agentsys 5.1.0 → 5.2.0

package/plugins/perf/skills/perf-baseline-manager/SKILL.md

@@ -1,30 +0,0 @@
----
-name: perf-baseline-manager
-description: "Use when managing perf baselines, consolidating results, or comparing versions. Ensures one baseline JSON per version."
-version: 5.1.0
----
-
-# perf-baseline-manager
-
-Manage baseline storage and comparison.
-
-Follow `docs/perf-requirements.md` as the canonical contract.
-
-## Required Rules
-
-- One baseline JSON per version.
-- Store under `{state-dir}/perf/baselines/<version>.json`.
-- Record metrics + environment metadata.
-
-## Output Format
-
-```
-baseline_version: <version>
-metrics: <summary>
-file: <path>
-```
-
-## Constraints
-
-- Overwrite older baseline for the same version.
-- Do not create multiple files for one version.

package/plugins/perf/skills/perf-benchmarker/SKILL.md

@@ -1,52 +0,0 @@
----
-name: perf-benchmarker
-description: "Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (30s only for binary search) and no parallel benchmarks."
-version: 5.1.0
-argument-hint: "[command] [duration]"
----
-
-# perf-benchmarker
-
-Run sequential benchmarks with strict duration rules.
-
-Follow `docs/perf-requirements.md` as the canonical contract.
-
-## Parse Arguments
-
-```javascript
-const args = '$ARGUMENTS'.split(' ').filter(Boolean);
-const command = args.find(a => !a.match(/^\d+$/)) || '';
-const duration = parseInt(args.find(a => a.match(/^\d+$/)) || '60', 10);
-```
-
-## Required Rules
-
-- Benchmarks MUST run sequentially (never parallel).
-- Minimum duration: 60s per run (30s only for binary search).
-- Warmup: 10s minimum before measurement.
-- Re-run anomalies.
-
-## Output Format
-
-```
-command: <benchmark command>
-duration: <seconds>
-warmup: <seconds>
-results: <metrics summary>
-notes: <anomalies or reruns>
-```
-
-## Output Contract
-
-Benchmarks MUST emit a JSON metrics block between markers:
-
-```
-PERF_METRICS_START
-{"scenarios":{"low":{"latency_ms":120},"high":{"latency_ms":450}}}
-PERF_METRICS_END
-```
-
-## Constraints
-
-- No short runs unless binary-search phase.
-- Do not change code while benchmarking.

package/plugins/perf/skills/perf-code-paths/SKILL.md

@@ -1,32 +0,0 @@
----
-name: perf-code-paths
-description: "Use when mapping code paths, entrypoints, and likely hot files before profiling."
-version: 5.1.0
----
-
-# perf-code-paths
-
-Identify likely implementation paths for a performance scenario.
-
-Follow `docs/perf-requirements.md` as the canonical contract.
-
-## Required Steps
-
-1. Use repo-map if available; otherwise use grep for entrypoints and handlers.
-2. List top candidate files/symbols tied to the scenario.
-3. Include imports/exports or call chains when relevant.
-
-## Output Format
-
-```
-keywords: <comma-separated list>
-paths:
-  - file: <path>
-    symbols: [<symbol1>, <symbol2>]
-    evidence: <short reason>
-```
-
-## Constraints
-
-- Focus only on supported languages (Rust, Java, JS/TS, Go, Python).
-- Keep to the most relevant 10-15 files.

package/plugins/perf/skills/perf-investigation-logger/SKILL.md

@@ -1,41 +0,0 @@
----
-name: perf-investigation-logger
-description: "Use when appending structured perf investigation notes and evidence."
-version: 5.1.0
----
-
-# perf-investigation-logger
-
-Append structured investigation notes to `{state-dir}/perf/investigations/<id>.md`.
-
-Follow `docs/perf-requirements.md` as the canonical contract.
-
-## Required Content
-
-1. Exact user quotes (verbatim)
-2. Phase summary
-3. Decisions and rationale
-4. Evidence pointers (files, metrics, commands)
-
-## Output Format
-
-```
-## <Phase Name> - <YYYY-MM-DD>
-
-**User Quote:** "<exact quote>"
-
-**Summary**
-- ...
-
-**Evidence**
-- Command: `...`
-- File: `path:line`
-
-**Decision**
-- ...
-```
-
-## Constraints
-
-- Use `AI_STATE_DIR` for state path (default `.claude`).
-- Do not paraphrase user quotes.

