@soleri/forge 9.0.0 → 9.0.1

package/dist/skills/verification-before-completion.md

@@ -1,182 +0,0 @@
----
-name: verification-before-completion
-description: Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
----
-
-<!-- Adapted from superpowers (MIT License) -->
-
-# Verification Before Completion
-
-## Overview
-
-Claiming work is complete without verification is dishonesty, not efficiency.
-
-**Core principle:** Evidence before claims, always.
-
-**Violating the letter of this rule is violating the spirit of this rule.**
-
-## The Iron Law
-
-```
-NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
-```
-
-If you haven't run the verification command in this message, you cannot claim it passes.
-
-## The Gate Function
-
-```
-BEFORE claiming any status or expressing satisfaction:
-
-1. IDENTIFY: What command proves this claim?
-2. RUN: Execute the FULL command (fresh, complete)
-3. READ: Full output, check exit code, count failures
-4. VERIFY: Does output confirm the claim?
-   - If NO: State actual status with evidence
-   - If YES: State claim WITH evidence
-5. AGENT CHECK: Run system diagnostics
-6. ONLY THEN: Make the claim
-
-Skip any step = lying, not verifying
-```
-
-## Agent System Checks
-
-After passing all verification commands, run system diagnostics:
-
-### Health Check
-
-```
-YOUR_AGENT_core op:admin_health
-```
-
-Catches issues tests might miss — vault corruption, stale caches, configuration drift.
-
-### Full Diagnostic
-
-```
-YOUR_AGENT_core op:admin_diagnostic
-```
-
-Comprehensive system check — module status, database integrity, cache health, configuration validity.
-
-### Vault Analytics
-
-```
-YOUR_AGENT_core op:admin_vault_analytics
-```
-
-Verify knowledge quality metrics — are capture rates healthy? Any degradation?
-
-If any check reports problems, address them before claiming completion.
-
-## Common Failures
-
-| Claim                 | Requires                        | Not Sufficient                 |
-| --------------------- | ------------------------------- | ------------------------------ |
-| Tests pass            | Test command output: 0 failures | Previous run, "should pass"    |
-| Linter clean          | Linter output: 0 errors         | Partial check, extrapolation   |
-| Build succeeds        | Build command: exit 0           | Linter passing, logs look good |
-| Bug fixed             | Test original symptom: passes   | Code changed, assumed fixed    |
-| Regression test works | Red-green cycle verified        | Test passes once               |
-| Agent completed       | VCS diff shows changes          | Agent reports "success"        |
-| Requirements met      | Line-by-line checklist          | Tests passing                  |
-| Agent healthy         | `admin_diagnostic` clean        | "No errors in logs"            |
-
-## Red Flags - STOP
-
-- Using "should", "probably", "seems to"
-- Expressing satisfaction before verification ("Great!", "Perfect!", "Done!", etc.)
-- About to commit/push/PR without verification
-- Trusting agent success reports
-- Relying on partial verification
-- Thinking "just this once"
-- Tired and wanting work over
-- ANY wording implying success without having run verification
-
-## Rationalization Prevention
-
-| Excuse                                  | Reality                |
-| --------------------------------------- | ---------------------- |
-| "Should work now"                       | RUN the verification   |
-| "I'm confident"                         | Confidence ≠ evidence  |
-| "Just this once"                        | No exceptions          |
-| "Linter passed"                         | Linter ≠ compiler      |
-| "Agent said success"                    | Verify independently   |
-| "I'm tired"                             | Exhaustion ≠ excuse    |
-| "Partial check is enough"               | Partial proves nothing |
-| "Different words so rule doesn't apply" | Spirit over letter     |
-
-## Key Patterns
-
-**Tests:**
-
-```
-[Run test command] [See: 34/34 pass] "All tests pass"
-NOT: "Should pass now" / "Looks correct"
-```
-
-**Regression tests (TDD Red-Green):**
-
-```
-Write -> Run (pass) -> Revert fix -> Run (MUST FAIL) -> Restore -> Run (pass)
-NOT: "I've written a regression test" (without red-green verification)
-```
-
-**Build:**
-
-```
-[Run build] [See: exit 0] "Build passes"
-NOT: "Linter passed" (linter doesn't check compilation)
-```
-
-**Requirements:**
-
-```
-Re-read plan -> Create checklist -> Verify each -> Report gaps or completion
-NOT: "Tests pass, phase complete"
-```
-
-**Agent delegation:**
-
-```
-Agent reports success -> Check VCS diff -> Verify changes -> Report actual state
-NOT: Trust agent report
-```
-
-## After Verification — Capture Session
-
-Once work is verified complete, capture a session summary so context persists:
-
-```
-YOUR_AGENT_core op:session_capture
-  params: {
-    summary: "<what was accomplished, files modified, key decisions>"
-  }
-```
-
-This ensures the next session has context about what was verified and completed.
