agent-method 1.5.3 → 1.5.6

package/templates/full/Reviews/project.md

@@ -0,0 +1,41 @@
+# Project Review
+
+<!-- AGENT: Synthesize from PROJECT.md and PROJECT-PROFILE.md. Track how the project
+     vision, scope, and principles evolve over time. Update after significant scope
+     changes, audience shifts, or principle revisions.
+
+     Source: PROJECT.md, PROJECT-PROFILE.md
+     Parent: Reviews/INDEX.md (update "At a glance" row when this changes) -->
+
+## Project identity
+
+| Field | Current value |
+|-------|--------------|
+| Name | {from PROJECT.md} |
+| Type | {from PROJECT-PROFILE.md} |
+| Lifecycle stage | {from PROJECT-PROFILE.md} |
+| Active extensions | {from PROJECT-PROFILE.md} |
+
+## Scope evolution
+
+<!-- AGENT: Track how project scope has changed. Has it grown, contracted, or shifted? -->
+
+| Date | Change | Type | Impact |
+|------|--------|------|--------|
+<!-- {date} | {what changed} | {expansion / contraction / pivot} | {brief impact} -->
+
+## Principle adherence
+
+<!-- AGENT: Review PROJECT.md principles. Are they being followed in practice? -->
+
+| Principle | Status | Evidence |
+|-----------|--------|----------|
+<!-- {principle from PROJECT.md} | {followed / at risk / violated} | {brief evidence} -->
+
+## Audience alignment
+
+<!-- AGENT: Are we building for the right audience? Any shifts in who uses this? -->
+
+## Technology health
+
+<!-- AGENT: Are technology choices from PROJECT.md still appropriate? Any concerns? -->

package/templates/full/Reviews/requirements.md

@@ -0,0 +1,42 @@
+# Requirements Review
+
+<!-- AGENT: Synthesize from REQUIREMENTS.md. Track requirements coverage, completion
+     status, and traceability to roadmap phases. Update after requirement changes
+     or phase completions that satisfy requirements.
+
+     Source: REQUIREMENTS.md, ROADMAP.md (phase mapping)
+     Parent: Reviews/INDEX.md (update "At a glance" row when this changes) -->
+
+## Coverage summary
+
+| Status | Count | Percentage |
+|--------|-------|------------|
+| Done | {N} | {%} |
+| In progress | {N} | {%} |
+| Pending | {N} | {%} |
+| Deferred | {N} | {%} |
+| **Total** | {N} | 100% |
+
+## Traceability matrix
+
+<!-- AGENT: Map requirements to roadmap phases. Which phases satisfy which requirements? -->
+
+| Requirement | Description | Phase | Status |
+|-------------|-------------|-------|--------|
+<!-- {R-ID} | {brief description} | {phase} | {done / in progress / pending} -->
+
+## Coverage gaps
+
+<!-- AGENT: Are there requirements with no clear path to completion? -->
+
+| Requirement | Gap description | Risk |
+|-------------|----------------|------|
+<!-- Requirements not yet mapped to a phase or at risk of being unmet -->
+
+## Change history
+
+<!-- AGENT: Track when requirements are added, modified, or removed. -->
+
+| Date | Requirement | Change | Rationale |
+|------|-------------|--------|-----------|
+<!-- {date} | {R-ID} | {added / modified / removed} | {why} -->

package/templates/full/Reviews/roadmap.md

@@ -0,0 +1,41 @@
+# Roadmap Review
+
+<!-- AGENT: Synthesize from ROADMAP.md. This is the high-level view of phase progress,
+     milestones, and project trajectory. Update after phase completions or milestone changes.
+
+     Source: ROADMAP.md
+     Parent: Reviews/INDEX.md (update "At a glance" row when this changes) -->
+
+## Phase progress
+
+| Phase | Name | Status | Completion | Gate |
+|-------|------|--------|------------|------|
+<!-- Populate from ROADMAP.md. Show all phases with current status. -->
+
+## Milestone timeline
+
+<!-- AGENT: Track when phases were completed or are expected to complete. -->
+
+| Milestone | Target | Actual | Delta |
+|-----------|--------|--------|-------|
+<!-- {phase/milestone name} | {expected date} | {actual date} | {on time / early / late} -->
+
+## Velocity analysis
+
+<!-- AGENT: Observe patterns in phase completion speed. -->
+
+- **Average phase duration**: {estimate based on completed phases}
+- **Trend**: {accelerating / steady / slowing}
+- **Bottleneck phases**: {any phases that took significantly longer}
+
+## Upcoming work
+
+<!-- AGENT: What's next on the roadmap? Any dependencies or risks? -->
+
+### Next phase
+
+{Brief description of what's coming and what it depends on.}
+
+### Risks to timeline
+
+<!-- Known risks that could delay upcoming phases. -->