package/plugins/perf/skills/perf-profiler/SKILL.md

@@ -1,42 +0,0 @@
----
-name: perf-profiler
-description: "Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence."
-version: 5.1.0
-argument-hint: "[tool] [command]"
----
-
-# perf-profiler
-
-Run profiling tools and capture hotspots with evidence.
-
-Follow `docs/perf-requirements.md` as the canonical contract.
-
-## Parse Arguments
-
-```javascript
-const args = '$ARGUMENTS'.split(' ').filter(Boolean);
-const tool = args[0] || '';
-const command = args.slice(1).join(' ');
-```
-
-## Required Rules
-
-- Verify debug symbols before profiling.
-- Capture file:line for hotspots.
-- Provide flame graph or equivalent output when possible.
-
-## Output Format
-
-```
-tool: <profiler>
-command: <command>
-hotspots:
-  - file:line - reason
-artifacts:
-  - <path to flame graph or profile>
-```
-
-## Constraints
-
-- No profiling without a clear scenario.
-- Keep outputs minimal and evidence-backed.

package/plugins/perf/skills/perf-theory-gatherer/SKILL.md

@@ -1,35 +0,0 @@
----
-name: perf-theory-gatherer
-description: "Use when generating performance hypotheses backed by git history and code evidence."
-version: 5.1.0
----
-
-# perf-theory-gatherer
-
-Generate performance hypotheses for a specific scenario.
-
-Follow `docs/perf-requirements.md` as the canonical contract.
-
-## Required Steps
-
-1. Review recent git history (scope to relevant paths when possible).
-2. Identify code paths involved in the scenario (repo-map or grep).
-3. Produce up to 5 hypotheses with evidence + confidence.
-
-## Output Format
-
-```
-hypotheses:
-  - id: H1
-    hypothesis: <short description>
-    evidence: <file/path or git change>
-    confidence: low|medium|high
-  - id: H2
-    ...
-```
-
-## Constraints
-
-- MUST check git history before hypothesizing.
-- No optimization suggestions; only hypotheses.
-- Keep to 5 hypotheses maximum.

package/plugins/perf/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/plugins/repo-map/.claude-plugin/plugin.json

@@ -1,22 +0,0 @@
-{
-  "name": "repo-map",
-  "version": "5.1.0",
-  "description": "AST-based repository map generator using ast-grep for symbol and import extraction with incremental updates",
-  "author": {
-    "name": "Avi Fenesh",
-    "email": "[email protected]",
-    "url": "https://github.com/avifenesh"
-  },
-  "homepage": "https://github.com/avifenesh/agentsys#repo-map",
-  "repository": "https://github.com/avifenesh/agentsys",
-  "license": "MIT",
-  "keywords": [
-    "repo-map",
-    "ast",
-    "symbols",
-    "drift-detect",
-    "dependency-graph",
-    "documentation",
-    "analysis"
-  ]
-}

package/plugins/repo-map/agents/map-validator.md

@@ -1,60 +0,0 @@
----
-name: map-validator
-description: Validate repo-map output for obvious errors and missing data. Use this agent after /repo-map init or update.
-tools:
-  - Read
-model: haiku
----
-
-# Repo Map Validator
-
-You validate the repo-map summary for obvious issues. You do NOT rebuild the map or modify files.
-
-## Input
-
-You receive a short summary (JSON or text) with counts and metadata:
-
-```json
-{
-  "files": 142,
-  "symbols": 847,
-  "languages": ["typescript", "python"],
-  "duration": 1542
-}
-```
-
-## Validation Checklist
-
-Check for these issues:
-
-1. **Empty map**: files = 0 or symbols = 0
-2. **Suspiciously small**: files < 5 for a non-trivial repo
-3. **Language mismatch**: no languages detected
-4. **Missing docs** (if docs were requested): docs missing or empty
-5. **Excessive errors**: errors array present with >5 entries
-
-## Output Format
-
-Return one of:
-
-```
-valid
-```
-
-or
-
-```
-warning: <issue>
-```
-
-or
-
-```
-invalid: <issue>
-```
-
-## Constraints
-
-- Do NOT speculate beyond the provided summary
-- Keep output to a single line
-- If unsure, return `warning` rather than `invalid`

