The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
chore: remove legacy insaits integration
Affaan Mustafa8488811b80c0
diff --git a/WORKING-CONTEXT.md b/WORKING-CONTEXT.mdindex 82ae07bad..66a70ef03 100644--- a/WORKING-CONTEXT.md+++ b/WORKING-CONTEXT.md@@ -155,6 +155,7 @@ Keep this file detailed for only the current sprint, blockers, and next actions.- 2026-04-05: Direct-ported the safe `globals` bump from PR `#1243` into `main` as part of the council lane and closed the PR as superseded.- 2026-04-05: Closed PR `#1232` after full audit. The proposed `skill-scout` workflow overlaps current `search-first`, `/skill-create`, and `skill-stocktake`; if a dedicated marketplace-discovery layer returns later it should be rebuilt on top of the current install/catalog model rather than landing as a parallel discovery path.- 2026-04-05: Ported the safe localized README switcher fixes from PR `#1209` directly into `main` rather than merging the docs PR wholesale. The navigation now consistently includes `Português (Brasil)` and `Türkçe` across the localized README switchers, while newer localized body copy stays intact.+- 2026-04-05: Removed the stale InsAIts shipped surface from `main`. ECC no longer ships the external Python MCP entry, opt-in hook wiring, wrapper/monitor scripts, or current docs mentions for `insa-its`; changelog history remains, but the live product surface is now fully ECC-native again.- 2026-04-05: Salvaged the reusable Hermes-generated operator workflow lane without replaying the whole branch. Added six ECC-native top-level skills instead of the old nested `skills/hermes-generated/*` tree: `automation-audit-ops`, `email-ops`, `finance-billing-ops`, `messages-ops`, `research-ops`, and `terminal-ops`. `research-ops` now wraps the existing research stack, while the other five extend `operator-workflows` without introducing any external runtime assumptions.- 2026-04-05: Added `skills/product-capability` plus `docs/examples/product-capability-template.md` as the canonical PRD-to-SRS lane for issue `#1185`. This is the ECC-native capability-contract step between vague product intent and implementation, and it lives in `business-content` rather than spawning a parallel planning subsystem.- 2026-04-05: Tightened `product-lens` so it no longer overlaps the new capability-contract lane. `product-lens` now explicitly owns product diagnosis / brief validation, while `product-capability` owns implementation-ready capability plans and SRS-style constraints.diff --git a/docs/pt-BR/README.md b/docs/pt-BR/README.mdindex 88e6fa2ef..8298a2ba6 100644--- a/docs/pt-BR/README.md+++ b/docs/pt-BR/README.md@@ -89,7 +89,7 @@ Este repositório contém apenas o código. Os guias explicam tudo.- **Revisão de orquestração** — Pontuação de auditoria de harness tornado determinístico, status de orquestração e compatibilidade de launcher reforçados, prevenção de loop de observer com guarda de 5 camadas.- **Confiabilidade do observer** — Correção de explosão de memória com throttling e tail sampling, correção de acesso sandbox, lógica de início preguiçoso e guarda de reentrância.- **12 ecossistemas de linguagem** — Novas regras para Java, PHP, Perl, Kotlin/Android/KMP, C++ e Rust se juntam ao TypeScript, Python, Go e regras comuns existentes.-- **Contribuições da comunidade** — Traduções para coreano e chinês, hook de segurança InsAIts, otimização de hook biome, skills VideoDB, skills operacionais Evos, instalador PowerShell, suporte ao IDE Antigravity.