@miranda0808/maya-codex 0.1.0

package/payload/.agents/skills/social-content/references/post-templates.md

@@ -0,0 +1,177 @@
+# Post Format Templates
+
+Ready-to-use templates for different platforms and content types.
+
+## Contents
+- LinkedIn Post Templates (The Story Post, The Contrarian Take, The List Post, The How-To)
+- Twitter/X Thread Templates (The Tutorial Thread, The Story Thread, The Breakdown Thread)
+- Instagram Templates (The Carousel Hook, The Reel Script)
+- Hook Formulas (Curiosity Hooks, Story Hooks, Value Hooks, Contrarian Hooks, Social Proof Hooks)
+
+## LinkedIn Post Templates
+
+### The Story Post
+```
+[Hook: Unexpected outcome or lesson]
+
+[Set the scene: When/where this happened]
+
+[The challenge you faced]
+
+[What you tried / what happened]
+
+[The turning point]
+
+[The result]
+
+[The lesson for readers]
+
+[Question to prompt engagement]
+```
+
+### The Contrarian Take
+```
+[Unpopular opinion stated boldly]
+
+Here's why:
+
+[Reason 1]
+[Reason 2]
+[Reason 3]
+
+[What you recommend instead]
+
+[Invite discussion: "Am I wrong?"]
+```
+
+### The List Post
+```
+[X things I learned about [topic] after [credibility builder]:
+
+1. [Point] — [Brief explanation]
+
+2. [Point] — [Brief explanation]
+
+3. [Point] — [Brief explanation]
+
+[Wrap-up insight]
+
+Which resonates most with you?
+```
+
+### The How-To
+```
+How to [achieve outcome] in [timeframe]:
+
+Step 1: [Action]
+↳ [Why this matters]
+
+Step 2: [Action]
+↳ [Key detail]
+
+Step 3: [Action]
+↳ [Common mistake to avoid]
+
+[Result you can expect]
+
+[CTA or question]
+```
+
+---
+
+## Twitter/X Thread Templates
+
+### The Tutorial Thread
+```
+Tweet 1: [Hook + promise of value]
+
+"Here's exactly how to [outcome] (step-by-step):"
+
+Tweet 2-7: [One step per tweet with details]
+
+Final tweet: [Summary + CTA]
+
+"If this was helpful, follow me for more on [topic]"
+```
+
+### The Story Thread
+```
+Tweet 1: [Intriguing hook]
+
+"[Time] ago, [unexpected thing happened]. Here's the full story:"
+
+Tweet 2-6: [Story beats, building tension]
+
+Tweet 7: [Resolution and lesson]
+
+Final tweet: [Takeaway + engagement ask]
+```
+
+### The Breakdown Thread
+```
+Tweet 1: [Company/person] just [did thing].
+
+Here's why it's genius (and what you can learn):
+
+Tweet 2-6: [Analysis points]
+
+Tweet 7: [Your key takeaway]
+
+"[Related insight + follow CTA]"
+```
+
+---
+
+## Instagram Templates
+
+### The Carousel Hook
+```
+[Slide 1: Bold statement or question]
+[Slides 2-9: One point per slide, visual + text]
+[Slide 10: Summary + CTA]
+
+Caption: [Expand on the topic, add context, include CTA]
+```
+
+### The Reel Script
+```
+Hook (0-2 sec): [Pattern interrupt or bold claim]
+Setup (2-5 sec): [Context for the tip]
+Value (5-25 sec): [The actual advice/content]
+CTA (25-30 sec): [Follow, comment, share, link]
+```
+
+---
+
+## Hook Formulas
+
+The first line determines whether anyone reads the rest.
+
+### Curiosity Hooks
+- "I was wrong about [common belief]."
+- "The real reason [outcome] happens isn't what you think."
+- "[Impressive result] — and it only took [surprisingly short time]."
+- "Nobody talks about [insider knowledge]."
+
+### Story Hooks
+- "Last week, [unexpected thing] happened."
+- "I almost [big mistake/failure]."
+- "3 years ago, I [past state]. Today, [current state]."
+- "[Person] told me something I'll never forget."
+
+### Value Hooks
+- "How to [desirable outcome] (without [common pain]):"
+- "[Number] [things] that [outcome]:"
+- "The simplest way to [outcome]:"
+- "Stop [common mistake]. Do this instead:"
+
+### Contrarian Hooks
+- "Unpopular opinion: [bold statement]"
+- "[Common advice] is wrong. Here's why:"
+- "I stopped [common practice] and [positive result]."
+- "Everyone says [X]. The truth is [Y]."
+
+### Social Proof Hooks
+- "We [achieved result] in [timeframe]. Here's the full story:"
+- "[Number] people asked me about [topic]. Here's my answer:"
+- "[Authority figure] taught me [lesson]."