-
-## When To Apply
-
-**ALWAYS before:**
-
-- ANY variation of success/completion claims
-- ANY expression of satisfaction
-- ANY positive statement about work state
-- Committing, PR creation, task completion
-- Moving to next task
-- Delegating to agents
-
-## The Bottom Line
-
-Run the command. Read the output. THEN claim the result. This is non-negotiable.
-
-## Agent Tools Reference
-
-| Op                      | When to Use                         |
-| ----------------------- | ----------------------------------- |
-| `admin_health`          | Quick system health check           |
-| `admin_diagnostic`      | Comprehensive system diagnostic     |
-| `admin_vault_analytics` | Knowledge quality metrics           |
-| `session_capture`       | Persist verified completion context |

package/dist/skills/writing-plans.md

@@ -1,215 +0,0 @@
----
-name: writing-plans
-description: Use when you have a spec or requirements for a multi-step task, before touching code
----
-
-<!-- Adapted from superpowers (MIT License) -->
-
-# Writing Plans
-
-## Overview
-
-Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.
-
-Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.
-
-**Announce at start:** "I'm using the writing-plans skill to create the implementation plan."
-
-**Save plans to:** `docs/plans/YYYY-MM-DD-<feature-name>.md`
-
-## Before Writing — Search First, Plan Second
-
-**Never write a plan from scratch.** Always search for existing knowledge first.
-
-### 1. Vault First
-
-Check the vault for relevant implementation patterns:
-
-```
-YOUR_AGENT_core op:search_intelligent
-  params: { query: "<feature being planned>" }
-```
-
-Look for:
-
-- **Implementation patterns** — proven approaches for similar features
-- **Anti-patterns** — approaches that failed and should be avoided
-- **Testing patterns** — how similar features were tested
-
-Also check brain strengths for what's worked:
-
-```
-YOUR_AGENT_core op:brain_strengths
-```
-
-Browse related knowledge domains for additional context:
-
-```
-YOUR_AGENT_core op:vault_domains
-YOUR_AGENT_core op:vault_tags
-```
-
-### 2. Web Search Second
-
-If the vault doesn't have implementation guidance, search the web:
-
-- **Libraries and tools** — is there a package that does this already?
-- **Reference implementations** — how did other projects solve this?
-- **API documentation** — official docs for libraries you'll use
-- **Known issues** — pitfalls others ran into
-
-### 3. Then Write the Plan
-
-Incorporate vault insights and web findings into the plan. Reference specific vault entries and documentation links when they inform a step. A plan informed by existing knowledge is dramatically better than one written from first principles.
-
-## Create a Tracked Plan
-
-Use the agent's planning system to create a tracked, resumable plan:
-
-```
-YOUR_AGENT_core op:create_plan
-  params: {
-    objective: "<one-sentence goal>",
-    scope: { included: [...], excluded: [...] },
-    steps: [
-      { title: "Step 1 title", description: "details" },
-      ...
-    ]
-  }
-```
-
-This makes the plan persistent across sessions — if context compacts or sessions change, the plan survives.
