agent-method 1.5.0

package/templates/full/.context/METHODOLOGY.md

@@ -0,0 +1,84 @@
+# Methodology Reference
+
+Pair with: entry point (CLAUDE.md / .cursorrules / AGENT.md)
+Use when: agent needs operational guidance beyond entry point rules
+
+This file contains methodology operational details that overflow from the entry point. For lite and standard integration profiles, the entry point stays lean — this file provides depth when needed. For full profile projects, this file serves as a reference but the entry point contains all rules directly.
+
+## Workflows
+
+Select based on query type:
+- **General task** — Review, Plan, Implement, Document, Update
+- **Code change** — Review, Plan, Implement, Context-sync, Update
+- **Context refresh** — Scan, Compare, Update-context, Cascade, Record
+- **First session** — Detect, Initialize, Map, Pair, Ready
+- **Discovery (brownfield)** — Inventory, Map-dependencies, Extract-patterns, Assess, Bootstrap
+
+## Interaction level
+
+The entry point's `mode` setting controls checkpoint density:
+
+| Level | Behavior |
+|-------|----------|
+| autonomous | Execute full plan, report at completion |
+| checkpoint | Propose plan, wait for approval, report at completion (default) |
+| collaborative | Back-and-forth at each step |
+| supervised | Explain intent before every file change |
+
+## Extended conventions
+
+These conventions supplement the core set in the entry point:
+- Every code change is also a context change — update the codebase map
+- Keep intelligence layer files under 300 lines — split into index + components subdirectory when exceeded
+- SUMMARY.md entries follow audit trail format: date, plan, outcome, files, decisions, next
+
+## Safety invariants
+
+These rules are absolute — they hold regardless of profile, project type, or lifecycle stage:
+
+- **Never modify project source code** through methodology operations — only create/modify methodology files (STATE.md, .context/, PLAN.md, etc.)
+- **Never delete existing project files** — methodology integration is purely additive
+- **Never overwrite existing entry point content** — only append methodology sections
+
+## Do-not rules
+
+- Load files not in the scoping table's read-set for the current query type
+- Defer STATE.md decision recording to end of session
+- Skip cascade checks after file changes
+- Load multiple specialist .context/ files for a single query
+- Update docs/ for typo fixes or internal-only changes
+
+## File scale management
+
+When any intelligence layer file exceeds 300 lines (~3,750 tokens):
+1. Split into index file (original path) + components subdirectory
+2. Index keeps active content + navigation table
+3. Components hold archived sections grouped by semantic boundary
+4. Update .context/REGISTRY.md (if it exists) with new file entries
+
+## Audit trail format
+
+SUMMARY.md session entries follow this structure:
+```
+### {date} — {brief description}
+**Plan**: {what was planned}
+**Outcome**: {what was done}
+**Files created**: {list}
+**Files updated**: {list}
+**Decisions**: {key decisions made}
+**Next**: {what should happen next session}
+```
+
+## Docs maintenance triggers
+
+| Trigger | Update these docs/ files |
+|---------|------------------------|
+| Phase completed | docs/index.md (progress section) |
+| Architecture decision | docs/index.md (architecture section) |
+
+## Navigation registry protocol
+
+When .context/REGISTRY.md exists, update it after:
+- File split, creation, deletion, or rename
+- Topic index changes (new keywords)
+- Growth alerts (files approaching 300-line threshold)