+- **Contribuições da comunidade** — Traduções para coreano e chinês, otimização de hook biome, skills VideoDB, skills operacionais Evos, instalador PowerShell, suporte ao IDE Antigravity.- **CI reforçado** — 19 correções de falhas de teste, aplicação de contagem de catálogo, validação de manifesto de instalação e suíte de testes completa no verde.### v1.8.0 — Sistema de Desempenho de Harness (Mar 2026)diff --git a/docs/zh-CN/README.md b/docs/zh-CN/README.mdindex 3ea2d83a3..851e9697e 100644--- a/docs/zh-CN/README.md+++ b/docs/zh-CN/README.md@@ -90,7 +90,7 @@* **编排系统大修** — 使治理审核评分具有确定性,强化编排状态和启动器兼容性,通过 5 层防护防止观察者循环。* **观察者可靠性** — 通过节流和尾部采样修复内存爆炸问题,修复沙箱访问,实现延迟启动逻辑,并增加重入防护。* **12 个语言生态系统** — 新增 Java、PHP、Perl、Kotlin/Android/KMP、C++ 和 Rust 规则,与现有的 TypeScript、Python、Go 及通用规则并列。-* **社区贡献** — 韩语和中文翻译,InsAIts 安全钩子,biome 钩子优化,VideoDB 技能,Evos 操作技能,PowerShell 安装程序,Antigravity IDE 支持。+* **社区贡献** — 韩语和中文翻译,biome 钩子优化,VideoDB 技能,Evos 操作技能,PowerShell 安装程序,Antigravity IDE 支持。* **CI 强化** — 修复 19 个测试失败问题,强制执行目录计数,验证安装清单,并使完整测试套件通过。### v1.8.0 — 平台性能系统(2026 年 3 月)diff --git a/docs/zh-CN/hooks/README.md b/docs/zh-CN/hooks/README.mdindex b7aa75b1c..0cfb571f6 100644--- a/docs/zh-CN/hooks/README.md+++ b/docs/zh-CN/hooks/README.md@@ -25,8 +25,6 @@| **Git 推送提醒器** | `Bash` | 在 `git push` 前提醒检查变更 | 0 (警告) || **文档文件警告器** | `Write` | 对非标准 `.md`/`.txt` 文件发出警告(允许 README、CLAUDE、CONTRIBUTING、CHANGELOG、LICENSE、SKILL、docs/、skills/);跨平台路径处理 | 0 (警告) || **策略性压缩提醒器** | `Edit\|Write` | 建议在逻辑间隔(约每 50 次工具调用)手动执行 `/compact` | 0 (警告) |-| **InsAIts 安全监控器(可选加入)** | `Bash\|Write\|Edit\|MultiEdit` | 对高信号工具输入的可选安全扫描。除非设置 `ECC_ENABLE_INSAITS=1`,否则禁用。对关键发现进行拦截,对非关键发现发出警告,并将审计日志写入 `.insaits_audit_session.jsonl`。需要 `pip install insa-its`。[详情](../../../scripts/hooks/insaits-security-monitor.py) | 2 (拦截关键) / 0 (警告) |-### PostToolUse 钩子| 钩子 | 匹配器 | 功能 |diff --git a/hooks/README.md b/hooks/README.mdindex a88c91bf4..bbdbed105 100644--- a/hooks/README.md+++ b/hooks/README.md@@ -26,8 +26,6 @@ User request → Claude picks a tool → PreToolUse hook runs → Tool executes| **Pre-commit quality check** | `Bash` | Runs quality checks before `git commit`: lints staged files, validates commit message format when provided via `-m/--message`, detects console.log/debugger/secrets | 2 (blocks critical) / 0 (warns) || **Doc file warning** | `Write` | Warns about non-standard `.md`/`.txt` files (allows README, CLAUDE, CONTRIBUTING, CHANGELOG, LICENSE, SKILL, docs/, skills/); cross-platform path handling | 0 (warns) || **Strategic compact** | `Edit\|Write` | Suggests manual `/compact` at logical intervals (every ~50 tool calls) | 0 (warns) |-| **InsAIts security monitor (opt-in)** | `Bash\|Write\|Edit\|MultiEdit` | Optional security scan for high-signal tool inputs. Disabled unless `ECC_ENABLE_INSAITS=1`. Blocks on critical findings, warns on non-critical, and writes audit log to `.insaits_audit_session.jsonl`. Requires `pip install insa-its`. [Details](../scripts/hooks/insaits-security-monitor.py) | 2 (blocks critical) / 0 (warns) |-### PostToolUse Hooks| Hook | Matcher | What It Does |diff --git a/hooks/hooks.json b/hooks/hooks.jsonindex c0a380373..3da90a22d 100644--- a/hooks/hooks.json+++ b/hooks/hooks.json@@ -92,18 +92,6 @@"description": "Capture tool use observations for continuous