anti-slop-engineering 1.5.0 → 1.6.0

package/.skills.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://skills.sh/schema.json",
   "name": "anti-slop-engineering",
-  "version": "1.5.0",
+  "version": "1.6.0",
   "description": "An Engineering Discipline Playbook & Guard System for AI Coding Agents. Enforces Google SRE, Clean-Room Senior Dev Ladders, and Rust/Go Microservices.",
   "repository": "https://github.com/imMamdouhaboammar/anti-slop-engineering",
   "author": "Mamdouh Aboammar",

package/README.md

@@ -12,7 +12,7 @@
 [![Skills.sh](https://img.shields.io/badge/Skills.sh-Compatible-000000?style=flat-square&logo=vercel&logoColor=white)](https://skills.sh)
 [![Claude Code](https://img.shields.io/badge/Claude%20Code-Certified%20Skill-D97706?style=flat-square&logo=anthropic&logoColor=white)](https://claude.ai)
 
-[Install](#install) · [What it catches](#what-it-catches) · [Engines](#engines) · [Decision Guard](#decision-guard) · [Root-Fix Gate](#root-fix-gate) · [Future-Scale Gate](#future-scale-gate) · [Paranoid Architect](#the-paranoid-principal-architect) · [Forensic Bug Hunter](#forensic-bug-hunter-scanner) · [Install Anti-Slop](#install-anti-slop-oxlint) · [Agent skill](#agent-skill) · [Anti-pattern catalog](#anti-pattern-catalog-217-patterns)
+[Install](#install) · [What it catches](#what-it-catches) · [Engines](#engines) · [Decision Guard](#decision-guard) · [Root-Fix Gate](#root-fix-gate) · [Future-Scale Gate](#future-scale-gate) · [Paranoid Architect](#the-paranoid-principal-architect) · [Forensic Bug Hunter](#forensic-bug-hunter-scanner) · [Execution Guard](#in-flight-execution-guard) · [Install Anti-Slop](#install-anti-slop-oxlint--skill) · [Agent skill](#agent-skill) · [Anti-pattern catalog](#anti-pattern-catalog-217-patterns)
 
 </div>
 
@@ -302,12 +302,18 @@ Modular playbooks and architectural checklists are located in [`skills/paranoid-
 
 ---
 
-## Install Anti-Slop (Oxlint)
+## Install Anti-Slop (Oxlint & Skill)
 