package/templates/full/Reviews/state.md

@@ -0,0 +1,56 @@
+# State Review
+
+<!-- AGENT: Synthesize from STATE.md. Analyze decision patterns, blocker trends,
+     and open question resolution. This is the analytical view of project state —
+     STATE.md is the raw data, this file is the analysis.
+     Update after significant state changes (new blockers, major decisions).
+
+     Source: STATE.md
+     Parent: Reviews/INDEX.md (update "At a glance" row when this changes) -->
+
+## Decision analysis
+
+### Summary
+
+- **Total decisions**: {count}
+- **Decisions this phase**: {count}
+- **Most common decision type**: {technical / architectural / process / scope}
+
+### Recent decisions (last 10)
+
+| Date | Decision | Category |
+|------|----------|----------|
+<!-- Last 10 from STATE.md decisions table -->
+
+### Decision frequency
+
+<!-- AGENT: How often are decisions being made? Any patterns in timing? -->
+
+## Blocker analysis
+
+### Active blockers
+
+| Blocker | Since | Duration | Severity | Resolution path |
+|---------|-------|----------|----------|----------------|
+<!-- Active blockers from STATE.md with aging analysis -->
+
+### Resolved blockers
+
+- **Total resolved**: {count}
+- **Average resolution time**: {estimate}
+- **Most common blocker type**: {external dependency / technical / decision needed}
+
+## Open question analysis
+
+### Active questions
+
+| Question | Since | Duration | Priority |
+|----------|-------|----------|----------|
+<!-- Active open questions with aging -->
+
+### Resolution rate
+
+- **Total questions raised**: {count}
+- **Resolved**: {count} ({%})
+- **Still open**: {count}
+- **Average resolution time**: {estimate}

package/templates/full/SESSION-LOG.md

@@ -40,6 +40,27 @@ Append-only session observation log for case study data collection. Each session
 - **high**: Entry point + STATE.md + specialist context + multiple project files
 - **very high**: Extensive project context, multiple specialists, cross-file analysis
 
+**User response** (agent-observed — how did the user respond to the result?):
+- **accepted**: User proceeded to next step without changes
+- **edited**: User manually modified the agent's output
+- **revised**: User asked agent to redo or revise the result
+- **rejected**: User said no or declined the result entirely
+- **redirected**: User changed approach or gave new instructions
+
+**Refinement magnitude** (for medium/high effort only — how much changed from first attempt to final?):
+- **none**: Accepted as-is, 0% changed
+- **minor**: Small fixes — typos, naming, formatting (<10% changed)
+- **moderate**: Logic or structural changes, added/removed sections (10–50% changed)
+- **major**: Significant rework of approach or content (50–80% changed)
+- **rework**: Mostly rewritten, original approach abandoned (>80% changed)
+
+**Delta categories** (what kinds of changes were needed — select all that apply):
+- **accuracy**: Factual errors or incorrect implementation
+- **completeness**: Missing parts, incomplete coverage
+- **approach**: Wrong method or strategy
+- **scope**: Over-scoped or under-scoped
+- **style**: Formatting, naming, conventions
+
 ## Observation checklist
 