-
-## Grade the Plan
-
-After drafting, grade the plan for quality before presenting to the user:
-
-```
-YOUR_AGENT_core op:plan_grade
-  params: { planId: "<id from create_plan>" }
-```
-
-If the grade is below target, auto-improve:
-
-```
-YOUR_AGENT_core op:plan_auto_improve
-  params: { planId: "<id>" }
-```
-
-This iterates on the plan — filling gaps, adding missing test steps, clarifying ambiguous instructions. Repeat until the grade meets the target:
-
-```
-YOUR_AGENT_core op:plan_meets_grade
-  params: { planId: "<id>", targetGrade: "A" }
-```
-
-### Iterate on Drafts
-
-For complex plans, iterate before finalizing:
-
-```
-YOUR_AGENT_core op:plan_iterate
-  params: { planId: "<id>", feedback: "<what needs improvement>" }
-```
-
-This creates a new version of the plan incorporating the feedback, preserving version history.
-
-## Split into Tasks
-
-Once the plan is approved, split it into trackable tasks:
-
-```
-YOUR_AGENT_core op:plan_split
-  params: { planId: "<id>" }
-```
-
-This generates individual tasks from the plan steps, ready for execution tracking.
-
-## Bite-Sized Task Granularity
-
-**Each step is one action (2-5 minutes):**
-
-- "Write the failing test" - step
-- "Run it to make sure it fails" - step
-- "Implement the minimal code to make the test pass" - step
-- "Run the tests and make sure they pass" - step
-- "Commit" - step
-
-## Plan Document Header
-
-**Every plan MUST start with this header:**
-
-```markdown
-# [Feature Name] Implementation Plan
-
-> **For Claude:** REQUIRED SUB-SKILL: Use executing-plans to implement this plan task-by-task.
-
-**Goal:** [One sentence describing what this builds]
-
-**Architecture:** [2-3 sentences about approach]
-
-**Tech Stack:** [Key technologies/libraries]
-
----
-```
-
-## Task Structure
-
-Each task uses this format:
-
-- Files: Create / Modify / Test paths
-- Step 1: Write the failing test (with code)
-- Step 2: Run test to verify it fails (with expected output)
-- Step 3: Write minimal implementation (with code)
-- Step 4: Run test to verify it passes (with expected output)
-- Step 5: Commit (with exact git commands)
-
-## Remember
-
-- Exact file paths always
-- Complete code in plan (not "add validation")
-- Exact commands with expected output
-- DRY, YAGNI, TDD, frequent commits
-
-## After Plan Approval
-
-Once the user approves the plan, register it for tracking:
-
-```
-YOUR_AGENT_core op:approve_plan
-  params: { planId: "<id from create_plan>" }
-```
-
-Check plan stats for an overview:
-
-```
-YOUR_AGENT_core op:plan_stats
-```
-
-## Execution Handoff
-
-After saving the plan, offer execution choice:
-
-"Plan complete and saved to `docs/plans/<filename>.md`. Two execution options:
-
-**1. Subagent-Driven (this session)** - I dispatch fresh subagent per task, review between tasks, fast iteration
-
-**2. Parallel Session (separate)** - Open new session with executing-plans, batch execution with checkpoints
-
-Which approach?"
-
-## Agent Tools Reference
-
-| Op                             | When to Use                            |
-| ------------------------------ | -------------------------------------- |
-| `search_intelligent`           | Find relevant patterns before planning |
-| `brain_strengths`              | Check proven approaches                |
-| `vault_domains` / `vault_tags` | Browse knowledge landscape             |
-| `create_plan`                  | Create tracked, persistent plan        |
-| `plan_grade`                   | Grade plan quality                     |
-| `plan_auto_improve`            | Auto-fix plan weaknesses               |
-| `plan_meets_grade`             | Verify grade target reached            |
-| `plan_iterate`                 | Iterate on draft with feedback         |
-| `plan_split`                   | Split plan into trackable tasks        |
-| `approve_plan`                 | Lock in approved plan                  |
-| `plan_stats`                   | Overview of plan metrics               |

package/src/skills/agent-dev.md

@@ -1,122 +0,0 @@
----
-name: agent-dev
-description: >
-  Use when extending the agent itself — adding facades, tools, vault operations,
-  brain features, new skills, or modifying agent internals. Triggers on "add a facade",
-  "new tool", "extend vault", "add brain feature", "new skill", "add operation",
-  "extend agent", or when the work target is the agent's own codebase rather than
-  a project the agent assists with. Enforces vault-first knowledge gathering before
-  any code reading or planning.