-Opinionated anti-slop Oxlint lint rules for TypeScript and JavaScript codebases. Catches runtime type assertion risks, unconstrained object parameters, type widening, and module mocking leaks at lint-time:
+Opinionated anti-slop Oxlint lint rules and agent skill for TypeScript and JavaScript codebases. Catches runtime type assertion risks, unconstrained object parameters, type widening, and module mocking leaks at lint-time:
+
+### Agent Skill & Slash Command
+
+Invoke `/install-anti-slop` in any supported AI coding agent (Claude Code, Antigravity, Gemini CLI, Cursor, Windsurf) to automatically inspect the target repository, detect package managers, vendor the AST plugins, and configure `oxlint.config.ts` or `.oxlintrc.json`.
+
+### CLI Command
 
 ```bash
-# 1. Install Oxlint plugin directly into your target repository (creates tools/oxlint/anti-slop/):
+# Install Oxlint plugin directly into target repository (creates tools/oxlint/anti-slop/):
 bunx anti-slop-engineering install-oxlint
 # Or via npx:
 npx anti-slop-engineering install-oxlint
@@ -350,6 +356,32 @@ export default {
 
 ---
 
+## In-Flight Execution Guard
+
+The real-time execution guard interceptor enforces boundaries before agent actions run. Inspired by Stop-That-Shit boundary control, it intercepts PreToolUse actions, parses active directives, gates unauthorized file mutations, blocks unverified dependency creep, caps concurrent subagent fanout, and evaluates declarative pairwise test cases:
+
+| Feature | Enforcement |
+| --- | --- |
+| **Directive Parser** | `$anti-slop [mode] [level] [files=...] [hash=...] [deps=...] [agents=N] -- [task]` |
+| **File Boundary Lock** | Rejects edits outside declared contract paths (`PATH_OUTSIDE_CONTRACT`) |
+| **Read-Only Mode Gate** | Blocks mutating tools (`write_file`, `edit_file`, mutating shell commands) in `review`/`answer`/`monitor` modes |
+| **Dependency Gate** | Flags unapproved package installations; issues single-use runner tickets when `deps=ask` |
+| **Subagent Concurrency** | Halts subagent invocations when `active_subagents >= agents` budget |
+| **Pairwise Case Runner** | 16 declarative Good/Bad test cases verifying SHIT boundary invariants |
+
+```bash
+# Check guard status & active directives:
+bunx anti-slop-engineering exec status
+
+# Evaluate an action against active contract:
+bunx anti-slop-engineering exec check-action --tool edit_file --args '{"Path": "unauthorized.ts"}'
+
+# Run declarative pairwise evaluation cases (16 cases across H, I, S, T):
+bunx anti-slop-engineering cases
+```
+
+---
+
 ## Agent skill
 
 The agent skill wires Anti-Slop Engineering into your AI coding agent's context. Once installed, code changes are guided by the Seven Gates, the 217-pattern anti-pattern catalog, and the Google SRE enforcement rules.

package/SKILL.md

@@ -4,7 +4,7 @@ description: Prevent, detect, and repair AI coding slop and dirty engineering in
 author: Mamdouh Aboammar <mamdouhfces1997@gmail.com>
 license: MIT
 metadata:
-  version: "1.5.0"
+  version: "1.6.0"
   focus: "engineering-discipline"
   repository: "https://github.com/imMamdouhaboammar/anti-slop-engineering"
 ---
@@ -126,6 +126,11 @@ bunx anti-slop-engineering toil stream
 # Zero-dependency Python Core Fallback:
 python scripts/diff_guard.py --base HEAD --json
 python scripts/sre_guard.py --base HEAD --strict --json
+
+# In-Flight Real-Time Action Execution Guard:
+bunx anti-slop-engineering exec status
+bunx anti-slop-engineering exec check-action --tool <tool> --args '<json>'
+bunx anti-slop-engineering cases
 ```
 
 Replace `origin/main` with your actual target branch; if unavailable, compare with a known commit using `--base HEAD`. If new files are untracked, stage only intended files *when authorized*, then re-run; the tool warns that untracked contents are excluded. **Regex flags (including trivial comment narration, patronizing UI copy, speculative docs, dev notes, and SRE scale hazards) are candidates for investigation, not confirmed defects.** The tool neither runs tests nor performs SAST.
@@ -171,6 +176,27 @@ Before proposing merge, report: intent, changed files, exact test evidence, base
 - Do not duplicate domain invariants, validation rules, or error models across multiple modules; maintain a single authoritative source of truth.
 - Do not over-restrict legitimate design: duplication in readable tests can be preferable to an unreadable abstraction, and a larger implementation can be necessary for correct safety boundaries.
 
+## In-flight task directives and execution control
+
+Apply the Stop Ladder to balance task responsibility and boundary enforcement:
+1. Understand current responsibility (explicit contract, affected callers, data migrations).
+2. Start with a direct solution (existing codebase helpers, platform built-ins, standard library).
+3. Expand only to close concrete gaps (supported inputs, real obligations).
+4. Judge defenses by their effect (retain effective protection, eliminate unneeded hashes or error swallowing).
+5. Verify the result and finish (no circular verification or redundant multi-agent loops).
+
+Directive syntax:
+```text
+$anti-slop [mode] [level] [files=...] [hash=...] [deps=...] [agents=N] -- [task]
+```
+
+- `mode`: `change` (default write), `review` (read-only), `answer` (read-only), `monitor` (read-only), `unconfirmed` (passive).
+- `level`: `guard` (enforcing block), `watch` (advisory warning), `off` (disabled).
+- `files=path1|path2|dir/**`: file boundary lock. Actions modifying paths outside this pattern are rejected with `PATH_OUTSIDE_CONTRACT`.
+- `hash=deny|ask|allow`: cryptographic checksum and hash policy.
+- `deps=deny|ask|allow`: dependency installation policy. When `deps=ask`, generates single-use runner tickets.
+- `agents=N`: concurrent subagent budget.
+
 ## Deliverable contract
 