 At session close (or high-effort task completion), reflect on these before writing the entry:
@@ -54,6 +75,10 @@ At session close (or high-effort task completion), reflect on these before writi
 9. How ambiguous was the user's request? (low / medium / high)
 10. How much project context was loaded? (very low / low / medium / high / very high)
 11. Approximate token usage and time spent?
+12. How did the user respond to the result? (accepted / edited / revised / rejected / redirected)
+13. For medium/high effort: how many revision cycles before acceptance?
+14. What magnitude of change between first attempt and final result? (none / minor / moderate / major / rework)
+15. What categories of refinement were needed? (accuracy / completeness / approach / scope / style)
 
 ## Entry format
 
@@ -66,6 +91,10 @@ Tokens: ~{N}k | Time: ~{N} min
 Queries: {query types encountered}
 Features: {feature IDs activated}
 Cascades: {triggered}/{expected} | Decisions: {count}
+Response: {accepted / edited / revised / rejected / redirected}
+Revisions: {0 | count of revision cycles} | Magnitude: {none / minor / moderate / major / rework}
+Delta: {n/a | categories: accuracy, completeness, approach, scope, style} | Survival: ~{N}%
+Delta notes: {n/a | brief description of what changed between first attempt and final}
 Friction: {none | brief description}
 Finding: {none | observation with methodology implication}
 -->

package/templates/full/SUMMARY.md

@@ -1,12 +1,15 @@
 # Summary
 
-<!-- INSTRUCTION: This is the execution history — the audit trail.
-     Append a new entry at the END of this file after each task or session.
-     Never edit previous entries. The "Next" field bridges to the following session. -->
+<!-- AGENT: This file is the session audit trail — a chronological record of work done.
+     The management digest has moved to Management/DIGEST.md.
+     Append an entry after each session or significant task using the format below.
+     Never edit previous entries. -->
+
+## Session audit trail
 
 <!-- INSTRUCTION: Use this format for each entry:
 
-## {Date} — {Brief title}
+### {Date} — {Brief title}
 
 **Plan**: {What was planned for this session}
 **Outcome**: {What was actually accomplished}

package/templates/full/agentWorkflows/INDEX.md

@@ -0,0 +1,42 @@
+# Agent Workflows
+
+<!-- AGENT: This file is the overview of agent workflow performance.
+     It links to detailed analysis files for deep dives.
+     Update the summary table after high-effort sessions.
+
+     Source: SESSION-LOG.md entries, agent self-observation during sessions.
+     Detail lives in the linked analysis files — keep this file lean. -->
+
+## Workflow summary
+
+| Workflow | Times used | Last used | Typical effort | Analysis |
+|----------|-----------|-----------|---------------|----------|
+<!-- Populate from SESSION-LOG.md workflow field -->
+| {WF-XX} | {N} | {date} | {low/medium/high} | [sessions.md](sessions.md) |
+
+## Quick stats
+
+<!-- AGENT: Populate from SESSION-LOG.md. Update after each high-effort session. -->
+
+- **Total sessions**: {count}
+- **Acceptance rate**: {%} (accepted on first attempt)
+- **Average effort**: {low/medium/high}
+- **Most common workflow**: {WF-XX}
+- **Cascade compliance**: {triggered/expected} ({%})
+
+## Analysis files
+
+| File | What it covers | Last updated |
+|------|---------------|-------------|
+| [sessions.md](sessions.md) | Session-by-session analysis, effort distribution, query patterns | {date} |
+| [patterns.md](patterns.md) | Extracted behavioral patterns, what works vs. friction | {date} |
+| [observations.md](observations.md) | Case study observations, methodology findings | {date} |
+
+## Recent findings
+
+<!-- AGENT: Keep the 5 most recent significant findings here.
+     Full findings history in observations.md. -->
+
+| Date | Finding | Severity | Action taken |
+|------|---------|----------|-------------|
+<!-- Last 5 significant findings -->

