agentsys 5.1.0 → 5.2.0

package/adapters/opencode/skills/perf-theory-tester/SKILL.md

@@ -1,36 +0,0 @@
----
-name: perf-theory-tester
-description: "Use when running controlled perf experiments to validate hypotheses."
-version: 5.1.0
----
-
-# perf-theory-tester
-
-Test hypotheses using controlled experiments.
-
-Follow `docs/perf-requirements.md` as the canonical contract.
-
-## Required Steps
-
-1. Confirm baseline is clean.
-2. Apply a single change tied to the hypothesis.
-3. Run 2+ validation passes.
-4. Revert to baseline before the next experiment.
-
-## Output Format
-
-```
-hypothesis: <id>
-change: <summary>
-delta: <metrics>
-verdict: accept|reject|inconclusive
-evidence:
-  - command: <benchmark command>
-  - files: <changed files>
-```
-
-## Constraints
-
-- One change per experiment.
-- No parallel benchmarks.
-- Record evidence for each run.

package/adapters/opencode/skills/repo-mapping/SKILL.md

@@ -1,85 +0,0 @@
----
-name: repo-mapping
-description: "Use when user asks to \"create repo map\", \"generate repo map\", \"update repo map\", \"repo map status\", or \"map symbols/imports\". Builds and validates an AST-based repo map using ast-grep."
-argument-hint: "[action] [--force]"
----
-
-> **OpenCode Note**: Invoke agents using `@agent-name` syntax.
-> Available agents: task-discoverer, exploration-agent, planning-agent,
-> implementation-agent, deslop-agent, delivery-validator, sync-docs-agent, consult-agent
-> Example: `@exploration-agent analyze the codebase`
-
-
-# Repo Mapping Skill
-
-Build and maintain a cached AST-based map of repository symbols and imports using ast-grep.
-
-## Parse Arguments
-
-*(JavaScript reference - not executable in OpenCode)*
-
-## Primary Responsibilities
-
-1. **Generate map** on demand (`/repo-map init`)
-2. **Update map** incrementally (`/repo-map update`)
-3. **Check status** and staleness (`/repo-map status`)
-4. **Validate output** with the map-validator agent
-
-## Core Data Contract
-
-Repo map is stored in the platform state directory:
-
-- Claude Code: `.claude/repo-map.json`
-- OpenCode: `.opencode/repo-map.json`
-- Codex CLI: `.codex/repo-map.json`
-
-Minimal structure:
-
-```json
-{
-  "version": "1.0.0",
-  "generated": "2026-01-25T12:00:00Z",
-  "updated": "2026-01-25T12:05:00Z",
-  "git": { "commit": "abc123", "branch": "main" },
-  "project": { "languages": ["typescript", "python"] },
-  "stats": { "totalFiles": 142, "totalSymbols": 847 },
-  "files": {
-    "src/auth/login.ts": {
-      "hash": "deadbeef1234abcd",
-      "language": "typescript",
-      "symbols": { "exports": [], "functions": [], "classes": [] },
-      "imports": [ { "source": "./utils", "kind": "named" } ]
-    }
-  }
-}
-```
-
-## Behavior Rules
-
-- **Never** run ast-grep without user approval if it is not installed
-- **Never** install dependencies without explicit user consent
-- **Always** validate map output with `map-validator` after init/update
-- **Prefer** incremental update unless map is stale or history rewritten
-
-## When to Suggest Repo Map
-
-If a user asks for drift detection, documentation alignment, or repo analysis and repo-map is missing:
-
-```
-Repo map not found. For better analysis, run:
-  /repo-map init
-```
-
-## Staleness Signals
-
-- Map commit not found (rebased)
-- Branch changed
-- Git hooks marked stale
-- Commits behind HEAD
-
-## Output Expectations
-
-Keep outputs concise:
-
-- **init/update**: file count, symbol count, commit, warnings
-- **status**: staleness, commits behind, last updated