package/templates/full/.context/REGISTRY.md

@@ -0,0 +1,75 @@
+# Navigation Registry
+
+<!-- INSTRUCTION: This file is the agent's map of all intelligence layer files.
+     It enables fast content location across split file trees without reading every file.
+
+     Populate this file when your first file split happens (any intelligence layer file
+     exceeding 300 lines). Until then, this file can remain empty — your project is small
+     enough that direct navigation works.
+
+     Three sections to maintain:
+     1. File tree — every intelligence layer file with path, lines, status, digest
+     2. Topic index — keyword → file path + section hint for fast lookup
+     3. Structural log — when files are split, deleted, or renamed
+
+     Update this file as a cascade whenever:
+     - A file is split into index + components
+     - A file is created, deleted, or renamed
+     - During context refresh (verify line counts, flag stale entries) -->
+
+## File tree
+
+<!-- INSTRUCTION: Add rows as your project grows. Status: active (normal file),
+     index (split into components), component (archived section from a split file) -->
+
+| Path | Lines | Status | Digest |
+|------|-------|--------|--------|
+| `{AGENT}.md` | — | active | Agent entry point |
+| `STATE.md` | — | active | Current position, decisions, blockers |
+| `ROADMAP.md` | — | active | Development phases |
+| `PLAN.md` | — | active | Current task |
+| `SUMMARY.md` | — | active | Session history |
+| `REQUIREMENTS.md` | — | active | What the project must achieve |
+| `.context/BASE.md` | — | active | System model, project map |
+| `.context/REGISTRY.md` | — | active | This file |
+
+### Growth alerts
+
+<!-- Files approaching the 300-line threshold. Update during context refresh. -->
+
+| Path | Lines | Threshold | Action needed |
+|------|-------|-----------|---------------|
+| — | — | 300 | No files approaching threshold yet |
+
+---
+
+## Topic index
+
+<!-- INSTRUCTION: Add entries as your project develops content worth indexing.
+     The topic index is most valuable AFTER files have been split — it lets the agent
+     find content that moved from one file to component files. -->
+
+| Topic | File | Section hint |
+|-------|------|-------------|
+| — | — | Populate when content is worth indexing |
+
+---
+
+## Structural log
+
+<!-- Records when files are split, created, deleted, or renamed.
+     Enables the agent to understand why an expected file might not exist. -->
+
+| Date | Action | Source | Target(s) | Reason |
+|------|--------|--------|-----------|--------|
+| — | — | — | — | No structural changes yet |
+
+---
+
+## Maintenance protocol
+
+**After file split**: Update file tree (new components, changed statuses). Add topic index entries. Add structural log entry.
+
+**After file creation/deletion**: Update file tree. Update topic index. Add structural log entry.
+
+**During context refresh**: Verify line counts. Flag growth alerts. Remove stale entries.