package/templates/full/agentWorkflows/observations.md

@@ -0,0 +1,65 @@
+# Case Study Observations
+
+<!-- AGENT: Record methodology observations — findings from running the methodology
+     on this project that have implications for methodology improvement. These feed
+     into refinement reports (see case-studies/refinement-report-template.md).
+     Update whenever a significant finding emerges during a session.
+
+     Source: SESSION-LOG.md (finding field), agent self-observation
+     Parent: agentWorkflows/INDEX.md (update recent findings when this changes) -->
+
+## Observation log
+
+<!-- AGENT: Append new observations. Never edit or delete previous entries. -->
+
+| # | Date | Observation | Category | Severity | Action |
+|---|------|-------------|----------|----------|--------|
+<!-- {N} | {date} | {what was observed} | {see categories below} | {critical/major/minor/enhancement} | {what was done or proposed} -->
+
+## Categories
+
+Observations are classified into these categories (matching the refinement report template):
+
+| Category | Code | Description |
+|----------|------|-------------|
+| Context quality | CQ | How well .context/ files serve the project |
+| Decision preservation | DP | Whether decisions are captured accurately and timely |
+| Scope discipline | SD | Whether scoping rules are followed correctly |
+| Cascade coverage | CC | Whether cascade rules trigger correctly and completely |
+| Audit completeness | AC | Whether session records are complete and useful |
+| Bootstrap speed | BS | How quickly new projects get productive |
+| Lifecycle fit | LF | Whether lifecycle stage affects methodology effectiveness |
+| Model adequacy | MA | Whether the model tier matches task complexity |
+
+## Severity guide
+
+| Severity | Definition | Response |
+|----------|-----------|----------|
+| **Critical** | Methodology fails to function correctly | Immediate fix needed |
+| **Major** | Methodology works but produces poor results | Fix before next case study |
+| **Minor** | Methodology works but could be smoother | Fix when convenient |
+| **Enhancement** | Opportunity to improve, not a problem | Add to backlog |
+
+## Summary by category
+
+<!-- AGENT: Aggregate observations by category. Update as observations accumulate. -->
+
+| Category | Critical | Major | Minor | Enhancement | Total |
+|----------|----------|-------|-------|-------------|-------|
+| Context quality | {N} | {N} | {N} | {N} | {N} |
+| Decision preservation | {N} | {N} | {N} | {N} | {N} |
+| Scope discipline | {N} | {N} | {N} | {N} | {N} |
+| Cascade coverage | {N} | {N} | {N} | {N} | {N} |
+| Audit completeness | {N} | {N} | {N} | {N} | {N} |
+| Bootstrap speed | {N} | {N} | {N} | {N} | {N} |
+| Lifecycle fit | {N} | {N} | {N} | {N} | {N} |
+| Model adequacy | {N} | {N} | {N} | {N} | {N} |
+
+## Refinement candidates
+
+<!-- AGENT: Observations promoted to refinement report candidates. These are findings
+     significant enough to warrant methodology changes. -->
+
+| Observation # | Category | Proposed change | Status |
+|--------------|----------|----------------|--------|
+<!-- {N} | {code} | {what should change in the methodology} | {proposed / accepted / implemented / rejected} -->

package/templates/full/agentWorkflows/patterns.md

@@ -0,0 +1,68 @@
+# Behavioral Patterns
+
+<!-- AGENT: Extract recurring patterns from SESSION-LOG.md and session experience.
+     Focus on what works, what doesn't, and what could be improved.
+     Update when new patterns emerge or existing patterns are confirmed/disproven.
+
+     Source: SESSION-LOG.md (friction and finding fields), agent self-observation
+     Parent: agentWorkflows/INDEX.md (update recent findings when this changes) -->
+
+## Effective patterns
+
+<!-- AGENT: Patterns that consistently lead to good outcomes (accepted results,
+     efficient execution, accurate context loading). -->
+
+### Context loading
+
+<!-- What context loading strategies work best for this project? -->
+
+### Cascade compliance
+
+<!-- How well are cascade rules followed? Any patterns in misses? -->
+
+- **Cascade compliance rate**: {triggered/expected} ({%})
+- **Common cascade misses**: {which cascade rules get missed most?}
+
+### Decision recording
+
+<!-- Is decision recording happening in the same response? Any delays? -->
+
+### Query routing
+
+<!-- Are queries routing to the correct workflow? Any misclassifications? -->
+
+## Friction points
+
+<!-- AGENT: Patterns that consistently cause problems — methodology rules that
+     are hard to follow, scoping that doesn't fit, cascades that are unclear. -->
+
+### Recurring friction
+
+| Pattern | Frequency | Impact | Potential fix |
+|---------|-----------|--------|--------------|
+<!-- {description} | {how often} | {low/medium/high} | {what might help} -->
+
+### Methodology gaps
+
+<!-- Are there query types or situations not covered by current scoping rules? -->
+
+### Scale issues
+
+<!-- Are any files consistently approaching the 300-line threshold? -->
+
+## Anti-patterns
+
+<!-- AGENT: Things that should be avoided — approaches that lead to rejections,
+     context loading that wastes tokens, cascades that produce low-value updates. -->
+
+| Anti-pattern | Observed | Consequence | Prevention |
+|-------------|----------|-------------|------------|
+<!-- {description} | {when it happened} | {what went wrong} | {how to avoid} -->
+
+## Improvement suggestions
+
+<!-- AGENT: Based on patterns observed, what methodology changes would help? -->
+
+| Suggestion | Evidence | Priority | Status |
+|-----------|----------|----------|--------|
+<!-- {what to change} | {based on what pattern} | {low/medium/high} | {proposed / implemented / rejected} -->

