Inanis_Vault/23-Cooking/docs/superpowers/plans/2026-03-25-location-file.md

Location File Implementation Plan

For agentic workers: REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (- [ ]) syntax for tracking.

Goal: Build a location file system — a template for documenting local market conditions and a CLAUDE.md that tells Claude Code how to process those files into structured analysis.

Architecture: Two files. Locations/_Location Template.md is the user-facing template: blank zones with a fully-worked Tbilisi, Georgia example showing exactly what to fill in. CLAUDE.md is the agent-facing instruction file: tells Claude Code how to read a location file and produce all five analysis subsections when the user says "Process my [City] location file" or "Update my [City] location file".

Tech Stack: Markdown, Obsidian wiki links, CLAUDE.md (Claude Code context file).

---

File Map

Action	File	Responsibility
Create	Locations/_Location Template.md	Four-zone template with blank fields + worked Tbilisi example
Create	CLAUDE.md	Agent processing instructions for generate and update workflows

---

Task 1: Create Locations/_Location Template.md

Files:

• Create: Locations/_Location Template.md

• Step 1: Create the Locations folder and template file

Create C:\Users\toami\Inanis_Vault\23-Cooking\Locations\_Location Template.md with this exact content:

# [City, Country]

**Region:** [e.g. Northern Thailand, Catalonia, Oaxacan Valleys]
**First visited:** [YYYY-MM-DD]
**Last updated:** [YYYY-MM-DD]

---

## Observations
*Fill this in before running the agent. Either format works — freeform dump, structured fields, or both.*

**Freeform notes:**
[Write whatever you see — proteins, produce, what's abundant, what's absent, prices, anything notable]

**Structured fields:**
```
Proteins seen:
Produce seen:
Starches:
Fats available:
Acids available:
Aromatics:
Condiments:
Notables:
First impressions:
```

---

### Example — Tbilisi, Georgia
*This shows the expected detail level. Delete this section from your own location files.*

**Freeform notes:**
Markets are covered and permanent — not just weekend affairs. Walnuts everywhere and cheap, used as both protein and fat. Tkemali (sour plum sauce) is the primary condiment and acid. Lamb and pork are the dominant proteins; chicken is available but less interesting. Sulguni cheese is salty and stretchy, used in everything. Bread culture is strong — shoti (torpedo-shaped) and lavash baked fresh. Strong wine culture; local wine vinegars available. Fresh tarragon, dill, and cilantro dominate the herb section.

**Structured fields:**
```
Proteins seen:     lamb, pork, chicken, eggs, walnuts, sulguni cheese
Produce seen:      eggplant, tomatoes, peppers, spinach, beets, beans
Starches:          shoti bread, lavash, potatoes, dried beans (lobio)
Fats available:    sunflower oil, butter, walnut paste
Acids available:   tkemali (sour plum sauce), wine vinegar, pomegranate
Aromatics:         garlic, onion, tarragon, dill, cilantro, fenugreek (utskho suneli), coriander seed
Condiments:        tkemali, adjika (spicy walnut-pepper paste), satsebeli (tomato-walnut sauce)
Notables:          blue fenugreek (utskho suneli) — the defining Georgian spice; churchkhela (walnut-grape snack)
First impressions: Walnuts are a staple fat+protein here, not a garnish. Tkemali does the acid work that citrus does elsewhere. Georgian cuisine sits between Middle Eastern and Eastern European — it doesn't fit cleanly into any of the 10 profiles, which makes it a good test of the substitution system.
```

---

## Analysis
*Agent fills this in. Say "Process my [City, Country] location file" in Claude Code.*

### Ingredient Role Map
*Agent fills in — your observations mapped to framework roles (Fat / Acid / Aromatic / Starch / Protein / Umami)*

### Profile Matches
*Agent fills in — which of the 10 profiles work here, with confidence indicators (✦ partial / ✦✦ workable / ✦✦✦ full)*

### Meal Options
*Agent fills in — 3–5 concrete builds using what's available, formatted as formula fills*

### Regional Intelligence
*Agent fills in — what's culinarily notable and different about this location*

### Things to Look Out For
*Agent fills in — specific ingredients or products worth seeking, with a brief note on each*

---

## Visit Log
*Append dated entries here on each visit. Say "Update my [City, Country] location file" to refresh the analysis.*

### [YYYY-MM-DD] (first visit)
[Your notes from this visit — what you found, what surprised you, what was missing]

• Step 2: Verify the file was created correctly

Check that:

• The file exists at Locations/_Location Template.md

• Zone headers are present: ## Observations, ## Analysis, ## Visit Log

• The Tbilisi example section is present with both freeform and structured fields filled in

• The Analysis zone has all five placeholder subsections: Ingredient Role Map, Profile Matches, Meal Options, Regional Intelligence, Things to Look Out For

• Step 3: Commit

git add "23-Cooking/Locations/_Location Template.md"
git commit -m "add location file template — four-zone structure with Tbilisi example"

---

Task 2: Create CLAUDE.md

Files:

• Create: CLAUDE.md

• Step 1: Create the file with full content

Create C:\Users\toami\Inanis_Vault\23-Cooking\CLAUDE.md with this exact content:

# Cooking Framework — Claude Code Instructions

This directory contains a personal cooking framework for a frequent traveler. The system uses a formula-based approach: every meal = Protein + Produce + Starch + Fat + Acid + Aromatic + Technique.