package/templates/full/.cursorrules

@@ -0,0 +1,128 @@
+# {Project Name} — Agent Entry Point
+
+<!-- INSTRUCTION: Replace {Project Name} and write a 1-2 sentence project description below -->
+{Describe what your project does, its architecture, and key technologies.}
+
+## On every query
+
+1. This file is auto-loaded — read it first
+2. Read `STATE.md` for current position, decisions, blockers
+3. Check `PROJECT-PROFILE.md` for lifecycle stage and active extensions
+4. Scope based on query type (see table below)
+
+## Scoping rules
+
+| Query type | Read before acting | Update after acting |
+|------------|-------------------|-------------------|
+| **Planning / roadmap** | REQUIREMENTS.md, ROADMAP.md | STATE.md, PLAN.md |
+| **Context refresh** | .context/ (all), project structure | .context/, this file (if scoping rules affected) |
+| **Project discovery** | Project structure, package files, key source files | .context/BASE.md, .context/ specialists, STATE.md |
+| **{your-domain-type}** | .context/BASE.md + .context/{SPECIALIST}.md | {affected working files} |
+| **Structural navigation** | .context/REGISTRY.md | .context/REGISTRY.md (if structure changed) |
+| **Methodology guidance** | .context/METHODOLOGY.md | -- |
+| **Phase completion** | SUMMARY.md | SUMMARY.md, STATE.md, ROADMAP.md |
+| **Backlog / ideas** | todos/backlog.md | todos/backlog.md |
+
+<!-- INSTRUCTION: Replace the {your-domain-type} row with project-specific query types.
+     Each should pair .context/BASE.md with one specialist. Add as many rows as needed. -->
+
+## Dependency cascade
+
+When a file changes, check this table and update dependent files in the same response.
+
+| When this changes | Also update |
+|------------------|-------------|
+| Phase completion | SUMMARY.md (add entry), STATE.md (update position), ROADMAP.md (mark done) |
+| Requirements change | REQUIREMENTS.md, ROADMAP.md, PLAN.md (if current task affected) |
+| New decision made | STATE.md (decisions table — record immediately, never defer) |
+| Open question resolved | STATE.md (mark resolved with resolution text, don't delete) |
+| Project structure | .context/BASE.md (codebase map), this file (if new query types needed) |
+| Intelligence layer file exceeds 300 lines | Restructure into index + components subdirectory (keep active content, archive completed sections) |
+| File split, created, deleted, or renamed | .context/REGISTRY.md (file tree, topic index, structural log) |
+| New domain area | .context/BASE.md, consider new .context/ specialist, this file (if new scoping row) |
+| Lifecycle stage change | PROJECT-PROFILE.md (update stage + date), STATE.md (record decision) |
+| Session close | SESSION-LOG.md (append micro-entry — workflow, features, cascades, friction, findings) |
+
+<!-- INSTRUCTION: Add project-specific cascade rules below the universal ones above. -->
+
+## Docs maintenance
+
+<!-- INSTRUCTION: This table tells the agent when to update human-facing docs.
+     Add rows as your docs/ structure grows. -->
+
+| Trigger | Update these docs/ files |
+|---------|------------------------|
+| Phase completed | docs/index.md (progress section) |
+| Architecture decision | docs/index.md (architecture section) |
+| {structural-change} | {specific docs/ files} |
+
+## Workflow
+
+Select based on query type:
+- **General task** — Review, Plan, Implement, Document, Update
+- **Code change** — Review, Plan, Implement, Context-sync, Update
+- **Context refresh** — Scan, Compare, Update-context, Cascade, Record
+- **First session** — Detect, Initialize, Map, Pair, Ready
+- **Discovery (brownfield)** — Inventory, Map-dependencies, Extract-patterns, Assess, Bootstrap
+
+## Interaction level
+
+mode: checkpoint
+<!-- autonomous | checkpoint | collaborative | supervised -->
+<!-- checkpoint: propose plan, wait for approval, report at completion (default) -->
+
+## Model tier
+
+tier: full
+<!-- lite | standard | full -->
+<!-- lite: minimal rules, STATE.md only, 2 cascade rules — for Haiku or simple projects -->
+<!-- standard: core rules + context pairing, overflow to .context/METHODOLOGY.md — for Sonnet (default) -->
+<!-- full: all rules in entry point, all intelligence layer files — for Opus or complex projects -->
+
+## Method version
+
+method_version: 1.5
+<!-- Tracks which methodology version generated this entry point -->
+<!-- Use `agent-method status` to compare against latest -->
+
+## CLI tools (optional)
+
+Available via `npx agent-method` (zero-install) or `pip install agent-method-tools`:
+
+| When you want to... | Run |
+|---------------------|-----|
+| Validate this entry point | `agent-method check` |
+| See what type of project this is | `agent-method scan` |
+| Test how a query routes | `agent-method route "your question"` |
+| Extract a refinement report | `agent-method refine` |
+| Check methodology version | `agent-method status` |
+| Update methodology files | `agent-method upgrade` |
+| See what an entry point should contain | `agent-method init code` / `context` / `data` / `mix` |
+
+<!-- INSTRUCTION: The agent can suggest these commands when the user asks about validation,
+     project setup, or methodology updates. All commands auto-detect project type and find
+     entry points automatically. Add --json for machine-readable output. -->
+
+## Conventions
+
+- Record decisions in STATE.md in the SAME response as the work — never defer
+- Load .context/BASE.md + one specialist per query — never all context files
+- After every file change, check the cascade table — deferred cascades don't happen
+- Every code change is also a context change — update the codebase map
+- Surface uncertainty as open questions in STATE.md — never guess silently
+- Keep intelligence layer files under 300 lines — split into index + components subdirectory when exceeded
+- Propose plans and wait for approval — the human controls direction
+- SUMMARY.md entries follow audit trail format: date, plan, outcome, files, decisions, next
+- At session close, append a micro-entry to SESSION-LOG.md — never skip, never read previous entries during normal work
+
+## Do not
+
+- Modify project source code, tests, or pre-existing documentation through methodology operations — only create/modify methodology files (STATE.md, .context/, PLAN.md, etc.)
+- Delete existing project files during brownfield integration — methodology is additive only
+- Load files not in the scoping table's read-set for the current query type
+- Defer STATE.md decision recording to end of session
+- Skip cascade checks after file changes
+- Load multiple specialist .context/ files for a single query
+- Update docs/ for typo fixes or internal-only changes
+
+<!-- INSTRUCTION: Add project-specific "do not" rules as you discover common mistakes -->