package/adapters/opencode/skills/sync-docs/SKILL.md

@@ -1,245 +0,0 @@
----
-name: sync-docs
-description: "Sync documentation with code. Use when user asks to update docs, check docs, fix stale documentation, update changelog, or after code changes."
-version: 5.1.0
-argument-hint: "[report|apply] [--scope=all|recent|before-pr] [--include-undocumented]"
-allowed-tools: Bash(git:*), Read, Grep, Glob
----
-
-> **OpenCode Note**: Invoke agents using `@agent-name` syntax.
-> Available agents: task-discoverer, exploration-agent, planning-agent,
-> implementation-agent, deslop-agent, delivery-validator, sync-docs-agent, consult-agent
-> Example: `@exploration-agent analyze the codebase`
-
-
-# sync-docs
-
-Unified skill for syncing documentation with code state. Combines discovery, analysis, and CHANGELOG update into a single workflow.
-
-## Parse Arguments
-
-*(JavaScript reference - not executable in OpenCode)*
-
-## Quick Start - Agent Instructions
-
-**Step 1**: Get changed files (use Bash):
-```bash
-# Recent changes (default scope)
-git diff --name-only origin/main..HEAD 2>/dev/null || git diff --name-only HEAD~5..HEAD
-
-# Or for all files
-git ls-files '*.md'
-```
-
-**Step 2**: Find docs that reference changed files (use Grep):
-- Search for filenames, function names, class names in `*.md` files
-- Check README.md, CHANGELOG.md, docs/*.md
-
-**Step 3**: Analyze each doc for issues:
-- Version mismatches (compare doc versions to package.json)
-- Removed exports (symbols in docs but not in code)
-- Outdated code examples
-- Import path changes
-
-**Step 4**: Check CHANGELOG:
-- Look for `## [Unreleased]` section
-- Compare recent commit messages to CHANGELOG entries
-
-**Step 5**: If repo-map exists (`{stateDir}/repo-map.json` - platform state directory):
-- Load it to get accurate export list
-- Find exports not mentioned in any documentation
-- Report as `undocumented-export` issues
-
-## Input
-
-Arguments: `[report|apply] [--scope=all|recent|before-pr] [--include-undocumented]`
-
-- **Mode**: `report` (default) or `apply`
-- **Scope**:
-  - `recent` (default): Files changed since last commit to main
-  - `all`: Scan all docs against all code
-  - `before-pr`: Files in current branch, optimized for /next-task Phase 11
-- **--include-undocumented**: Find exports not mentioned in any docs (uses repo-map)
-
-## Architecture
-
-This skill orchestrates all documentation sync operations:
-
-```
-sync-docs skill
-    |-- Phase 1: Detect project context
-    |-- Phase 2: Find related docs (lib/collectors/docs-patterns)
-    |-- Phase 3: Analyze issues
-    |-- Phase 3.5: Find undocumented exports (repo-map integration)
-    |-- Phase 4: Check CHANGELOG
-    |-- Phase 5: Return structured results
-```
-
-The skill MUST NOT apply fixes directly. It returns structured data for the orchestrator to decide what to do.
-
----
-
-## Implementation Details (Reference)
-
-The sections below describe the internal JavaScript implementation for reference only. Agents should follow the Quick Start instructions above using Bash, Read, and Grep tools.
-
-### Phase 1: Detect Project Context
-
-Detect project type and find documentation files.
-
-### Phase 1.5: Ensure Repo-Map
-
-Before analyzing issues, ensure repo-map is available for accurate symbol detection:
-
-- Use AskUserQuestion tool for user input
-
-
-**User Interaction (only if ast-grep not installed):**
-
-Use AskUserQuestion:
-- Header: "ast-grep Required"
-- Question: "ast-grep not found. Install for better doc sync accuracy?"
-- Options:
-  - "Yes, show instructions" - Display platform-specific install instructions
-  - "No, use regex fallback" - Continue with less accurate regex-based detection
-