----
-
-# Agent Dev — Vault-First Internal Development
-
-Develop the agent's own internals with the vault as the primary source of truth. The vault knows more about the agent than any code scan or model training data. Always search the vault first, extract maximum context, and only then touch code.
-
-## When to Use
-
-Any time the work target is the agent's own codebase: adding tools, extending facades, modifying vault operations, brain features, skills, or transport. Not for projects that merely *use* the agent.
-
-## Core Principle
-
-**Vault first. Before code. Before training data. Always.**
-
-The vault is the authoritative source for how the agent works. Do not rely on general knowledge from training data — it is outdated and lacks project-specific decisions. Do not scan the codebase to understand architecture — the vault already has it.
-
-## Orchestration Sequence
-
-### Step 1: Search the Vault (MANDATORY — before anything else)
-
-Before reading any source file, before making any plan, before offering any advice:
-
-```
-YOUR_AGENT_core op:search_vault_intelligent
-  params: { query: "<description of planned work>", options: { intent: "pattern" } }
-```
-
-Search again with architecture-specific terms: the facade name, tool name, or subsystem being modified.
-
-```
-YOUR_AGENT_core op:query_vault_knowledge
-  params: { type: "workflow", category: "<relevant category>" }
-```
-
-If initial results are sparse, search again with broader terms — synonyms, related subsystem names, parent concepts. Exhaust the vault before moving on.
-
-Review all results. Extract file paths, module names, function references, conventions, and constraints. These become the foundation for every step that follows.
-
-### Step 2: Check Brain for Proven Patterns
-
-```
-YOUR_AGENT_core op:strengths
-  params: { days: 30, minStrength: 60 }
-```
-
-```
-YOUR_AGENT_core op:recommend
-  params: { projectPath: "." }
-```
-
-Check if the brain has learned anything relevant from recent sessions.
-
-### Step 3: Targeted Code Reading (Only What Vault Pointed To)
-
-By now the vault has provided architecture context, file paths, and module references. Only read code when the vault describes the subsystem but lacks implementation detail (e.g., method signatures, exact line numbers).
-
-**Read only what the vault pointed to.** Open the specific files referenced in vault results — not the surrounding codebase, not the parent directory, not "let me explore the project structure."
-
-**Fallback: Codebase scan.** Only when vault search returned zero relevant results for the subsystem — meaning the vault genuinely has no knowledge about it — fall back to `Grep` with targeted terms. This is the last resort, not the default.
-
-### Step 4: Plan with Vault Context
-
-Create the implementation plan referencing vault findings explicitly:
-
-- Which patterns apply (cite vault entry titles)
-- Which anti-patterns to avoid (cite the specific anti-pattern)
-- Which conventions to follow (naming, facade structure, tool registration)
-
-Every plan must trace its decisions back to vault knowledge. If a decision has no vault backing, flag it as a new architectural choice that should be captured after implementation (Step 7).
-
-### Step 5: Implement
-
-Follow the plan. Key conventions for agent internals:
-
-- **Facades**: Thin routing layer — delegate to domain modules. No business logic in facades.
-- **Tools**: Follow `op:operation_name` naming, return structured responses.
-- **Vault writes**: All writes go through the vault intelligence layer.
-- **Tests**: Colocated test files. Run with vitest.
-- **Build**: Must compile without errors before considering done.
-
-### Step 6: Validate and Self-Correct
-
-Run the relevant test suite. Rebuild — must complete without errors.
-
-**Self-correction loop:** If tests fail or build breaks, do NOT ask the user what to do. Read the error, trace the cause in the code just written, fix it, and re-run. Repeat until green. The agent owns the code it wrote — if something fails, the agent fixes its own implementation. Only escalate to the user when the failure is outside the agent's control (missing infrastructure, permissions, unclear requirements).
