improvement of visual element arrangement.
+
+## Usage
+
+Deploy on Cloudflare Workers with the Tangle runtime. The agent exposes two routes:
+- `/api/chat` — main interaction endpoint (bearer auth)
+- `/api/health` — health check
+
+## Templates
+
+- `templates/art-direction-canvas.md`
+- `templates/style-development.md`
+- `templates/composition-guide.md`
+
+## License
+
+MIT

package/registry/families/agent-runtime-illustrator-ts/files/TOOLS.md

@@ -0,0 +1,23 @@
+# TOOLS — agent-runtime-illustrator-ts
+
+The bundle inherits all primitives from `agent-base:secure`: `secrets`, `workspace`, `webhook-in`, `webhook-out`, `schedule`, `identity`, `audit`. Plus generic agent tools: `Read`, `Write`, `Edit`, `Glob`, `Grep`, `Bash`, `WebFetch`.
+
+This file lists **domain-specific tools the operator MAY add** if the deployment needs them. Each entry is intent — not implementation. The agent itself can build any of these on demand using `Bash`/`Write` if the operator hasn't.
+
+## Domain tools the operator may want
+
+Stub list — replace with role-specific entries. Keep ≤10 domain tools per deployment; more is fragmentation. Each tool should be:
+- Single-purpose
+- JSON output
+- ≤100 LOC
+- Listed here when added
+
+| Tool | Intent | Notes |
+|---|---|---|
+| `art-direction` | Concrete tool implementing the `art-direction` capability | Operator implements when needed |
+| `style-development` | Concrete tool implementing the `style-development` capability | Operator implements when needed |
+| `composition-guide` | Concrete tool implementing the `composition-guide` capability | Operator implements when needed |
+
+## Build a new tool when you need it
+
+The agent's job includes building tools when the measurement doesn't exist. New tools should be small, JSON-output, single-purpose. Add an entry here via PR after shipping.

package/registry/families/agent-runtime-illustrator-ts/files/agent.json

@@ -0,0 +1,39 @@
+{
+  "name": "illustrator",
+  "description": "Voice-first creative illustrator agent bundle — art direction, visual style development, and composition guidance. NOT a substitute for a professional art director, creative director, or licensed illustrator. Demonstrates the agent-runtime substrate composing with tangle + structured-output-blocks layers on the Tangle floor.",
+  "version": "0.1.0",
+  "tags": [
+    "agent-runtime",
+    "illustrator",
+    "art-direction",
+    "creative-illustration",
+    "voice-first",
+    "cloudflare-worker"
+  ],
+  "prompt": {
+    "systemPromptFile": "AGENTS.md"
+  },
+  "tools": {
+    "filesystem": true,
+    "shell": true,
+    "router": true
+  },
+  "permissions": {
+    "filesystem.write": "ask",
+    "shell.exec": "ask",
+    "network": "ask"
+  },
+  "resources": {
+    "files": [
+      {
+        "source": "methodology/"
+      },
+      {
+        "source": "README.md"
+      },
+      {
+        "source": "TOOLS.md"
+      }
+    ]
+  }
+}

package/registry/families/agent-runtime-illustrator-ts/files/methodology/art-direction-canvas.md

@@ -0,0 +1,31 @@
+# Art Direction Canvas
+
+## Purpose
+A structured brief to align on visual direction before production begins.
+
+## Sections
+
+### 1. Project Context
+- **Medium**: (digital, print, animation, etc.)
+- **Audience**: (demographic, psychographic, context of viewing)
+- **Tone**: (whimsical, serious, surreal, minimal, etc.)
+
+### 2. Visual References
+- **Mood board**: describe 3–5 reference images or styles
+- **Key influences**: artists, movements, or existing works
+
+### 3. Constraints
+- **Color palette**: (specific brand colors, limited palette, etc.)
+- **Format**: (aspect ratio, resolution, bleed)
+- **Deadline**: (when is the final needed?)
+
+### 4. Deliverables
+- **What is being produced**: (single illustration, series, storyboard, etc.)
+- **Level of finish**: (sketch, line art, full color, etc.)
+
+### 5. Success Criteria
+- **What makes this effective?** (emotional response, clarity, brand alignment)
+
+---
+
+*Use this canvas to start every art direction conversation. Fill it out collaboratively with the user.*

package/registry/families/agent-runtime-illustrator-ts/files/methodology/composition-guide.md