-If user declines or repo-map unavailable, the system falls back to regex-based export detection automatically.
-
-*(JavaScript reference - not executable in OpenCode)*
-
-This phase gathers context about the project without requiring external scripts.
-
-## Phase 2: Find Related Documentation
-
-Use lib/collectors/docs-patterns to find docs related to changed files:
-
-*(JavaScript reference - not executable in OpenCode)*
-
-## Phase 3: Analyze Documentation Issues
-
-For each related doc, check for issues:
-
-*(JavaScript reference - not executable in OpenCode)*
-
-Issue types detected:
-- `outdated-version`: Version string doesn't match current
-- `removed-export`: References removed symbol
-- `code-example`: Code example may be outdated
-- `import-path`: Import path changed
-- `undocumented-export`: Export exists in code but not mentioned in any docs (requires repo-map)
-
-## Phase 4: Check CHANGELOG
-
-*(JavaScript reference - not executable in OpenCode)*
-
-## Phase 5: Return Structured Results
-
-Combine all results into a single output:
-
-```json
-{
-  "mode": "report|apply",
-  "scope": "recent|all|before-pr|path",
-  "context": {
-    "projectType": "javascript|python|rust|go|unknown",
-    "docFiles": ["README.md", "CHANGELOG.md"]
-  },
-  "repoMap": {
-    "available": true,
-    "fallbackReason": null,
-    "stats": { "files": 142, "symbols": 847 }
-  },
-  "discovery": {
-    "changedFilesCount": 5,
-    "relatedDocsCount": 3,
-    "relatedDocs": [
-      { "doc": "README.md", "referencedFile": "src/api.js", "referenceTypes": ["filename", "import"] }
-    ]
-  },
-  "issues": [
-    {
-      "type": "outdated-version",
-      "severity": "low",
-      "doc": "README.md",
-      "line": 15,
-      "current": "1.0.0",
-      "expected": "1.1.0",
-      "autoFix": true,
-      "suggestion": "Update version from 1.0.0 to 1.1.0"
-    }
-  ],
-  "undocumentedExports": [
-    {
-      "type": "undocumented-export",
-      "severity": "low",
-      "file": "src/utils.js",
-      "name": "formatDate",
-      "line": 25,
-      "certainty": "MEDIUM",
-      "suggestion": "Export 'formatDate' in src/utils.js is not mentioned in any documentation"
-    }
-  ],
-  "fixes": [
-    {
-      "file": "README.md",
-      "type": "update-version",
-      "line": 15,
-      "search": "1.0.0",
-      "replace": "1.1.0"
-    }
-  ],
-  "changelog": {
-    "exists": true,
-    "hasUnreleased": true,
-    "undocumented": ["feat: add new feature"],
-    "status": "needs-update|ok"
-  },
-  "summary": {
-    "issueCount": 3,
-    "fixableCount": 2,
-    "bySeverity": { "high": 0, "medium": 1, "low": 2 }
-  }
-}
-```
-
-## Output Format
-
-Output the result as JSON between markers:
-
-```
-=== SYNC_DOCS_RESULT ===
-{JSON output}
-=== END_RESULT ===
-```
-
-## Usage by Agents
-
-### sync-docs-agent (standalone /sync-docs)
-
-```
-Skill: sync-docs
-Args: report --scope=recent
-```
-
-### /next-task Phase 11
-
-```
-Skill: sync-docs
-Args: apply --scope=before-pr
-```
-
-The orchestrator receives the structured result and spawns `simple-fixer` if fixes are needed.
-
-## Constraints
-
-1. **Report mode by default** - Never modify files unless explicitly in apply mode
-2. **Structured output** - Always return JSON between markers
-3. **No direct fixes** - Return fix instructions, let orchestrator decide
-4. **Preserve formatting** - Fix suggestions should preserve existing style
-5. **Safe changes only** - Only auto-fixable issues get fix entries
-
-## Error Handling
-
-- **No git**: Exit with error "Git required for change detection"
-- **No docs found**: Report empty docFiles, suggest creating README.md
-- **No changed files**: Report scope as "empty", suggest using --scope=all