-
-### Step 7: Capture What Was Learned
-
-If this work revealed new architectural knowledge, a useful pattern, or a surprising anti-pattern:
-
-```
-YOUR_AGENT_core op:capture_knowledge
-  params: {
-    title: "<what was learned>",
-    description: "<the pattern or anti-pattern>",
-    type: "pattern",
-    tags: ["<relevant-tags>"]
-  }
-```
-
-This ensures future sessions benefit from today's discovery — making the vault smarter for the next developer.
-
-## Anti-Patterns to Avoid
-
-- **Code-first exploration**: Reading source files before searching the vault. The vault already has the architecture — scanning code is slower and gives less context.
-- **Training-data advice**: Offering general guidance from model training data instead of searching the vault for project-specific knowledge.
-- **Skipping vault search**: The vault contains all architecture knowledge. Not searching it means reinventing knowledge that already exists.
-- **Planning without vault context**: Plans created without vault knowledge miss conventions, duplicate existing patterns, or violate architectural boundaries.
-- **Broad codebase scanning**: Exploring directories and reading files "to understand the project" instead of using vault results as a targeted map.
-
-## Exit Criteria
-
-Development is complete when: vault was searched exhaustively first (Step 1), implementation follows discovered patterns, tests pass, build succeeds, and any new learning is captured back to vault (Step 7).

package/src/skills/agent-guide.md

@@ -1,110 +0,0 @@
----
-name: agent-guide
-description: >
-  Use when the user asks "what can you do", "help me", "how do I use this",
-  "what features do you have", "what tools are available", "how does this work",
-  "show me your capabilities", "what are you", "who are you", or any question
-  about the agent's identity, capabilities, available tools, or how to use them.
-  Not needed for proactive tool suggestions — those are handled by engine rules.
----
-
-# Agent Guide — Capability Discovery
-
-Help users understand what this agent can do, how to use it effectively, and what makes it different from a raw LLM. This skill handles the deep discovery flow — proactive tool suggestions during normal work are handled by the engine rules (Tool Advocacy section).
-
-## When to Use
-
-- "What can you do?" / "What are your capabilities?"
-- "How do I search for X?" / "How do I capture knowledge?"
-- "What tools do you have?" / "Show me your features"
-- "Who are you?" / "What is this agent?"
-- "Help" / "I'm stuck" / "How does this work?"
-- First-time users, onboarding, or anyone unfamiliar with the agent
-
-## Capability Discovery Sequence
-
-### Step 1: Identity
-
-```
-YOUR_AGENT_core op:activate
-  params: { projectPath: "." }
-```
-
-This returns the agent's persona: name, role, description, tone, principles, and domains. Present the identity first — who the agent is and what it specializes in.
-
-### Step 2: Health & Status
-
-```
-YOUR_AGENT_core op:admin_health
-```
-
-Shows what subsystems are active: vault (how many entries), brain (vocabulary size), LLM availability. This tells the user what the agent currently has to work with.
-
-### Step 3: Available Tools
-
-```
-YOUR_AGENT_core op:admin_tool_list
-```
-
-Lists all facades and operations. Present them grouped by category with plain-language descriptions.
-
-### Step 4: Present by What Users Can DO
-
-Organize capabilities by user goals, not technical names:
-
-**Knowledge & Memory**
-- Search the vault for patterns, anti-patterns, and architectural decisions
-- Capture new knowledge from the current session
-- Search across sessions and projects for relevant context
-- Curate: deduplicate, groom, resolve contradictions
-
-**Planning & Execution**
-- Create structured plans with vault context and brain recommendations
-- Split plans into tasks with complexity estimates
-- Track execution with drift detection
-- Complete with knowledge capture and session recording
-
-**Intelligence & Learning**
-- Brain learns from every session — patterns get stronger with use
-- Recommendations based on similar past work
-- Strength tracking: which patterns are proven vs experimental
-- Feedback loop: brain improves based on what works
-
-**Quality & Validation**
-- Health checks across all subsystems
-- Iterative validation loops with configurable targets
-- Governance: policies, proposals, quotas
-
-**Identity & Control**
-- Persona activation and deactivation
-- Intent routing: the agent classifies what you want and routes to the right workflow
-- Project registration and cross-project linking
-
-**Domain Knowledge** (varies by agent)
-- Each domain has: `get_patterns`, `search`, `get_entry`, `capture`, `remove`
-- Call `op:activate` to discover which domains are configured
-
-## Common Questions
-
-### "What makes you different from regular Claude?"