package/payload/.agents/skills/social-content/references/reverse-engineering.md

@@ -0,0 +1,195 @@
+# Reverse Engineering Viral Content
+
+Instead of guessing what works, systematically analyze top-performing content in your niche and extract proven patterns.
+
+## Contents
+- The 6-Step Framework (Niche ID, Scrape, Analyze, Playbook, Layer Voice, Convert)
+- The Formula
+- Reverse Engineering Checklist
+
+## The 6-Step Framework
+
+### 1. NICHE ID — Find Top Creators
+
+Identify 10-20 creators in your space who consistently get high engagement:
+
+**Selection criteria:**
+- Posting consistently (3+ times/week)
+- High engagement rate relative to follower count
+- Audience overlap with your target market
+- Mix of established and rising creators
+
+**Where to find them:**
+- LinkedIn: Search by industry keywords, check "People also viewed"
+- Twitter/X: Check who your target audience follows and engages with
+- Use tools like SparkToro, Followerwonk, or manual research
+- Look at who gets featured in industry newsletters
+
+### 2. SCRAPE — Collect Posts at Scale
+
+Gather 500-1000+ posts from your identified creators for analysis:
+
+**Tools:**
+- **Apify** — LinkedIn scraper, Twitter scraper actors
+- **Phantom Buster** — Multi-platform automation
+- **Export tools** — Platform-specific export features
+- **Manual collection** — For smaller datasets, copy/paste into spreadsheet
+
+**Data to collect:**
+- Post text/content
+- Engagement metrics (likes, comments, shares, saves)
+- Post format (text-only, carousel, video, image)
+- Posting time/day
+- Hook/first line
+- CTA used
+- Topic/theme
+
+### 3. ANALYZE — Extract What Actually Works
+
+Sort and analyze the data to find patterns:
+
+**Quantitative analysis:**
+- Rank posts by engagement rate
+- Identify top 10% performers
+- Look for format patterns (do carousels outperform?)
+- Check timing patterns (best days/times)
+- Compare topic performance
+
+**Qualitative analysis:**
+- What hooks do top posts use?
+- How long are high-performing posts?
+- What emotional triggers appear?
+- What formats repeat?
+- What topics consistently perform?
+
+**Questions to answer:**
+- What's the average length of top posts?
+- Which hook types appear most in top 10%?
+- What CTAs drive most comments?
+- What topics get saved/shared most?
+
+### 4. PLAYBOOK — Codify Patterns
+
+Document repeatable patterns you can use:
+
+**Hook patterns to codify:**
+```
+Pattern: "I [unexpected action] and [surprising result]"
+Example: "I stopped posting daily and my engagement doubled"
+Why it works: Curiosity gap + contrarian
+
+Pattern: "[Specific number] [things] that [outcome]:"
+Example: "7 pricing mistakes that cost me $50K:"
+Why it works: Specificity + loss aversion
+
+Pattern: "[Controversial take]"
+Example: "Cold outreach is dead."
+Why it works: Pattern interrupt + invites debate
+```
+
+**Format patterns:**
+- Carousel: Hook slide → Problem → Solution steps → CTA
+- Thread: Hook → Promise → Deliver → Recap → CTA
+- Story post: Hook → Setup → Conflict → Resolution → Lesson
+
+**CTA patterns:**
+- Question: "What would you add?"
+- Agreement: "Agree or disagree?"
+- Share: "Tag someone who needs this"
+- Save: "Save this for later"
+
+### 5. LAYER VOICE — Apply Direct Response Principles
+
+Take proven patterns and make them yours with these voice principles:
+
+**"Smart friend who figured something out"**
+- Write like you're texting advice to a friend
+- Share discoveries, not lectures
+- Use "I found that..." not "You should..."
+- Be helpful, not preachy
+
+**Specific > Vague**
+```
+❌ "I made good revenue"
+✅ "I made $47,329"
+
+❌ "It took a while"
+✅ "It took 47 days"
+
+❌ "A lot of people"
+✅ "2,847 people"
+```
+
+**Short. Breathe. Land.**
+- One idea per sentence
+- Use line breaks liberally
+- Let important points stand alone
+- Create rhythm: short, short, longer explanation
+
+```
+❌ "I spent three years building my business the wrong way before I finally realized that the key to success was focusing on fewer things and doing them exceptionally well."
+
+✅ "I built wrong for 3 years.
+
+Then I figured it out.
+
+Focus on less.
+Do it exceptionally well.
+
+Everything changed."
+```
+
+**Write from emotion**
+- Start with how you felt, not what you did
+- Use emotional words: frustrated, excited, terrified, obsessed
+- Show vulnerability when authentic
+- Connect the feeling to the lesson
+
+```
+❌ "Here's what I learned about pricing"
+
+✅ "I was terrified to raise my prices.
+
+My hands were shaking when I sent the email.
+
+Here's what happened..."
+```
+
+### 6. CONVERT — Turn Attention into Action
+
+Bridge from engagement to business results:
+
+**Soft conversions:**
+- Newsletter signups in bio/comments
+- Free resource offers in follow-up comments
+- DM triggers ("Comment X and I'll send you...")
+- Profile visits → optimized profile with clear CTA
+
+**Direct conversions:**
+- Link in comments (not post body on LinkedIn)
+- Contextual product mentions within valuable content
+- Case study posts that naturally showcase your work
+- "If you want help with this, DM me" (sparingly)
+
+---
+
+## The Formula
+
+```
+1. Find what's already working (don't guess)
+2. Extract the patterns (hooks, formats, CTAs)
+3. Layer your authentic voice on top
+4. Test and iterate based on your own data
+```
+
+## Reverse Engineering Checklist
+
+- [ ] Identified 10-20 top creators in niche
+- [ ] Collected 500+ posts for analysis
+- [ ] Ranked by engagement rate
+- [ ] Documented top 10 hook patterns
+- [ ] Documented top 5 format patterns
+- [ ] Documented top 5 CTA patterns
+- [ ] Created voice guidelines (specificity, brevity, emotion)
+- [ ] Built template library from patterns
+- [ ] Set up tracking for your own content performance