## Key Reference Files

- `Flavor Sense.md` — the four flavor mechanisms (fat as solvent, acid resets palate, salt in layers, browning creates umami)
- `Flavor Profile Formulas.md` — 10 flavor profiles as role principles with "identify by" cues
- `Role Substitution Logic.md` — substitution hierarchies for each role
- `Frameworks.md` — three cooking techniques: One-Pan Sear, Steam-Sauté, Starch-Buffer
- `Weekly Planning Template.md` — market-first meal planning entry point
- `Essential Non-Perishables.md` — pantry stocking guide

---

## Location File Workflow

Location files live in `Locations/[City, Country].md`. They have four zones:
- **Zone 1 (Header):** Location name, region, first visited, last updated
- **Zone 2 (Observations):** User-filled market notes — freeform or structured fields
- **Zone 3 (Analysis):** Agent-generated output — five subsections
- **Zone 4 (Visit Log):** Chronological user notes from each visit

### When the user says "Process my [City] location file"

1. Find the file at `Locations/[City, Country].md`
2. Read Zone 2 (Observations) — parse both freeform text and structured fields; treat them as the same pool of information
3. Map observations to framework roles using `Role Substitution Logic.md`:
   - Fat: any cooking oil, animal fat, or dairy fat mentioned
   - Acid: citrus, vinegar, fermented liquids, sour dairy, or sour-tasting condiments
   - Aromatic: alliums + any secondary aromatics (ginger, lemongrass, spices, herbs)
   - Starch: any grain, root vegetable, legume, or bread
   - Protein: any meat, fish, egg, legume, or tofu
   - Umami: any fermented condiment, aged cheese, concentrated tomato, or mushroom
4. Match observations to the 10 profiles in `Flavor Profile Formulas.md`. Assign confidence:
   - ✦✦✦ = all three defining elements (fat + acid + aromatic character) present
   - ✦✦ = two of three defining elements present, or key secondary aromatics missing
   - ✦ = only partial match; note specifically what's absent
   - Omit profiles that score below ✦ (nothing available)
5. Generate 3–5 meal options using available ingredients. Each formatted as:
   `*[Meal name]* — [Technique] · [Profile] · [protein] / [produce] / [starch] / [fat] / [acid] / [aromatic]`
   Use techniques from `Frameworks.md`: One-Pan Sear or Steam-Sauté (Starch-Buffer if microwave available)
6. Write 3–5 bullet points of regional intelligence — what's culinarily notable about this location, what differs from the framework's defaults, what a traveler would benefit from knowing. Draw on your knowledge of the region's culinary traditions.
7. Write 3–5 "things to look out for" — specific ingredients or products worth seeking on the next market visit, each with a one-line explanation of why it matters (flavor role, rarity, value)
8. Replace Zone 3 (Analysis) with the five subsections filled in
9. In Zone 1, set "First visited" to today's date if currently blank; set "Last updated" to today's date
10. Stage and commit:
    ```bash
    git add "23-Cooking/Locations/[City, Country].md"
    git commit -m "generate location file: [City, Country]"
    ```

### When the user says "Update my [City] location file"

1. Find the file at `Locations/[City, Country].md`
2. Read Zone 2 (Observations) AND Zone 4 (Visit Log) — the full visit log supplements and may revise the original observations; treat both as one combined pool of information
3. Re-run steps 3–8 from the generate workflow above using the combined observations
4. In Zone 1, set "Last updated" to today's date; leave "First visited" unchanged
5. Stage and commit:
    ```bash
    git add "23-Cooking/Locations/[City, Country].md"
    git commit -m "update location file: [City, Country]"
    ```

---

## Analysis Output Format

### Ingredient Role Map
Inline format, one line:
> **Fat:** [items] | **Acid:** [items] | **Aromatic:** [items] | **Starch:** [items] | **Protein:** [items] | **Umami:** [items]

### Profile Matches
One line per profile, ordered by confidence (highest first):
> [Profile Name] ✦✦✦
> [Profile Name] ✦✦ (missing: [specific absent element])
> [Profile Name] ✦ (missing: [specific absent elements])

### Meal Options
3–5 items, one per line, italicised meal name:
> *[Meal name]* — [Technique] · [Profile] · [protein] / [produce] / [starch] / [fat] / [acid] / [aromatic]

### Regional Intelligence
3–5 bullet points. Focus on: staple ingredients, local cooking patterns, things that differ from framework defaults, and anything a traveler without local knowledge would miss.

### Things to Look Out For
3–5 items, each with name and one-line explanation:
> **[Ingredient/product]** — [why it matters: flavor role, what profile it unlocks, rarity, or value]

• Step 2: Verify the file was created correctly

Check that:

• The file exists at 23-Cooking/CLAUDE.md

• Both workflow sections are present: "Process my [City] location file" and "Update my [City] location file"

• All five Analysis output format sections are present with their format examples

• The 10-step generate workflow and 5-step update workflow are complete

• Step 3: Commit

git add "23-Cooking/CLAUDE.md"
git commit -m "add CLAUDE.md — agent instructions for location file processing"