package/templates/full/AGENT.md

@@ -0,0 +1,128 @@
+# {Project Name} — Agent Entry Point
+
+<!-- INSTRUCTION: Replace {Project Name} and write a 1-2 sentence project description below -->
+{Describe what your project does, its architecture, and key technologies.}
+
+## On every query
+
+1. This file is auto-loaded — read it first
+2. Read `STATE.md` for current position, decisions, blockers
+3. Check `PROJECT-PROFILE.md` for lifecycle stage and active extensions
+4. Scope based on query type (see table below)
+
+## Scoping rules
+
+| Query type | Read before acting | Update after acting |
+|------------|-------------------|-------------------|
+| **Planning / roadmap** | REQUIREMENTS.md, ROADMAP.md | STATE.md, PLAN.md |
+| **Context refresh** | .context/ (all), project structure | .context/, this file (if scoping rules affected) |
+| **Project discovery** | Project structure, package files, key source files | .context/BASE.md, .context/ specialists, STATE.md |
+| **{your-domain-type}** | .context/BASE.md + .context/{SPECIALIST}.md | {affected working files} |
+| **Structural navigation** | .context/REGISTRY.md | .context/REGISTRY.md (if structure changed) |
+| **Methodology guidance** | .context/METHODOLOGY.md | -- |
+| **Phase completion** | SUMMARY.md | SUMMARY.md, STATE.md, ROADMAP.md |
+| **Backlog / ideas** | todos/backlog.md | todos/backlog.md |
+
+<!-- INSTRUCTION: Replace the {your-domain-type} row with project-specific query types.
+     Each should pair .context/BASE.md with one specialist. Add as many rows as needed. -->
+
+## Dependency cascade
+
+When a file changes, check this table and update dependent files in the same response.
+
+| When this changes | Also update |
+|------------------|-------------|
+| Phase completion | SUMMARY.md (add entry), STATE.md (update position), ROADMAP.md (mark done) |
+| Requirements change | REQUIREMENTS.md, ROADMAP.md, PLAN.md (if current task affected) |
+| New decision made | STATE.md (decisions table — record immediately, never defer) |
+| Open question resolved | STATE.md (mark resolved with resolution text, don't delete) |
+| Project structure | .context/BASE.md (codebase map), this file (if new query types needed) |
+| Intelligence layer file exceeds 300 lines | Restructure into index + components subdirectory (keep active content, archive completed sections) |
+| File split, created, deleted, or renamed | .context/REGISTRY.md (file tree, topic index, structural log) |
+| New domain area | .context/BASE.md, consider new .context/ specialist, this file (if new scoping row) |
+| Lifecycle stage change | PROJECT-PROFILE.md (update stage + date), STATE.md (record decision) |
+| Session close | SESSION-LOG.md (append micro-entry — workflow, features, cascades, friction, findings) |
+
+<!-- INSTRUCTION: Add project-specific cascade rules below the universal ones above. -->
+
+## Docs maintenance
+
+<!-- INSTRUCTION: This table tells the agent when to update human-facing docs.
+     Add rows as your docs/ structure grows. -->
+
+| Trigger | Update these docs/ files |
+|---------|------------------------|
+| Phase completed | docs/index.md (progress section) |
+| Architecture decision | docs/index.md (architecture section) |
+| {structural-change} | {specific docs/ files} |
+
+## Workflow
+
+Select based on query type:
+- **General task** — Review, Plan, Implement, Document, Update
+- **Code change** — Review, Plan, Implement, Context-sync, Update
+- **Context refresh** — Scan, Compare, Update-context, Cascade, Record
+- **First session** — Detect, Initialize, Map, Pair, Ready
+- **Discovery (brownfield)** — Inventory, Map-dependencies, Extract-patterns, Assess, Bootstrap
+
+## Interaction level
+
+mode: checkpoint
+<!-- autonomous | checkpoint | collaborative | supervised -->
+<!-- checkpoint: propose plan, wait for approval, report at completion (default) -->
+
+## Model tier
+
+tier: full
+<!-- lite | standard | full -->
+<!-- lite: minimal rules, STATE.md only, 2 cascade rules — for Haiku or simple projects -->
+<!-- standard: core rules + context pairing, overflow to .context/METHODOLOGY.md — for Sonnet (default) -->
+<!-- full: all rules in entry point, all intelligence layer files — for Opus or complex projects -->
+
+## Method version
+
+method_version: 1.5
+<!-- Tracks which methodology version generated this entry point -->
+<!-- Use `agent-method status` to compare against latest -->
+
+## CLI tools (optional)
+
+Available via `npx agent-method` (zero-install) or `pip install agent-method-tools`:
+
+| When you want to... | Run |
+|---------------------|-----|
+| Validate this entry point | `agent-method check` |
+| See what type of project this is | `agent-method scan` |
+| Test how a query routes | `agent-method route "your question"` |
+| Extract a refinement report | `agent-method refine` |
+| Check methodology version | `agent-method status` |
+| Update methodology files | `agent-method upgrade` |
+| See what an entry point should contain | `agent-method init code` / `context` / `data` / `mix` |
+
+<!-- INSTRUCTION: The agent can suggest these commands when the user asks about validation,
+     project setup, or methodology updates. All commands auto-detect project type and find
+     entry points automatically. Add --json for machine-readable output. -->
+
+## Conventions
+
+- Record decisions in STATE.md in the SAME response as the work — never defer
+- Load .context/BASE.md + one specialist per query — never all context files
+- After every file change, check the cascade table — deferred cascades don't happen
+- Every code change is also a context change — update the codebase map
+- Surface uncertainty as open questions in STATE.md — never guess silently
+- Keep intelligence layer files under 300 lines — split into index + components subdirectory when exceeded
+- Propose plans and wait for approval — the human controls direction
+- SUMMARY.md entries follow audit trail format: date, plan, outcome, files, decisions, next
+- At session close, append a micro-entry to SESSION-LOG.md — never skip, never read previous entries during normal work
+
+## Do not
+
+- Modify project source code, tests, or pre-existing documentation through methodology operations — only create/modify methodology files (STATE.md, .context/, PLAN.md, etc.)
+- Delete existing project files during brownfield integration — methodology is additive only
+- Load files not in the scoping table's read-set for the current query type
+- Defer STATE.md decision recording to end of session
+- Skip cascade checks after file changes
+- Load multiple specialist .context/ files for a single query
+- Update docs/ for typo fixes or internal-only changes
+
+<!-- INSTRUCTION: Add project-specific "do not" rules as you discover common mistakes -->