learning","id": "pre:observe:continuous-learning"},- {- "matcher": "Bash|Write|Edit|MultiEdit",- "hooks": [- {- "type": "command",- "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/hooks/run-with-flags.js\" \"pre:insaits-security\" \"scripts/hooks/insaits-security-wrapper.js\" \"standard,strict\"",- "timeout": 15- }- ],- "description": "Optional InsAIts AI security monitor for Bash/Edit/Write flows. Enable with ECC_ENABLE_INSAITS=1. Requires: pip install insa-its",- "id": "pre:insaits:security"- },{"matcher": "Bash|Write|Edit|MultiEdit","hooks": [diff --git a/mcp-configs/mcp-servers.json b/mcp-configs/mcp-servers.jsonindex d163d9375..03e2e2fb3 100644--- a/mcp-configs/mcp-servers.json+++ b/mcp-configs/mcp-servers.json@@ -104,11 +104,6 @@"args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/your/projects"],"description": "Filesystem operations (set your path)"},- "insaits": {- "command": "python3",- "args": ["-m", "insa_its.mcp_server"],- "description": "AI-to-AI security monitoring — anomaly detection, credential exposure, hallucination checks, forensic tracing. 23 anomaly types, OWASP MCP Top 10 coverage. 100% local. Install: pip install insa-its"- },"playwright": {"command": "npx","args": ["-y", "@playwright/mcp", "--browser", "chrome"],diff --git a/scripts/hooks/insaits-security-monitor.py b/scripts/hooks/insaits-security-monitor.pydeleted file mode 100644index da1bbf242..000000000--- a/scripts/hooks/insaits-security-monitor.py+++ /dev/null@@ -1,269 +0,0 @@-#!/usr/bin/env python3-"""-InsAIts Security Monitor -- PreToolUse Hook for Claude Code-============================================================--Real-time security monitoring for Claude Code tool inputs.-Detects credential exposure, prompt injection, behavioral anomalies,-hallucination chains, and 20+ other anomaly types -- runs 100% locally.--Writes audit events to .insaits_audit_session.jsonl for forensic tracing.--Setup:- pip install insa-its- export ECC_ENABLE_INSAITS=1-- Add to .claude/settings.json:- {- "hooks": {- "PreToolUse": [- {- "matcher": "Bash|Write|Edit|MultiEdit",- "hooks": [- {- "type": "command",- "command": "node scripts/hooks/insaits-security-wrapper.js"- }- ]- }- ]- }- }--How it works:- Claude Code passes tool input as JSON on stdin.- This script runs InsAIts anomaly detection on the content.- Exit code 0 = clean (pass through).- Exit code 2 = critical issue found (blocks tool execution).- Stderr output = non-blocking warning shown to Claude.--Environment variables:- INSAITS_DEV_MODE Set to "true" to enable dev mode (no API key needed).- Defaults to "false" (strict mode).- INSAITS_MODEL LLM model identifier for fingerprinting. Default: claude-opus.- INSAITS_FAIL_MODE "open" (default) = continue on SDK errors.- "closed" = block tool execution on SDK errors.- INSAITS_VERBOSE Set to any value to enable debug logging.--Detections include:- - Credential exposure (API keys, tokens, passwords)- - Prompt injection patterns- - Hallucination indicators (phantom citations, fact contradictions)- - Behavioral anomalies (context loss, semantic drift)- - Tool description divergence- - Shorthand emergence / jargon drift--All processing is local -- no data leaves your machine.