package/templates/full/agentWorkflows/sessions.md

@@ -0,0 +1,92 @@
+# Session Analysis
+
+<!-- AGENT: Synthesize from SESSION-LOG.md. Aggregate session metrics into
+     actionable patterns. This transforms raw session data into analysis.
+     Update after every 5 sessions or after any high-effort session.
+
+     Source: SESSION-LOG.md
+     Parent: agentWorkflows/INDEX.md (update quick stats when this changes) -->
+
+## Effort distribution
+
+| Effort level | Count | Percentage | Avg time |
+|-------------|-------|------------|----------|
+| Low | {N} | {%} | ~{N} min |
+| Medium | {N} | {%} | ~{N} min |
+| High | {N} | {%} | ~{N} min |
+
+## Query type frequency
+
+<!-- AGENT: Which query types appear most often in SESSION-LOG.md? -->
+
+| Query type | Count | Typical effort | Typical outcome |
+|-----------|-------|---------------|----------------|
+<!-- Populate from SESSION-LOG.md queries field -->
+
+## Workflow usage
+
+| Workflow | Count | Success rate | Avg effort |
+|----------|-------|-------------|------------|
+<!-- Populate from SESSION-LOG.md workflow field -->
+
+## Acceptance analysis
+
+### Overall
+
+| Response | Count | Percentage |
+|----------|-------|------------|
+| Accepted | {N} | {%} |
+| Edited | {N} | {%} |
+| Revised | {N} | {%} |
+| Rejected | {N} | {%} |
+| Redirected | {N} | {%} |
+
+### By effort level
+
+<!-- AGENT: Break down acceptance rates by effort level. Do high-effort tasks
+     get revised more often? -->
+
+| Effort | Accepted | Edited | Revised | Rejected |
+|--------|----------|--------|---------|----------|
+| Low | {%} | {%} | {%} | {%} |
+| Medium | {%} | {%} | {%} | {%} |
+| High | {%} | {%} | {%} | {%} |
+
+## Refinement patterns
+
+<!-- AGENT: For medium/high effort tasks, what refinement patterns emerge? -->
+
+### Magnitude distribution
+
+| Magnitude | Count | Percentage |
+|-----------|-------|------------|
+| None | {N} | {%} |
+| Minor | {N} | {%} |
+| Moderate | {N} | {%} |
+| Major | {N} | {%} |
+| Rework | {N} | {%} |
+
+### Delta categories
+
+<!-- Which types of changes are most common? -->
+
+| Category | Count | Notes |
+|----------|-------|-------|
+| Accuracy | {N} | {pattern notes} |
+| Completeness | {N} | {pattern notes} |
+| Approach | {N} | {pattern notes} |
+| Scope | {N} | {pattern notes} |
+| Style | {N} | {pattern notes} |
+
+## Context level patterns
+
+<!-- AGENT: How much context is typically loaded? Does more context correlate with
+     better acceptance rates? -->
+
+| Context level | Count | Acceptance rate |
+|--------------|-------|----------------|
+| Very low | {N} | {%} |
+| Low | {N} | {%} |
+| Medium | {N} | {%} |
+| High | {N} | {%} |
+| Very high | {N} | {%} |