package/templates/full/CLAUDE.md

@@ -0,0 +1,128 @@
+# {Project Name} — Agent Entry Point
+
+<!-- INSTRUCTION: Replace {Project Name} and write a 1-2 sentence project description below -->
+{Describe what your project does, its architecture, and key technologies.}
+
+## On every query
+
+1. This file is auto-loaded — read it first
+2. Read `STATE.md` for current position, decisions, blockers
+3. Check `PROJECT-PROFILE.md` for lifecycle stage and active extensions
+4. Scope based on query type (see table below)
+
+## Scoping rules
+
+| Query type | Read before acting | Update after acting |
+|------------|-------------------|-------------------|
+| **Planning / roadmap** | REQUIREMENTS.md, ROADMAP.md | STATE.md, PLAN.md |
+| **Context refresh** | .context/ (all), project structure | .context/, this file (if scoping rules affected) |
+| **Project discovery** | Project structure, package files, key source files | .context/BASE.md, .context/ specialists, STATE.md |
+| **{your-domain-type}** | .context/BASE.md + .context/{SPECIALIST}.md | {affected working files} |
+| **Structural navigation** | .context/REGISTRY.md | .context/REGISTRY.md (if structure changed) |
+| **Methodology guidance** | .context/METHODOLOGY.md | -- |
+| **Phase completion** | SUMMARY.md | SUMMARY.md, STATE.md, ROADMAP.md |
+| **Backlog / ideas** | todos/backlog.md | todos/backlog.md |
+
+<!-- INSTRUCTION: Replace the {your-domain-type} row with project-specific query types.
+     Each should pair .context/BASE.md with one specialist. Add as many rows as needed. -->
+
+## Dependency cascade
+
+When a file changes, check this table and update dependent files in the same response.
+
+| When this changes | Also update |
+|------------------|-------------|
+| Phase completion | SUMMARY.md (add entry), STATE.md (update position), ROADMAP.md (mark done) |
+| Requirements change | REQUIREMENTS.md, ROADMAP.md, PLAN.md (if current task affected) |
+| New decision made | STATE.md (decisions table — record immediately, never defer) |
+| Open question resolved | STATE.md (mark resolved with resolution text, don't delete) |
+| Project structure | .context/BASE.md (codebase map), this file (if new query types needed) |
+| Intelligence layer file exceeds 300 lines | Restructure into index + components subdirectory (keep active content, archive completed sections) |
+| File split, created, deleted, or renamed | .context/REGISTRY.md (file tree, topic index, structural log) |
+| New domain area | .context/BASE.md, consider new .context/ specialist, this file (if new scoping row) |
+| Lifecycle stage change | PROJECT-PROFILE.md (update stage + date), STATE.md (record decision) |
+| Session close | SESSION-LOG.md (append micro-entry — workflow, features, cascades, friction, findings) |
+
+<!-- INSTRUCTION: Add project-specific cascade rules below the universal ones above. -->
+
+## Docs maintenance
+
+<!-- INSTRUCTION: This table tells the agent when to update human-facing docs.
+     Add rows as your docs/ structure grows. -->
+
+| Trigger | Update these docs/ files |
+|---------|------------------------|
+| Phase completed | docs/index.md (progress section) |
+| Architecture decision | docs/index.md (architecture section) |
+| {structural-change} | {specific docs/ files} |
+
+## Workflow
+
+Select based on query type:
+- **General task** — Review, Plan, Implement, Document, Update