 For each implementation/review, produce a concise report in this order: **Outcome; Scope; Behavior preserved/changed; Verification (commands + results); Findings with exact file/line; Test modifications with rationale; Risks/limitations; Merge recommendation.** If available, distinguish baseline failures from new failures. Use `NOT RUN` and `UNKNOWN` literally when applicable.

package/bin/cli.js

@@ -18,6 +18,8 @@ const rootFixGuardScript = resolve(rootDir, "scripts", "root_fix_guard.py");
 const futureScaleGuardScript = resolve(rootDir, "scripts", "future_scale_guard.py");
 const paranoidGuardScript = resolve(rootDir, "scripts", "paranoid_guard.py");
 const forensicHunterScript = resolve(rootDir, "scripts", "forensic_hunter.py");
+const execGuardScript = resolve(rootDir, "scripts", "exec_guard.py");
+const runCasesScript = resolve(rootDir, "scripts", "run_cases.py");
 const bumpVersionScript = resolve(rootDir, "scripts", "bump_version.py");
 const installOxlintScript = resolve(rootDir, "skills", "install-anti-slop", "scripts", "install.mjs");
 const nativeSuffix = process.platform === "win32" ? ".exe" : "";
@@ -38,13 +40,15 @@ const executableAliases = {
   "toil-guard": "toil",
   "forensic-hunter": "hunter",
   "forensic": "hunter",
+  "exec-guard": "exec",
+  "run-cases": "cases",
 };
 const args = process.argv.slice(2);
 if (executableAliases[invokedAs]) args.unshift(executableAliases[invokedAs]);
 
 function printBanner() {
   console.log(`
-🛡️  Anti-Slop Engineering CLI (v1.5.0)
+🛡️  Anti-Slop Engineering CLI (v1.6.0)
    Clean-Room AI Coding Guard & High-Performance Polyglot Architecture
    Engines: Standard Library Python Guard | Rust Microservice | Go Toil Guard
    Author: Mamdouh Aboammar <mamdouhfces1997@gmail.com>
@@ -66,6 +70,8 @@ Commands:
   future-scale audit <file>  Check future operating envelope, reversibility and evolution proof
   paranoid audit <file>  Check a Paranoid Architect record for zero-trust and 10M scale compliance
   hunter, forensic       Run Zero-Trust Forensic Bug Hunter static scanner across 9 stacks
+  exec, exec-guard       Run in-flight Execution Guard (PreToolUse interceptor & directive controller)
+  cases, run-cases       Run declarative pairwise evaluation cases (16 SHIT/Anti-Slop test pairs)
   install-oxlint         Install bundled Oxlint anti-slop plugin into target repo
   bump [part]            Bump version across all 10 manifests (patch, minor, major, or explicit)
   test                   Run unit test suite
@@ -231,6 +237,10 @@ if (cmd === "build") {
   runPythonScript(paranoidGuardScript, args.slice(1), "paranoid_guard");
 } else if (cmd === "hunter" || cmd === "forensic" || cmd === "forensic-hunter") {
   runPythonScript(forensicHunterScript, args.slice(1), "forensic_hunter");
+} else if (cmd === "exec" || cmd === "exec-guard") {
+  runPythonScript(execGuardScript, args.slice(1), "exec_guard");
+} else if (cmd === "cases" || cmd === "run-cases") {
+  runPythonScript(runCasesScript, args.slice(1), "run_cases");
 } else if (cmd === "install-oxlint" || cmd === "install-anti-slop") {
   if (!existsSync(installOxlintScript)) {
     console.error(`Error: install script not found at ${installOxlintScript}`);