--Author: Cristi Bogdan -- YuyAI (https://github.com/Nomadu27/InsAIts)-License: Apache 2.0-"""--from __future__ import annotations--import hashlib-import json-import logging-import os-import sys-import time-from typing import Any, Dict, List, Tuple--# Configure logging to stderr so it does not interfere with stdout protocol-logging.basicConfig(- stream=sys.stderr,- format="[InsAIts] %(message)s",- level=logging.DEBUG if os.environ.get("INSAITS_VERBOSE") else logging.WARNING,-)-log = logging.getLogger("insaits-hook")--# Try importing InsAIts SDK-try:- from insa_its import insAItsMonitor- INSAITS_AVAILABLE: bool = True-except ImportError:- INSAITS_AVAILABLE = False--# --- Constants ----AUDIT_FILE: str = ".insaits_audit_session.jsonl"-MIN_CONTENT_LENGTH: int = 10-MAX_SCAN_LENGTH: int = 4000-DEFAULT_MODEL: str = "claude-opus"-BLOCKING_SEVERITIES: frozenset = frozenset({"CRITICAL"})---def extract_content(data: Dict[str, Any]) -> Tuple[str, str]:- """Extract inspectable text from a Claude Code tool input payload.-- Returns:- A (text, context) tuple where *text* is the content to scan and- *context* is a short label for the audit log.- """- tool_name: str = data.get("tool_name", "")- tool_input: Dict[str, Any] = data.get("tool_input", {})-- text: str = ""- context: str = ""-- if tool_name in ("Write", "Edit", "MultiEdit"):- text = tool_input.get("content", "") or tool_input.get("new_string", "")- context = "file:" + str(tool_input.get("file_path", ""))[:80]- elif tool_name == "Bash":- # PreToolUse: the tool hasn't executed yet, inspect the command- command: str = str(tool_input.get("command", ""))- text = command- context = "bash:" + command[:80]- elif "content" in data:- content: Any = data["content"]- if isinstance(content, list):- text = "\n".join(- b.get("text", "") for b in content if b.get("type") == "text"- )- elif isinstance(content, str):- text = content- context = str(data.get("task", ""))-- return text, context---def write_audit(event: Dict[str, Any]) -> None:- """Append an audit event to the JSONL audit log.-- Creates a new dict to avoid mutating the caller's *event*.- """- try:- enriched: Dict[str, Any] = {- **event,- "timestamp": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),- }- enriched["hash"] = hashlib.sha256(- json.dumps(enriched, sort_keys=True).encode()- ).hexdigest()[:16]- with open(AUDIT_FILE, "a", encoding="utf-8") as f:- f.write(json.dumps(enriched) + "\n")- except OSError as exc:- log.warning("Failed to write audit log %s: %s", AUDIT_FILE, exc)---def get_anomaly_attr(anomaly: Any, key: str, default: str = "") -> str:- """Get a field from an anomaly that may be a dict or an object.-- The SDK's ``send_message()`` returns anomalies as dicts, while- other code paths may return dataclass/object instances. This- helper handles both transparently.- """- if isinstance(anomaly, dict):- return str(anomaly.get(key, default))- return str(getattr(anomaly, key, default))---def format_feedback(anomalies: List[Any]) -> str:- """Format detected anomalies as feedback for Claude Code.-- Returns:- A human-readable multi-line string describing each finding.- """- lines: List[str] = [- "== InsAIts Security Monitor -- Issues Detected ==",- "",- ]- for i, a in enumerate(anomalies, 1):- sev: str = get_anomaly_attr(a, "severity", "MEDIUM")- atype: str = get_anomaly_attr(a, "type", "UNKNOWN")- detail: str = get_anomaly_attr(a, "details", "")- lines.extend([- f"{i}. [{sev}] {atype}",- f" {detail[:120]}",- "",- ])- lines.extend([- "-" * 56,- "Fix the issues above before continuing.",- "Audit log: " + AUDIT_FILE,- ])- return "\n".join(lines)---def main() -> None:- """Entry point for the Claude Code PreToolUse hook."""