package/templates/full/intro/README.md

@@ -0,0 +1,39 @@
+# Methodology Overview
+
+This project uses the **wwa** (Working With Agents) methodology for AI-agent-assisted development. The methodology gives your AI agent persistent memory, structured workflows, and scoped context loading across sessions.
+
+## How it works
+
+Your agent reads an entry point file (CLAUDE.md, .cursorrules, or AGENT.md) at the start of every session. That file tells the agent:
+
+- **What to read** — scoping rules match your question to the right files
+- **What to update** — cascade rules keep dependent files in sync
+- **How to work** — workflows guide the agent through structured steps
+
+Key files the agent manages:
+
+| File | Purpose |
+|------|---------|
+| STATE.md | Decisions, blockers, current position (cross-session memory) |
+| PLAN.md | Current task with verification criteria |
+| ROADMAP.md | Phase breakdown with gate criteria |
+| REQUIREMENTS.md | Scoped features with phase traceability |
+| .context/BASE.md | Core project context — architecture, codebase map |
+| .context/REGISTRY.md | Navigation map for split file trees |
+| .context/DOCS-MAP.md | Maps your project components to their documentation |
+
+## Your project's docs/
+
+The `docs/` folder is reserved for **your project's documentation** — API references, architecture guides, setup instructions, etc. It is not created at setup time. Instead, the agent proposes new docs/ files as your project grows, based on scaffolding rules in `.context/DOCS-MAP.md`.
+
+## Full documentation
+
+For the complete methodology guide, templates reference, and architecture docs:
+
+**https://github.com/anthropics/agent-method**
+
+Key pages:
+- [Quick Start](https://github.com/anthropics/agent-method/blob/main/docs/guides/quick-start.md)
+- [For Developers](https://github.com/anthropics/agent-method/blob/main/docs/guides/for-developers.md)
+- [File Roles](https://github.com/anthropics/agent-method/blob/main/docs/architecture/file-roles.md)
+- [CLI Tools](https://github.com/anthropics/agent-method/blob/main/docs/guides/for-developers/cli-tools.md)

package/templates/starter/.context/BASE.md

@@ -64,3 +64,38 @@
 | PLAN.md | Current atomic task |
 | ROADMAP.md | Phase breakdown and progress |
 | PROJECT.md | Project vision and structure |
+| SUMMARY.md | Execution history — session audit trail |
+| SESSION-LOG.md | Session metrics for case study data |
+
+## Agent onboarding
+
+<!-- AGENT: Use these questions to populate this file during the first session.
+     Ask the user each question at Stage 2 (Architecture), draft this file from
+     the answers, and show the draft at the checkpoint before writing.
+     Remove this section after the file is populated — it's scaffolding. -->
+
+### Greenfield
+
+Ask the user:
+1. What are the main components or modules? (populate "What this system is")
+2. How do they connect? Data flow, API calls, event-driven? (populate System model)
+3. What is the directory structure and what does each directory do? (populate Codebase map)
+4. What are the key external dependencies? (populate Dependencies table)
+5. What recurring task types will you work on? (populate Pairing protocol — helps create specialist context files)
+
+### Brownfield
+
+<!-- AGENT: For brownfield projects, auto-populate most of this from the Stage 1 scan.
+     Build the codebase map from what you found. Ask targeted questions only for gaps. -->
+
+Pre-fill from scan:
+- **What this system is**: infer from README + source structure + config files
+- **System model**: infer from imports, API routes, database connections, event patterns
+- **Codebase map**: build from directory listing + language detection + framework patterns
+- **Dependencies**: extract from lockfiles and config
+
+Ask the user only for gaps:
+1. I found [components]. Are there connections between them I'm missing? (validate System model)
+2. Which parts of the codebase get the most changes? (helps prioritize Pairing protocol)
+3. Are there historical patterns or conventions not visible in code? (e.g., "we always use X for Y")
+4. What types of work will you primarily do? (populate Pairing protocol for specialist files)