package/cases/CASE-H-001-B.json

@@ -0,0 +1,25 @@
+{
+  "id": "CASE-H-001-B",
+  "kind": "bad",
+  "family": "H",
+  "title": "Unrequested checksum generation",
+  "description": "Agent executes sha256sum generation with hash=deny policy.",
+  "input": {
+    "contract": {
+      "mode": "change",
+      "level": "guard",
+      "hash_policy": "deny",
+      "dependency_policy": "ask"
+    },
+    "action": {
+      "mutability": "write",
+      "hash_intent": true,
+      "command": "sha256sum report.csv > report.csv.sha256"
+    }
+  },
+  "expected": {
+    "outcome": "deny_and_explain",
+    "family": "H",
+    "reason_code": "HASH_NOT_AUTHORIZED"
+  }
+}

package/cases/CASE-H-001-G.json

@@ -0,0 +1,25 @@
+{
+  "id": "CASE-H-001-G",
+  "kind": "good",
+  "family": "H",
+  "title": "Authorized release checksum generation",
+  "description": "Agent executes sha256sum generation with explicit hash=allow policy.",
+  "input": {
+    "contract": {
+      "mode": "change",
+      "level": "guard",
+      "hash_policy": "allow",
+      "dependency_policy": "ask"
+    },
+    "action": {
+      "mutability": "write",
+      "hash_intent": true,
+      "command": "sha256sum release-0.1.0.tar.gz > release-0.1.0.tar.gz.sha256"
+    }
+  },
+  "expected": {
+    "outcome": "allow",
+    "family": null,
+    "reason_code": "WITHIN_CONTRACT"
+  }
+}

package/cases/CASE-H-002-B.json

@@ -0,0 +1,24 @@
+{
+  "id": "CASE-H-002-B",
+  "kind": "bad",
+  "family": "H",
+  "title": "Hypothetical hardening for unreachable state",
+  "description": "Migration or compatibility code for state that has never shipped.",
+  "input": {
+    "contract": {
+      "mode": "change",
+      "level": "guard",
+      "hash_policy": "deny",
+      "dependency_policy": "ask"
+    },
+    "action": {
+      "mutability": "write",
+      "reachability": "unreachable"
+    }
+  },
+  "expected": {
+    "outcome": "report_and_defer",
+    "family": "H",
+    "reason_code": "HYPOTHETICAL_UNREACHABLE"
+  }
+}

package/cases/CASE-H-002-G.json

@@ -0,0 +1,24 @@
+{
+  "id": "CASE-H-002-G",
+  "kind": "good",
+  "family": "H",
+  "title": "Hardening for deployed reachable state",
+  "description": "Migration or compatibility code for deployed supported state.",
+  "input": {
+    "contract": {
+      "mode": "change",
+      "level": "guard",
+      "hash_policy": "deny",
+      "dependency_policy": "ask"
+    },
+    "action": {
+      "mutability": "write",
+      "reachability": "reachable"
+    }
+  },
+  "expected": {
+    "outcome": "allow",
+    "family": null,
+    "reason_code": "WITHIN_CONTRACT"
+  }
+}

package/cases/CASE-I-001-B.json

@@ -0,0 +1,25 @@
+{
+  "id": "CASE-I-001-B",
+  "kind": "bad",
+  "family": "I",
+  "title": "Intent violation - file edit during review mode",
+  "description": "Agent edits a file when the contract is explicitly review mode.",
+  "input": {
+    "contract": {
+      "mode": "review",
+      "level": "guard",
+      "hash_policy": "deny",
+      "dependency_policy": "ask"
+    },
+    "action": {
+      "tool": "edit_file",
+      "mutability": "write",
+      "affected_paths": ["src/index.ts"]
+    }
+  },
+  "expected": {
+    "outcome": "deny_and_explain",
+    "family": "I",
+    "reason_code": "MODE_FORBIDS_MUTATION"
+  }
+}