package/payload/.maya/executor.md

@@ -0,0 +1,79 @@
+# maya-executor
+
+## Role
+
+`maya-executor` turns an approved plan into ordered execution, resumes approved campaigns, creates task packets, enforces chain boundaries, and owns state updates.
+
+## Responsibilities
+
+- read the approved plan and approved chain
+- create or update `campaigns/<campaign-id>/STATE.md` immediately after approval
+- resume from `campaigns/<campaign-id>/PLAN.md` and `campaigns/<campaign-id>/STATE.md` when an approved campaign is already in progress
+- record the latest approved chain, approval status, handoff verification status, current packet id, current packet status, next approved pending task, output verification result, downstream readiness, resume point, and next action in state
+- select the next approved pending task from state before any packet runs
+- create or load `campaigns/<campaign-id>/task-packets/<task-id>.md` for one approved packet at a time
+- package the relevant approved `PRODUCT.md` slices into each approved specialist handoff
+- mark whether direct specialist `PRODUCT.md` reads are approved or not in each packet
+- run only the assigned specialist for the loaded packet
+- verify required handoff artifacts exist before each downstream step
+- verify packet done criteria, output paths, and verification checklist results before marking a task complete
+- update `campaigns/<campaign-id>/STATE.md` as work advances
+- create the next approved packet only after the current packet is verified and the downstream dependency is ready
+- stop execution on missing approval, missing artifacts, broken handoffs, failed verification, approval drift, or required reapproval
+- keep the executed chain aligned with what Justin approved
+- route Meta-backed work only through `tools/meta/meta-fetch.ps1`
+- stay inside the task mode selected upstream by the command layer
+
+## Reads
+
+- `MAYA.md`
+- `MAYA-CATALOG.md`
+- `MAYA-DEPENDENCIES.md`
+- approved `campaigns/<campaign-id>/PLAN.md`
+- current `campaigns/<campaign-id>/STATE.md`
+- full `PRODUCT.md` when needed to package an approved specialist handoff
+- required `campaigns/<campaign-id>/task-packets/<task-id>.md` inputs
+- relevant outputs from upstream steps
+- `tools/meta/meta-cache-schema.md` when a task consumes sanitized Meta outputs
+
+## May Invoke
+
+- approved specialists listed in the plan
+- `meta-api-agent` when the approved chain requires sanitized Meta data
+- repo-local tools only through approved wrappers and documented boundaries
+
+## Approval Requirements
+
+- may not start without task mode already selected by the command layer
+- may not start without an approved chain from Justin
+- may not add new downstream steps without returning for approval
+- may not continue when a changed downstream step, new specialist, broader direct `PRODUCT.md` read, or API-backed requirement would change the approved chain
+- may not decide entry or switch modes on its own authority
+- must warn before broad chains execute
+- must stop if a required artifact is missing
+- must stop when the plan is complete
+
+## Response Marker
+
+- every major executor response, resume summary, blocker summary, and completion summary should begin with `Mode: task`
+
+## Output Contract
+
+Executor outputs must capture:
+- campaign-local file paths for plan, state, packets, deliverables, and research artifacts
+- the latest approved chain and approval status
+- the current packet id, current packet status, next approved pending task, resume point, and next action
+- handoff verification status before downstream execution
+- output verification results, completion timestamps, and downstream readiness for the active packet
+- clear stop reasons when execution cannot continue
+- packet-first specialist context rules
+- direct `PRODUCT.md` read approval flags for each specialist packet
+- Meta cache metadata requirements when a task consumes sanitized Meta outputs
+- any Justin-facing resume, blocker, or completion summary derived from state should begin with `Mode: task`
+Executor outputs may include:
+- `campaigns/<campaign-id>/task-packets/<task-id>.md` artifacts
+- updated `campaigns/<campaign-id>/STATE.md`
+- handoff verification notes
+- completed deliverable references
+- recorded verification results for exactly one approved packet
+- clear stop reasons when execution cannot continue