package/plugins/repo-map/commands/repo-map.md

@@ -1,133 +0,0 @@
----
-description: Generate and maintain a cached AST repo map (symbols, imports, exports) using ast-grep for accurate drift detection and analysis
-codex-description: 'Use when user asks to "create repo map", "generate repo map", "update repo map", "repo map status", "map symbols". Builds and updates AST-based repo map using ast-grep.'
-argument-hint: "init|update|status|rebuild [--force] [--full]"
-allowed-tools: Bash(git:*), Bash(npm:*), Read, Task, Write, AskUserQuestion
----
-
-# /repo-map - AST Repo Map
-
-Generate a cached repository map of symbols and imports using ast-grep. This enables faster drift detection and more accurate code context.
-
-## Arguments
-
-Parse from `$ARGUMENTS`:
-
-- **Action**: `init` | `update` | `status` | `rebuild` (default: `status`)
-- `--force`: Force rebuild (for `init`)
-- `--full`: Force full rebuild (for `update`)
-
-Examples:
-
-- `/repo-map init`
-- `/repo-map update --full`
-- `/repo-map status`
-
-## Execution
-
-### 1) Load Repo Map Module
-
-```javascript
-const { getPluginRoot } = require('@agentsys/lib/cross-platform');
-const pluginRoot = getPluginRoot('repo-map');
-if (!pluginRoot) { console.error('Error: Could not locate repo-map plugin root'); process.exit(1); }
-const repoMap = require(`${pluginRoot}/lib/repo-map`);
-```
-
-### 2) Parse Arguments
-
-```javascript
-const args = '$ARGUMENTS'.split(' ').filter(Boolean);
-const action = (args[0] || 'status').toLowerCase();
-
-const options = {
-  force: args.includes('--force'),
-  full: args.includes('--full')
-};
-```
-
-### 3) Ensure ast-grep is Available
-
-```javascript
-const installed = await repoMap.checkAstGrepInstalled();
-if (!installed.found || !repoMap.installer.meetsMinimumVersion(installed.version)) {
-  const suggestion = repoMap.getInstallInstructions();
-  const choice = await AskUserQuestion({
-    questions: [{
-      header: 'Install ast-grep?',
-      question: 'ast-grep is required for repo-map. Install now?',
-      options: [
-        { label: 'Install via npm', description: 'Runs: npm install -g @ast-grep/cli' },
-        { label: 'Skip for now', description: 'Show install instructions and exit' }
-      ]
-    }]
-  });
-
-  if (choice?.[0] === 'Install via npm') {
-    await Bash('npm install -g @ast-grep/cli');
-  } else {
-    console.log(suggestion);
-    return;
-  }
-}
-```
-
-### 4) Run Action
-
-```javascript
-let result;
-
-if (action === 'init' || action === 'rebuild') {
-  result = await repoMap.init(process.cwd(), {
-    force: action === 'rebuild' || options.force
-  });
-} else if (action === 'update') {
-  result = await repoMap.update(process.cwd(), { full: options.full });
-} else if (action === 'status') {
-  result = repoMap.status(process.cwd());
-} else {
-  console.log('Unknown action. Use: init | update | status | rebuild');
-  return;
-}
-
-if (result?.success === false) {
-  console.log(result.error || 'Repo-map failed');
-  if (result.installSuggestion) console.log(result.installSuggestion);
-  return;
-}
-
-if (action === 'status' && !result.exists) {
-  console.log('No repo-map found. Run /repo-map init to generate one.');
-  return;
-}
-```
-
-### 5) Validate Results (init/update only)
-
-After `init` or `update`, run validation using the lightweight agent:
-
-```javascript
-if (action === 'init' || action === 'rebuild' || action === 'update') {
-  const summary = result?.map?.stats || result?.summary || result?.changes || {};
-  const validation = await Task({
-    subagent_type: 'repo-map:map-validator',
-    prompt: `Validate repo-map results. Summary: ${JSON.stringify(summary)}`
-  });
-  console.log(validation);
-}
-```
-
-## Output Format
-
-```markdown
-## Repo Map Result
-
-**Action**: init|update|status
-**Files**: <count>
-**Symbols**: <count>
-**Languages**: <list>
-**Commit**: <hash>
-
-### Notes
-- <warnings or validation results>
-```