+- **Code change** — Review, Plan, Implement, Context-sync, Update
+- **Context refresh** — Scan, Compare, Update-context, Cascade, Record
+- **First session** — Detect, Initialize, Map, Pair, Ready
+- **Discovery (brownfield)** — Inventory, Map-dependencies, Extract-patterns, Assess, Bootstrap
+
+## Interaction level
+
+mode: checkpoint
+<!-- autonomous | checkpoint | collaborative | supervised -->
+<!-- checkpoint: propose plan, wait for approval, report at completion (default) -->
+
+## Model tier
+
+tier: full
+<!-- lite | standard | full -->
+<!-- lite: minimal rules, STATE.md only, 2 cascade rules — for Haiku or simple projects -->
+<!-- standard: core rules + context pairing, overflow to .context/METHODOLOGY.md — for Sonnet (default) -->
+<!-- full: all rules in entry point, all intelligence layer files — for Opus or complex projects -->
+
+## Method version
+
+method_version: 1.5
+<!-- Tracks which methodology version generated this entry point -->
+<!-- Use `agent-method status` to compare against latest -->
+
+## CLI tools (optional)
+
+Available via `npx agent-method` (zero-install) or `pip install agent-method-tools`:
+
+| When you want to... | Run |
+|---------------------|-----|
+| Validate this entry point | `agent-method check` |
+| See what type of project this is | `agent-method scan` |
+| Test how a query routes | `agent-method route "your question"` |
+| Extract a refinement report | `agent-method refine` |
+| Check methodology version | `agent-method status` |
+| Update methodology files | `agent-method upgrade` |
+| See what an entry point should contain | `agent-method init code` / `context` / `data` / `mix` |
+
+<!-- INSTRUCTION: The agent can suggest these commands when the user asks about validation,
+     project setup, or methodology updates. All commands auto-detect project type and find
+     entry points automatically. Add --json for machine-readable output. -->
+
+## Conventions
+
+- Record decisions in STATE.md in the SAME response as the work — never defer
+- Load .context/BASE.md + one specialist per query — never all context files
+- After every file change, check the cascade table — deferred cascades don't happen
+- Every code change is also a context change — update the codebase map
+- Surface uncertainty as open questions in STATE.md — never guess silently
+- Keep intelligence layer files under 300 lines — split into index + components subdirectory when exceeded
+- Propose plans and wait for approval — the human controls direction
+- SUMMARY.md entries follow audit trail format: date, plan, outcome, files, decisions, next
+- At session close, append a micro-entry to SESSION-LOG.md — never skip, never read previous entries during normal work
+
+## Do not
+
+- Modify project source code, tests, or pre-existing documentation through methodology operations — only create/modify methodology files (STATE.md, .context/, PLAN.md, etc.)
+- Delete existing project files during brownfield integration — methodology is additive only
+- Load files not in the scoping table's read-set for the current query type
+- Defer STATE.md decision recording to end of session
+- Skip cascade checks after file changes
+- Load multiple specialist .context/ files for a single query
+- Update docs/ for typo fixes or internal-only changes
+
+<!-- INSTRUCTION: Add project-specific "do not" rules as you discover common mistakes -->