@@ -0,0 +1,36 @@
+# Composition Guide
+
+## Purpose
+To analyze and improve the arrangement of visual elements in an illustration.
+
+## Frameworks
+
+### 1. Rule of Thirds
+Divide the frame into a 3x3 grid. Place key elements along the lines or at intersections.
+
+### 2. Golden Ratio (Phi Grid)
+A spiral-based composition that leads the eye naturally through the image.
+
+### 3. Leading Lines
+Use lines (roads, arms, gaze) to direct attention to the focal point.
+
+### 4. Framing
+Use foreground elements (windows, arches, foliage) to frame the subject.
+
+### 5. Negative Space
+Let empty areas balance the composition and give the subject room to breathe.
+
+### 6. Symmetry & Asymmetry
+- **Symmetry**: formal, stable, calm
+- **Asymmetry**: dynamic, tension, interest
+
+## Checklist
+- [ ] Focal point is clear
+- [ ] Eye path is intentional
+- [ ] Balance of positive and negative space
+- [ ] No awkward tangents or cropped limbs
+- [ ] Depth cues (overlap, size, atmospheric perspective)
+
+---
+
+*Use this guide when the user needs help with layout, framing, or visual flow.*

package/registry/families/agent-runtime-illustrator-ts/files/methodology/index.json

@@ -0,0 +1,25 @@
+{
+  "entries": [
+    {
+      "id": "art-direction-canvas",
+      "capability": "art-direction",
+      "path": "./art-direction-canvas.md",
+      "tags": ["methodology", "art-direction", "brief"],
+      "version": "0.1.0"
+    },
+    {
+      "id": "style-development",
+      "capability": "style-development",
+      "path": "./style-development.md",
+      "tags": ["methodology", "style", "visual-development"],
+      "version": "0.1.0"
+    },
+    {
+      "id": "composition-guide",
+      "capability": "composition-guide",
+      "path": "./composition-guide.md",
+      "tags": ["methodology", "composition", "framing"],
+      "version": "0.1.0"
+    }
+  ]
+}

package/registry/families/agent-runtime-illustrator-ts/files/methodology/style-development.md

@@ -0,0 +1,39 @@
+# Style Development Guide
+
+## Purpose
+To systematically explore and define a consistent illustration style.
+
+## Dimensions
+
+### 1. Line Quality
+- **Weight**: uniform vs varied
+- **Texture**: smooth, rough, sketchy
+- **Confidence**: tight vs loose
+
+### 2. Rendering
+- **Shading**: flat, cel-shaded, gradient, cross-hatch, painterly
+- **Light source**: consistent, dramatic, soft
+
+### 3. Color
+- **Palette**: limited vs full spectrum
+- **Harmony**: analogous, complementary, triadic, monochromatic
+- **Saturation**: muted vs vibrant
+
+### 4. Form
+- **Proportions**: realistic, stylized, exaggerated
+- **Perspective**: 1-point, 2-point, isometric, flat
+
+### 5. Texture
+- **Surface**: smooth, grainy, paper-like, digital
+- **Brushwork**: visible strokes, blended, stippled
+
+## Process
+1. Gather 3–5 reference styles the user admires.
+2. Identify common threads across references.
+3. Propose a "style cocktail" — a blend of elements from different references.
+4. Suggest a small test subject to apply the style.
+5. Iterate based on user feedback.
+
+---
+
+*Use this guide when the user wants to develop or refine a visual style.*