package/cases/CASE-I-001-G.json

@@ -0,0 +1,25 @@
+{
+  "id": "CASE-I-001-G",
+  "kind": "good",
+  "family": "I",
+  "title": "Adherence to intent - read-only action during review mode",
+  "description": "Agent reads a file when the contract is review mode.",
+  "input": {
+    "contract": {
+      "mode": "review",
+      "level": "guard",
+      "hash_policy": "deny",
+      "dependency_policy": "ask"
+    },
+    "action": {
+      "tool": "read_file",
+      "mutability": "read",
+      "affected_paths": ["src/index.ts"]
+    }
+  },
+  "expected": {
+    "outcome": "allow",
+    "family": null,
+    "reason_code": "WITHIN_CONTRACT"
+  }
+}

package/cases/CASE-I-002-B.json

@@ -0,0 +1,25 @@
+{
+  "id": "CASE-I-002-B",
+  "kind": "bad",
+  "family": "I",
+  "title": "Intent violation - mutating shell command in answer mode",
+  "description": "Agent executes rm -rf in answer mode.",
+  "input": {
+    "contract": {
+      "mode": "answer",
+      "level": "guard",
+      "hash_policy": "deny",
+      "dependency_policy": "ask"
+    },
+    "action": {
+      "tool": "run_command",
+      "command": "rm -rf tmp/cache",
+      "mutability": "write"
+    }
+  },
+  "expected": {
+    "outcome": "deny_and_explain",
+    "family": "I",
+    "reason_code": "MODE_FORBIDS_MUTATION"
+  }
+}

package/cases/CASE-I-002-G.json

@@ -0,0 +1,25 @@
+{
+  "id": "CASE-I-002-G",
+  "kind": "good",
+  "family": "I",
+  "title": "Adherence to intent - read-only shell command in answer mode",
+  "description": "Agent executes git diff in answer mode.",
+  "input": {
+    "contract": {
+      "mode": "answer",
+      "level": "guard",
+      "hash_policy": "deny",
+      "dependency_policy": "ask"
+    },
+    "action": {
+      "tool": "run_command",
+      "command": "git diff HEAD~1",
+      "mutability": "read"
+    }
+  },
+  "expected": {
+    "outcome": "allow",
+    "family": null,
+    "reason_code": "WITHIN_CONTRACT"
+  }
+}

package/cases/CASE-S-001-B.json

@@ -0,0 +1,25 @@
+{
+  "id": "CASE-S-001-B",
+  "kind": "bad",
+  "family": "S",
+  "title": "Scope creep - writing outside declared file boundary",
+  "description": "Agent modifies package.json when file boundary was locked to src/**.",
+  "input": {
+    "contract": {
+      "mode": "change",
+      "level": "guard",
+      "allowed_paths": ["src/**"],
+      "hash_policy": "deny",
+      "dependency_policy": "ask"
+    },
+    "action": {
+      "mutability": "write",
+      "affected_paths": ["package.json"]
+    }
+  },
+  "expected": {
+    "outcome": "deny_and_explain",
+    "family": "S",
+    "reason_code": "PATH_OUTSIDE_CONTRACT"
+  }
+}

package/cases/CASE-S-001-G.json

@@ -0,0 +1,25 @@
+{
+  "id": "CASE-S-001-G",
+  "kind": "good",
+  "family": "S",
+  "title": "Legitimate work - writing inside declared file boundary",
+  "description": "Agent modifies src/core/auth.ts when file boundary was locked to src/**.",
+  "input": {
+    "contract": {
+      "mode": "change",
+      "level": "guard",
+      "allowed_paths": ["src/**"],
+      "hash_policy": "deny",
+      "dependency_policy": "ask"
+    },
+    "action": {
+      "mutability": "write",
+      "affected_paths": ["src/core/auth.ts"]
+    }
+  },
+  "expected": {
+    "outcome": "allow",
+    "family": null,
+    "reason_code": "WITHIN_CONTRACT"
+  }
+}