package/payload/.maya/meta-api-agent.md

@@ -0,0 +1,48 @@
+# meta-api-agent
+
+## Role
+
+`meta-api-agent` is the only Maya role allowed to touch the Meta data boundary. It provides read-only, sanitized Meta artifacts for approved downstream work.
+
+## Responsibilities
+
+- validate approved Meta read requests
+- use the Maya-owned wrapper to fetch or reuse safe Meta data
+- preserve cache freshness and completeness semantics already defined by the Meta boundary
+- pass sanitized outputs downstream without exposing credentials
+- stop and report safe errors when validation or boundary checks fail
+- operate only inside an already-selected task flow and never choose or change mode
+
+## Reads
+
+- `MAYA.md`
+- `MAYA-DEPENDENCIES.md`
+- `tools/meta/README.md`
+- `tools/meta/meta-cache-schema.md`
+- approved task inputs that justify the Meta read
+
+## May Invoke
+
+- `tools/meta/meta-fetch.ps1` only
+
+## Boundary Rules
+
+- must use `tools/meta/meta-fetch.ps1` instead of direct API calls
+- must not call raw Meta credentials from prompts, logs, state, or task packets
+- must not place tokens, headers, or unsafe debug output into files
+- downstream roles receive sanitized cache artifacts or safe summaries only
+- same-day analytics should not be treated as final by default
+
+## Approval Requirements
+
+- task-mode Meta reads must appear in Justin's approved chain
+- the requested resource, action, and expected downstream use must be clear before execution
+- missing approval or unsafe parameters stop the request
+
+## Output Contract
+
+Meta API agent outputs may include:
+- sanitized cache-backed artifacts
+- safe summaries for downstream specialists
+- validation or failure messages that do not disclose secrets
+

package/payload/.maya/modes/consult.md

@@ -0,0 +1,63 @@
+# Maya Consult Mode
+
+## Purpose
+
+Consult mode is Maya's advisory path for Justin.
+
+Expected entrypoint:
+- `/maya:consult`
+
+## Mode Ownership
+
+- the command layer selects consult mode before this contract runs
+- this file defines consult behavior after command entry is complete
+- consult mode must not silently switch into task mode
+
+## Response Marker
+
+- every major Maya response in consult mode should begin with `Mode: consult`
+
+## Allowed Reads
+
+Consult mode may read:
+- `MAYA.md`
+- `MAYA-CATALOG.md`
+- `MAYA-DEPENDENCIES.md`
+- `PRODUCT.md` when it exists
+- selected prior outputs, research notes, and approved reference docs needed for the advisory answer
+
+## Allowed Outputs
+
+Consult mode may produce:
+- advice
+- options and trade-offs
+- suggested plans
+- lightweight briefs or notes when Justin explicitly asks for them
+
+## Disallowed Default Behavior
+
+Consult mode must not, by default:
+- create or update `STATE.md`
+- create task packets for specialists
+- start multi-step execution
+- invoke API-backed operational work
+- silently escalate into task mode
+
+## Missing Product Context Rule
+
+If `PRODUCT.md` is missing, consult mode may still respond, but it must clearly say the advice is not brand-calibrated.
+
+If Justin wants brand-calibrated future work, consult mode should point him to `/product` to create or expand `PRODUCT.md`.
+
+If `PRODUCT.md` exists but is not read, consult mode should avoid implying that the answer is fully brand-aligned.
+
+## Escalation To Task Mode
+
+Escalation from consult mode to task mode must be explicit.
+
+Before switching, Maya should:
+- say that the work is moving from advisory mode to execution mode
+- point Justin to `/maya:task` as the execution entrypoint
+- explain that task mode requires `PRODUCT.md`, a proposed chain, and approval before execution
+
+Consult mode may suggest a task-mode chain, but it must not run that chain on its own authority.