- raw: str = sys.stdin.read().strip()- if not raw:- sys.exit(0)-- try:- data: Dict[str, Any] = json.loads(raw)- except json.JSONDecodeError:- data = {"content": raw}-- text, context = extract_content(data)-- # Skip very short content (e.g. "OK", empty bash results)- if len(text.strip()) < MIN_CONTENT_LENGTH:- sys.exit(0)-- if not INSAITS_AVAILABLE:- log.warning("Not installed. Run: pip install insa-its")- sys.exit(0)-- # Wrap SDK calls so an internal error does not crash the hook- try:- monitor: insAItsMonitor = insAItsMonitor(- session_name="claude-code-hook",- dev_mode=os.environ.get(- "INSAITS_DEV_MODE", "false"- ).lower() in ("1", "true", "yes"),- )- result: Dict[str, Any] = monitor.send_message(- text=text[:MAX_SCAN_LENGTH],- sender_id="claude-code",- llm_id=os.environ.get("INSAITS_MODEL", DEFAULT_MODEL),- )- except Exception as exc: # Broad catch intentional: unknown SDK internals- fail_mode: str = os.environ.get("INSAITS_FAIL_MODE", "open").lower()- if fail_mode == "closed":- sys.stdout.write(- f"InsAIts SDK error ({type(exc).__name__}); "- "blocking execution to avoid unscanned input.\n"- )- sys.exit(2)- log.warning(- "SDK error (%s), skipping security scan: %s",- type(exc).__name__, exc,- )- sys.exit(0)-- anomalies: List[Any] = result.get("anomalies", [])-- # Write audit event regardless of findings- write_audit({- "tool": data.get("tool_name", "unknown"),- "context": context,- "anomaly_count": len(anomalies),- "anomaly_types": [get_anomaly_attr(a, "type") for a in anomalies],- "text_length": len(text),- })-- if not anomalies:- log.debug("Clean -- no anomalies detected.")- sys.exit(0)-- # Determine maximum severity- has_critical: bool = any(- get_anomaly_attr(a, "severity").upper() in BLOCKING_SEVERITIES- for a in anomalies- )-- feedback: str = format_feedback(anomalies)-- if has_critical:- # stdout feedback -> Claude Code shows to the model- sys.stdout.write(feedback + "\n")- sys.exit(2) # PreToolUse exit 2 = block tool execution- else:- # Non-critical: warn via stderr (non-blocking)- log.warning("\n%s", feedback)- sys.exit(0)---if __name__ == "__main__":- main()diff --git a/scripts/hooks/insaits-security-wrapper.js b/scripts/hooks/insaits-security-wrapper.jsdeleted file mode 100644index 9f3e46d83..000000000--- a/scripts/hooks/insaits-security-wrapper.js+++ /dev/null@@ -1,88 +0,0 @@-#!/usr/bin/env node-/**- * InsAIts Security Monitor — wrapper for run-with-flags compatibility.- *- * This thin wrapper receives stdin from the hooks infrastructure and- * delegates to the Python-based insaits-security-monitor.py script.- *- * The wrapper exists because run-with-flags.js spawns child scripts- * via `node`, so a JS entry point is needed to bridge to Python.- */--'use strict';--const path = require('path');-const { spawnSync } = require('child_process');--const MAX_STDIN = 1024 * 1024;--function isEnabled(value) {- return ['1', 'true', 'yes', 'on'].includes(String(value || '').toLowerCase());-}--let raw = '';-process.stdin.setEncoding('utf8');-process.stdin.on('data', chunk => {- if (raw.length < MAX_STDIN) {- raw += chunk.substring(0, MAX_STDIN - raw.length);- }-});--process.stdin.on('end', () => {- if (!isEnabled(process.env.ECC_ENABLE_INSAITS)) {- process.stdout.write(raw);- process.exit(0);- }-- const scriptDir = __dirname;- const pyScript = path.join(scriptDir, 'insaits-security-monitor.py');-- // Try python3 first (macOS/Linux), fall back to python (Windows)- const pythonCandidates = ['python3', 'python'];- let result;-- for (const pythonBin