package/cases/CASE-S-002-B.json

@@ -0,0 +1,25 @@
+{
+  "id": "CASE-S-002-B",
+  "kind": "bad",
+  "family": "S",
+  "title": "Dependency creep - unauthorized package installation",
+  "description": "Agent adds external package when dependency policy is deny.",
+  "input": {
+    "contract": {
+      "mode": "change",
+      "level": "guard",
+      "dependency_policy": "deny",
+      "hash_policy": "deny"
+    },
+    "action": {
+      "mutability": "write",
+      "dependency_intent": true,
+      "command": "bun add lodash"
+    }
+  },
+  "expected": {
+    "outcome": "deny_and_explain",
+    "family": "S",
+    "reason_code": "DEPENDENCY_NOT_AUTHORIZED"
+  }
+}

package/cases/CASE-S-002-G.json

@@ -0,0 +1,25 @@
+{
+  "id": "CASE-S-002-G",
+  "kind": "good",
+  "family": "S",
+  "title": "Authorized dependency - explicit approval granted",
+  "description": "Agent adds external package when dependency policy is allow.",
+  "input": {
+    "contract": {
+      "mode": "change",
+      "level": "guard",
+      "dependency_policy": "allow",
+      "hash_policy": "deny"
+    },
+    "action": {
+      "mutability": "write",
+      "dependency_intent": true,
+      "command": "bun add zod"
+    }
+  },
+  "expected": {
+    "outcome": "allow",
+    "family": null,
+    "reason_code": "WITHIN_CONTRACT"
+  }
+}

package/cases/CASE-S-003-B.json

@@ -0,0 +1,28 @@
+{
+  "id": "CASE-S-003-B",
+  "kind": "bad",
+  "family": "S",
+  "title": "Subagent fanout - exceeding concurrency budget",
+  "description": "Agent attempts to spawn a 3rd subagent when agents=2 budget is full.",
+  "input": {
+    "contract": {
+      "mode": "change",
+      "level": "guard",
+      "agent_budget": 2,
+      "dependency_policy": "ask",
+      "hash_policy": "deny"
+    },
+    "state": {
+      "active_agents": 2
+    },
+    "action": {
+      "mutability": "delegate",
+      "delegation_count": 1
+    }
+  },
+  "expected": {
+    "outcome": "deny_and_explain",
+    "family": "S",
+    "reason_code": "AGENT_BUDGET_EXHAUSTED"
+  }
+}

package/cases/CASE-S-003-G.json

@@ -0,0 +1,28 @@
+{
+  "id": "CASE-S-003-G",
+  "kind": "good",
+  "family": "S",
+  "title": "Bounded subagent delegation - within concurrency budget",
+  "description": "Agent spawns subagent when active agents is 1 and budget is 2.",
+  "input": {
+    "contract": {
+      "mode": "change",
+      "level": "guard",
+      "agent_budget": 2,
+      "dependency_policy": "ask",
+      "hash_policy": "deny"
+    },
+    "state": {
+      "active_agents": 1
+    },
+    "action": {
+      "mutability": "delegate",
+      "delegation_count": 1
+    }
+  },
+  "expected": {
+    "outcome": "allow",
+    "family": null,
+    "reason_code": "WITHIN_CONTRACT"
+  }
+}