-
-You have persistent knowledge (vault), learned patterns (brain), structured planning with grading, iterative validation loops, and domain-specific intelligence. Regular Claude starts fresh every conversation — this agent accumulates knowledge and gets smarter over time.
-
-### "How do I get the most out of you?"
-
-1. **Use the vault** — search before deciding, capture after learning
-2. **Use planning** — structured plans beat ad-hoc work for anything non-trivial
-3. **Trust the brain** — pattern recommendations come from real usage data
-4. **Capture everything** — every bug fix, every pattern, every anti-pattern. The vault grows smarter with use.
-5. **Use loops for quality** — iterative validation catches issues that single-pass work misses
-
-### "How do I add new capabilities?"
-
-Extensions in `src/extensions/` can add new ops, facades, middleware, and hooks. Domain packs add domain-specific knowledge and validation.
-
-## Anti-Patterns
-
-- **Listing raw op names without context** — always explain what the op does in plain language
-- **Claiming capabilities that do not exist** — only reference ops the agent actually has. When unsure, call `op:admin_tool_list` first
-- **Dumping the entire tool catalog** — answer the specific question, show relevant tools, not all tools
-- **Repeating what the user already knows** — if they ask about a specific feature, answer that, don't give the full tour

package/src/skills/agent-persona.md

@@ -1,66 +0,0 @@
----
-name: agent-persona
-description: >
-  Use when the user activates the agent's persona via its greeting phrase, or says
-  "activate persona", "be yourself", "stay in character", or any activation phrase
-  defined in the agent's persona configuration. Reinforces character persistence
-  through the session and survives context compaction.
----
-
-# Agent Persona — Stay in Character
-
-This skill reinforces persona persistence. The MCP activation loads the runtime payload — this skill ensures the character sticks across the full session, including after context compaction.
-
-## How It Works
-
-Every agent has a persona defined in `src/identity/persona.ts` (or `src/activation/persona.ts` in older agents). This file contains:
-
-- **name** — the agent's display name
-- **role** — what the agent does
-- **tone** — `precise`, `mentor`, or `pragmatic`
-- **greeting** — the activation response
-- **principles** — core values that guide behavior
-
-## Activation
-
-When the user triggers activation (greeting phrase or explicit request):
-
-```
-YOUR_AGENT_core op:activate
-  params: { projectPath: "." }
-```
-
-The activation response contains the full persona payload. Adopt it immediately.
-
-## Rules
-
-1. **Stay in character for EVERY response** until the user explicitly deactivates
-2. **Technical accuracy is the priority** — persona is the wrapper, not a replacement for correctness
-3. **Tone consistency** — match the configured tone (`precise` = concise and exact, `mentor` = educational and encouraging, `pragmatic` = direct and practical)
-4. If character drifts after context compaction, the persona information in the compacted summary should restore it — follow it
-
-## Context Compaction Survival
-
-Long sessions trigger context compaction. To survive:
-
-- The persona activation state is included in compaction summaries
-- After compaction, check if persona was active and re-adopt the character
-- Never break character just because the conversation was compacted
-
-## Deactivation
-
-When the user says "deactivate", "stop persona", "be normal", or uses the agent's deactivation phrase:
-
-```
-YOUR_AGENT_core op:activate
-  params: { deactivate: true }
-```
-
-Return to neutral assistant mode.
-
-## Anti-Patterns
-
-- **Dropping character mid-session** — if activated, stay activated
-- **Over-persona, under-substance** — character adds flavor, not replaces technical depth
-- **Forcing persona on unwilling users** — only activate when explicitly triggered
-- **Ignoring tone setting** — a `precise` agent should not use flowery language; a `mentor` agent should not be terse