package/adapters/opencode/skills/validate-delivery/SKILL.md

@@ -1,111 +0,0 @@
----
-name: validate-delivery
-description: "Use when user asks to \"validate delivery\", \"check readiness\", or \"verify completion\". Runs tests, build, and requirement checks with pass/fail instructions."
-version: 5.1.0
----
-
-# validate-delivery
-
-Autonomously validate that a task is complete and ready to ship.
-
-## Validation Checks
-
-### Check 1: Review Status
-
-*(JavaScript reference - not executable in OpenCode)*
-
-### Check 2: Tests Pass
-
-```bash
-# Detect test runner and run
-if grep -q '"test"' package.json; then
-  npm test; TEST_EXIT_CODE=$?
-elif [ -f "pytest.ini" ]; then
-  pytest; TEST_EXIT_CODE=$?
-elif [ -f "Cargo.toml" ]; then
-  cargo test; TEST_EXIT_CODE=$?
-elif [ -f "go.mod" ]; then
-  go test ./...; TEST_EXIT_CODE=$?
-else
-  TEST_EXIT_CODE=0  # No tests
-fi
-```
-
-### Check 3: Build Passes
-
-```bash
-if grep -q '"build"' package.json; then
-  npm run build; BUILD_EXIT_CODE=$?
-elif [ -f "Cargo.toml" ]; then
-  cargo build --release; BUILD_EXIT_CODE=$?
-elif [ -f "go.mod" ]; then
-  go build ./...; BUILD_EXIT_CODE=$?
-else
-  BUILD_EXIT_CODE=0  # No build step
-fi
-```
-
-### Check 4: Requirements Met
-
-*(JavaScript reference - not executable in OpenCode)*
-
-### Check 5: No Regressions
-
-```bash
-# Compare test counts before/after changes
-git stash
-BEFORE=$(npm test 2>&1 | grep -oE '[0-9]+ passing' | grep -oE '[0-9]+')
-git stash pop
-AFTER=$(npm test 2>&1 | grep -oE '[0-9]+ passing' | grep -oE '[0-9]+')
-[ "$AFTER" -lt "$BEFORE" ] && REGRESSION=true || REGRESSION=false
-```
-
-## Aggregate Results
-
-*(JavaScript reference - not executable in OpenCode)*
-
-## Decision and Output
-
-### If All Pass
-
-```javascript
-workflowState.completePhase({
-  approved: true,
-  checks,
-  summary: 'All validation checks passed'
-});
-
-return { approved: true, checks };
-```
-
-### If Any Fail
-
-*(JavaScript reference - not executable in OpenCode)*
-
-## Fix Instructions Generator
-
-*(JavaScript reference - not executable in OpenCode)*
-
-## Output Format
-
-```json
-{
-  "approved": true|false,
-  "checks": {
-    "reviewClean": { "passed": true },
-    "testsPassing": { "passed": true },
-    "buildPassing": { "passed": true },
-    "requirementsMet": { "passed": true },
-    "noRegressions": { "passed": true }
-  },
-  "failedChecks": [],
-  "fixInstructions": []
-}
-```
-
-## Constraints
-
-- NO human intervention - fully autonomous
-- Returns structured JSON for orchestrator
-- Generates specific fix instructions on failure
-- Workflow retries automatically after fixes

package/plugins/agnix/.claude-plugin/plugin.json

@@ -1,22 +0,0 @@
-{
-  "name": "agnix",
-  "version": "5.1.0",
-  "description": "Lint agent configurations before they break your workflow. Validates Skills, Hooks, MCP, Memory, Plugins.",
-  "author": {
-    "name": "Avi Fenesh",
-    "email": "[email protected]",
-    "url": "https://github.com/avifenesh"
-  },
-  "homepage": "https://github.com/avifenesh/agnix",
-  "repository": "https://github.com/avifenesh/agentsys",
-  "license": "MIT",
-  "keywords": [
-    "linting",
-    "validation",
-    "agents",
-    "skills",
-    "mcp",
-    "hooks",
-    "claude-code"
-  ]
-}

package/plugins/agnix/agents/agnix-agent.md

@@ -1,56 +0,0 @@
----
-name: agnix-agent
-description: Lint agent configurations using agnix CLI. Invoke agnix skill and return validation results.
-tools:
-  - Bash(agnix:*)
-  - Bash(cargo:*)
-  - Skill
-  - Read
-  - Glob
-  - Grep
-model: sonnet
----
-
-# Agnix Agent
-
-Validate agent configuration files using the agnix skill.
-
-## Workflow
-
-### 1. Parse Arguments
-
-Extract from prompt:
-- **path**: Target path (default: `.`)
-- **fix**: Whether to auto-fix
-- **strict**: Whether to treat warnings as errors
-- **target**: Tool-specific rules (claude-code, cursor, codex)
-
-### 2. Invoke Agnix Skill
-
-```
-Skill: agnix
-Args: [path] [--fix] [--strict] [--target=[target]]
-```
-
-The skill contains full CLI documentation and execution steps.
-
-### 3. Return Structured Results
-
-```
-=== AGNIX_RESULT ===
-{
-  "path": ".",
-  "errors": N,
-  "warnings": N,
-  "fixable": N,
-  "fixed": N,
-  "success": true|false
-}
-=== END_RESULT ===
-```
-
-## Constraints
-
-- Do NOT modify files unless `--fix` is passed
-- Return structured data for orchestrator
-- If agnix not installed, return install instructions