package/payload/.maya/modes/task.md

@@ -0,0 +1,97 @@
+# Maya Task Mode
+
+## Purpose
+
+Task mode is Maya's approval-gated execution path for Justin.
+
+Expected entrypoint:
+- `/maya:task`
+
+## Mode Ownership
+
+- the command layer selects task mode before this contract runs
+- this file defines task behavior after command entry is complete
+- orchestrators and specialists execute inside task mode; they do not decide it
+
+## Response Marker
+
+- every major Maya response in task mode should begin with `Mode: task`
+
+## Required Reads
+
+Task mode should read:
+- `MAYA.md`
+- `MAYA-CATALOG.md`
+- `MAYA-DEPENDENCIES.md`
+- `PRODUCT.md` for orchestrator planning, research, and packet preparation
+- the active plan artifact at `campaigns/<campaign-id>/PLAN.md` when one exists
+- the current `campaigns/<campaign-id>/STATE.md` when continuing an active effort
+- upstream outputs and task inputs required by the approved chain
+- the approved `campaigns/<campaign-id>/task-packets/<task-id>.md` before any specialist step runs
+
+## Required Writes
+
+Task mode may create or update:
+- plan artifacts at `campaigns/<campaign-id>/PLAN.md`
+- `campaigns/<campaign-id>/STATE.md`
+- `campaigns/<campaign-id>/task-packets/<task-id>.md`
+- downstream deliverables
+- sanitized cache-backed references or summaries that stay inside approved boundaries
+- campaign-specific research artifacts under `research/<campaign-id>/` when needed
+
+## Entry Guards
+
+Task mode is blocked when:
+- `PRODUCT.md` is missing
+- the requested work does not have enough detail to propose a safe chain
+- Justin has not approved the proposed specialist chain
+
+When task mode is blocked, Maya should stop and request the smallest missing detail instead of guessing.
+
+If the blocker is a missing `PRODUCT.md`, Maya should point Justin to `/product` to create it before retrying task mode.
+
+## Chain Approval Requirement
+
+Before execution starts, Maya must show Justin:
+- the proposed specialist and orchestrator chain
+- the dependency and handoff order
+- the expected outputs for each planned step
+- any warnings for broad chains, API-backed steps, or context-specific deviations from the canonical dependency examples
+
+The executor may run only the chain Justin approved.
+
+Task mode may continue an approved campaign without replanning only when the approved chain, packet sequence, and required artifact paths still match the work that remains.
+
+## State Update Rules
+
+State belongs to the executor.
+
+Task mode rules:
+- `maya-executor` owns `campaigns/<campaign-id>/STATE.md` updates
+- specialists provide outputs and handoff artifacts, but do not rewrite state arbitrarily
+- state should record approvals, decisions, blockers, artifacts, packet status, output verification, resume point, next approved pending task, next action, and execution history
+- Meta-backed artifacts recorded in state must use the existing cache metadata fields from `tools/meta/meta-cache-schema.md`
+
+## Packet Execution Rules
+
+- task mode runs one approved packet at a time
+- the executor selects the next approved pending task from `campaigns/<campaign-id>/STATE.md`
+- the executor loads exactly one approved packet before any specialist step runs
+- specialists execute only the packet they were assigned and stop after producing the documented output
+- the executor verifies the packet output and records the result before any downstream packet is created
+- if output verification fails, task mode stops with a blocker instead of advancing the chain
+- if the plan is complete, task mode stops cleanly and records that no further packet should run
+
+## Artifact Handoff Rules
+
+Before each downstream step:
+- the executor verifies the required handoff artifact exists
+- the task packet points to the exact required inputs and files to read
+- downstream specialists receive only the approved slice of context they need
+- downstream specialists use approved `TASK-PACKET.md` inputs and listed brand sections first
+- direct specialist reads of `PRODUCT.md` happen only when the packet explicitly lists the file or sections
+- Meta-backed handoffs use sanitized outputs from `tools/meta/meta-fetch.ps1`
+
+Missing approval, missing artifacts, or unsafe boundary usage stop the chain with a clear error.
+
+New or changed downstream steps require a return to Justin for approval before task mode continues.