package/templates/full/PLAN.md

@@ -0,0 +1,67 @@
+# Current Plan
+
+<!-- INSTRUCTION: This file contains ONE task at a time. Replace the entire
+     contents when starting a new task — never accumulate multiple plans.
+     The agent proposes the plan and waits for human approval before executing. -->
+
+## {Task name}
+
+### Objective
+
+{What this task achieves. One clear sentence.}
+
+### Prerequisites
+
+<!-- INSTRUCTION: What must be true before starting this task? -->
+
+- {Prior phase or task complete}
+- {Required files or context available}
+
+### Dependencies
+
+<!-- INSTRUCTION: What depends on this task? What does this task block? -->
+
+- {Phase/task that depends on this completing}
+
+---
+
+### Step 1: {Step name}
+
+**Objective**: {What this step achieves}
+
+**Read**: {Files to read before this step}
+**Produce**: {Files created or modified by this step}
+
+**Substeps**:
+- a. {First substep}
+- b. {Second substep}
+
+**Verify**: {How to confirm this step is complete and correct}
+
+---
+
+### Step 2: {Step name}
+
+**Objective**: {What this step achieves}
+
+**Read**: {Files to read}
+**Produce**: {Files created or modified}
+
+**Verify**: {Verification criteria}
+
+---
+
+<!-- INSTRUCTION: Add more steps as needed. Each step should have:
+     - Clear objective
+     - Read/produce specs (what files are involved)
+     - Substeps (if complex)
+     - Verification criteria (how to confirm it's done right) -->
+
+### Completion criteria
+
+{Task name} is done when:
+1. {Criterion 1 — specific and measurable}
+2. {Criterion 2}
+3. {Criterion 3}
+
+**Next after {task name}**: {What comes next}

package/templates/full/PROJECT-PROFILE.md

@@ -0,0 +1,61 @@
+# Project Profile
+
+<!-- INSTRUCTION: This file is maintained by the agent. It tracks your project's
+     type, lifecycle stage, and active extensions. The agent reads this to adjust
+     feature priorities and workflow selection. You can also update it manually
+     when your project's situation changes.
+
+     Fill in the initial values during setup. The agent updates lifecycle stage
+     and maturity as the project evolves. -->
+
+## Project identity
+
+- **Types**: [{project-type}]
+- **Extensions**: [{extensions-applied}]
+
+<!-- INSTRUCTION: Project types: code, data, analytical, mixed, general.
+     Extensions: code-project, data-exploration, analytical-system, or none. -->
+
+## Lifecycle
+
+- **Stage**: {stage}
+- **Maturity**: {maturity}
+- **Last transition**: {date} ({from} -> {to})
+
+<!-- INSTRUCTION: Lifecycle stages:
+     - discovery: Understanding an existing project (brownfield entry)
+     - design: Defining architecture and structure (greenfield start)
+     - development: Building and iterating (active implementation)
+     - evolution: Maintaining and extending (stable baseline)
+
+     Maturity levels: new, early, established, legacy.
+     The agent suggests transitions; you decide when to move. -->
+
+## Extension stack
+
+| Extension | Applied | Source |
+|-----------|---------|--------|
+| code-project | {yes/no} | {setup.sh / manual} |
+| data-exploration | {yes/no} | {setup.sh / manual} |
+| analytical-system | {yes/no} | {setup.sh / manual} |
+
+<!-- INSTRUCTION: Track which extensions are active. Extensions can be added
+     mid-project without re-running setup.sh — merge the extension file
+     into your entry point manually and update this table. -->
+
+## Discovery log
+
+<!-- INSTRUCTION: When the agent runs WF-08 (discovery workflow), key findings
+     are recorded here for quick reference. Only used during Discovery stage.
+     Can be deleted once the project moves to Development or Evolution. -->
+
+| Date | Finding | Severity | Action taken |
+|------|---------|----------|-------------|
+
+## Context evolution history
+
+<!-- INSTRUCTION: Track lifecycle transitions and extension changes over time.
+     Helps the agent understand how the project has evolved. -->
+
+| Date | Change | Rationale |
+|------|--------|-----------|