package/plugins/agnix/commands/agnix.md

@@ -1,139 +0,0 @@
----
-description: Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP', or mentions 'agent config issues', 'skill validation'.
-codex-description: 'Use when user asks to "lint agent configs", "validate skills", "check CLAUDE.md", "validate hooks", "lint MCP". Validates agent configuration files against 155 rules across 10+ AI tools.'
-argument-hint: "[path] [--fix] [--strict] [--target [target]]"
-allowed-tools: Task, Read
----
-
-# /agnix - Agent Config Linter
-
-Lint agent configurations before they break your workflow. Validates Skills, Hooks, MCP, Memory, Plugins across Claude Code, Cursor, GitHub Copilot, and Codex CLI.
-
-## Arguments
-
-Parse from $ARGUMENTS or use defaults:
-
-- **Path**: Target path (default: `.`)
-- **--fix**: Auto-fix issues
-- **--strict**: Treat warnings as errors
-- **--target**: `claude-code`, `cursor`, `codex`, or `generic` (default)
-
-## Execution
-
-### Phase 1: Spawn Agnix Agent
-
-```javascript
-const args = '$ARGUMENTS'.split(' ').filter(Boolean);
-const fix = args.includes('--fix');
-const strict = args.includes('--strict');
-
-// Parse --target (supports both --target=value and --target value forms)
-const allowedTargets = ['claude-code', 'cursor', 'codex', 'generic'];
-let rawTarget = 'generic';
-const targetEqIdx = args.findIndex(a => a.startsWith('--target='));
-const targetSpaceIdx = args.findIndex(a => a === '--target');
-if (targetEqIdx !== -1) {
-  rawTarget = args[targetEqIdx].split('=')[1] || 'generic';
-} else if (targetSpaceIdx !== -1 && args[targetSpaceIdx + 1] && !args[targetSpaceIdx + 1].startsWith('-')) {
-  rawTarget = args[targetSpaceIdx + 1];
-}
-const target = allowedTargets.includes(rawTarget) ? rawTarget : 'generic';
-
-// Parse path - exclude flags and --target's value, sanitize to prevent injection
-const excludeIndices = new Set([targetSpaceIdx, targetSpaceIdx + 1].filter(i => i >= 0));
-const path = (args.find((a, i) => !a.startsWith('-') && !excludeIndices.has(i)) || '.').replace(/[\n\r]/g, '');
-
-const result = await Task({
-  subagent_type: "agnix:agnix-agent",
-  prompt: `Validate agent configurations.
-Path: ${path}
-Fix: ${fix}
-Strict: ${strict}
-Target: ${target}
-
-Return structured results between === AGNIX_RESULT === markers.`
-});
-```
-
-### Phase 2: Parse Agent Results
-
-Extract structured JSON from agent output:
-
-```javascript
-function parseAgnix(output) {
-  const match = output.match(/=== AGNIX_RESULT ===[\s\S]*?({[\s\S]*?})[\s\S]*?=== END_RESULT ===/);
-  return match ? JSON.parse(match[1]) : { errors: 0, warnings: 0, diagnostics: [] };
-}
-
-const findings = parseAgnix(result);
-```
-
-### Phase 3: Present Results
-
-#### No Issues
-
-```markdown
-## Validation Passed
-
-No issues found in agent configurations.
-
-- Files validated: N
-- Target: {target}
-```
-
-#### Issues Found
-
-```markdown
-## Agent Config Issues
-
-| File | Line | Level | Rule | Message |
-|------|------|-------|------|---------|
-| SKILL.md | 3 | error | AS-004 | Invalid name |
-| CLAUDE.md | 15 | warning | PE-003 | Generic instruction |
-
-## Summary
-
-- **Errors**: N
-- **Warnings**: N
-- **Fixable**: N
-
-## Do Next
-
-- [ ] Run `/agnix --fix` to auto-fix {fixable} issues
-- [ ] Review remaining issues manually
-```
-
-#### After Fix
-
-```markdown
-## Fixed Issues
-
-| File | Line | Rule | Fix Applied |
-|------|------|------|-------------|
-| SKILL.md | 3 | AS-004 | Renamed to lowercase |
-
-**Fixed**: N issues
-**Remaining**: N issues (manual review needed)
-```
-
-## Supported Files
-
-| File Type | Examples |
-|-----------|----------|
-| Skills | `SKILL.md` |
-| Memory | `CLAUDE.md`, `AGENTS.md` |
-| Hooks | `${STATE_DIR}/settings.json` (Claude: .claude/, OpenCode: .opencode/, Codex: .codex/) |
-| MCP | `*.mcp.json` |
-| Cursor | `.cursor/rules/*.mdc` |
-| Copilot | `.github/copilot-instructions.md` |
-
-## Error Handling
-
-- **agnix not installed**: Show install command `cargo install agnix-cli`
-- **Invalid path**: Exit with "Path not found: [path]"
-- **Parse errors**: Show raw agnix output
-
-## Links
-
-- [agnix GitHub](https://github.com/avifenesh/agnix)
-- [Rules Reference](https://github.com/avifenesh/agnix/blob/main/knowledge-base/VALIDATION-RULES.md)