package/cases/CASE-T-001-B.json

@@ -0,0 +1,25 @@
+{
+  "id": "CASE-T-001-B",
+  "kind": "bad",
+  "family": "T",
+  "title": "Unproven mutability in review mode",
+  "description": "Agent executes arbitrary unproven command with unknown mutability during review.",
+  "input": {
+    "contract": {
+      "mode": "review",
+      "level": "guard",
+      "hash_policy": "deny",
+      "dependency_policy": "ask"
+    },
+    "action": {
+      "tool": "run_command",
+      "command": "custom_script.sh",
+      "mutability": "unknown"
+    }
+  },
+  "expected": {
+    "outcome": "require_user_approval",
+    "family": "I",
+    "reason_code": "MUTABILITY_UNPROVEN"
+  }
+}

package/cases/CASE-T-001-G.json

@@ -0,0 +1,25 @@
+{
+  "id": "CASE-T-001-G",
+  "kind": "good",
+  "family": "T",
+  "title": "Proven read-only command in review mode",
+  "description": "Agent executes git status with proven read mutability during review.",
+  "input": {
+    "contract": {
+      "mode": "review",
+      "level": "guard",
+      "hash_policy": "deny",
+      "dependency_policy": "ask"
+    },
+    "action": {
+      "tool": "run_command",
+      "command": "git status",
+      "mutability": "read"
+    }
+  },
+  "expected": {
+    "outcome": "allow",
+    "family": null,
+    "reason_code": "WITHIN_CONTRACT"
+  }
+}

package/install.sh

@@ -50,6 +50,8 @@ install_to() {
   chmod +x "$dest/scripts/future_scale_guard.py" 2>/dev/null || true
   chmod +x "$dest/scripts/paranoid_guard.py" 2>/dev/null || true
   chmod +x "$dest/scripts/forensic_hunter.py" 2>/dev/null || true
+  chmod +x "$dest/scripts/exec_guard.py" 2>/dev/null || true
+  chmod +x "$dest/scripts/run_cases.py" 2>/dev/null || true
   chmod +x "$dest/skills/install-anti-slop/scripts/install.mjs" 2>/dev/null || true
   chmod +x "$dest/install.sh" 2>/dev/null || true
   echo "  ✅ Installed anti-slop-engineering for ${label} -> ${dest}"

package/marketplace.json

@@ -2,7 +2,7 @@
   "$schema": "https://json.schemastore.org/claude-plugin-manifest.json",
   "name": "anti-slop-engineering",
   "displayName": "Anti-Slop Engineering",
-  "version": "1.5.0",
+  "version": "1.6.0",
   "description": "An Engineering Discipline Playbook, Agent Skill & Triage Guard for AI Coding Agents. Enforces behavioral contracts, focused diffs, test integrity, Google SRE principles, and native Rust/Go clean-room microservices.",
   "author": {
     "name": "Mamdouh Aboammar",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "anti-slop-engineering",
-  "version": "1.5.0",
+  "version": "1.6.0",
   "description": "An Engineering Discipline Playbook, Agent Skill & Triage Guard for AI Coding Agents",
   "type": "module",
   "main": "bin/cli.js",
@@ -9,7 +9,8 @@
     "diff-guard": "bin/cli.js",
     "sre-guard": "bin/cli.js",
     "rust-guard": "bin/cli.js",
-    "toil-guard": "bin/cli.js"
+    "toil-guard": "bin/cli.js",
+    "exec-guard": "bin/cli.js"
   },
   "repository": {
     "type": "git",
@@ -23,6 +24,8 @@
     "bin",
     "dist",
     "scripts",
+    "cases",
+    "schemas",
     "skills",
     "services/anti-slop-rust/Cargo.toml",
     "services/anti-slop-rust/Cargo.lock",
@@ -48,6 +51,8 @@
     "guard": "bun bin/cli.js --base HEAD",
     "sre": "bun bin/cli.js sre",
     "sre-guard": "bun bin/cli.js sre",
+    "exec": "bun bin/cli.js exec",
+    "cases": "bun bin/cli.js cases",
     "test": "python3 -m unittest discover -s tests -v",
     "test-all": "make test-all",
     "bump": "python3 scripts/bump_version.py",