of pythonCandidates) {- result = spawnSync(pythonBin, [pyScript], {- input: raw,- encoding: 'utf8',- env: process.env,- cwd: process.cwd(),- timeout: 14000,- });-- // ENOENT means binary not found — try next candidate- if (result.error && result.error.code === 'ENOENT') {- continue;- }- break;- }-- if (!result || (result.error && result.error.code === 'ENOENT')) {- process.stderr.write('[InsAIts] python3/python not found. Install Python 3.9+ and: pip install insa-its\n');- process.stdout.write(raw);- process.exit(0);- }-- // Log non-ENOENT spawn errors (timeout, signal kill, etc.) so users- // know the security monitor did not run — fail-open with a warning.- if (result.error) {- process.stderr.write(`[InsAIts] Security monitor failed to run: ${result.error.message}\n`);- process.stdout.write(raw);- process.exit(0);- }-- // result.status is null when the process was killed by a signal or- // timed out. Check BEFORE writing stdout to avoid leaking partial- // or corrupt monitor output. Pass through original raw input instead.- if (!Number.isInteger(result.status)) {- const signal = result.signal || 'unknown';- process.stderr.write(`[InsAIts] Security monitor killed (signal: ${signal}). Tool execution continues.\n`);- process.stdout.write(raw);- process.exit(0);- }-- if (result.stdout) process.stdout.write(result.stdout);- if (result.stderr) process.stderr.write(result.stderr);-- process.exit(result.status);-});diff --git a/tests/hooks/hooks.test.js b/tests/hooks/hooks.test.jsindex 2a526b38c..20c524878 100644--- a/tests/hooks/hooks.test.js+++ b/tests/hooks/hooks.test.js@@ -527,24 +527,6 @@ async function runTests() {passed++;else failed++;- // insaits-security-wrapper.js tests- console.log('\ninsaits-security-wrapper.js:');-- if (- await asyncTest('passes through input unchanged when integration is disabled', async () => {- const stdinData = JSON.stringify({- tool_name: 'Write',- tool_input: { file_path: 'src/index.ts', content: 'console.log("ok");' }- });- const result = await runScript(path.join(scriptsDir, 'insaits-security-wrapper.js'), stdinData, { ECC_ENABLE_INSAITS: '' });- assert.strictEqual(result.code, 0, `Exit code should be 0, got ${result.code}`);- assert.strictEqual(result.stdout, stdinData, 'Should pass stdin through unchanged');- assert.strictEqual(result.stderr, '', 'Should stay silent when integration is disabled');- })- )- passed++;- else failed++;-// check-console-log.js testsconsole.log('\ncheck-console-log.js:');@@ -2025,20 +2007,6 @@ async function runTests() {passed++;else failed++;- if (- test('InsAIts hook is opt-in and scoped to high-signal tool inputs', () => {- const hooksPath = path.join(__dirname, '..', '..', 'hooks', 'hooks.json');- const hooks = JSON.parse(fs.readFileSync(hooksPath, 'utf8'));- const insaitsHook = hooks.hooks.PreToolUse.find(entry => entry.description && entry.description.includes('InsAIts'));-- assert.ok(insaitsHook, 'Should define an InsAIts PreToolUse hook');- assert.strictEqual(insaitsHook.matcher, 'Bash|Write|Edit|MultiEdit', 'InsAIts hook should avoid matching every tool');- assert.ok(insaitsHook.description.includes('ECC_ENABLE_INSAITS=1'), 'InsAIts hook should document explicit opt-in');- assert.ok(insaitsHook.hooks[0].command.includes('insaits-security-wrapper.js'), 'InsAIts hook should execute through the JS wrapper');- })- )- passed++;- else failed++;// plugin.json validationconsole.log('\nplugin.json Validation:');