{ "markdown": "

\n \"AgentOps\n

\n\n# AgentOps — Enterprise Guardrails & Delivery Lifecycle for Claude Code\n\nA plugin for [Claude Code CLI](https://docs.anthropic.com/en/docs/claude-code) that wraps every session in 7 security layers, structures work with the STAR methodology, auto-pilots workflows, delegates to 12 specialist agents, learns from failures via self-evolution, and orchestrates full project builds from vision to merged PR.\n\n40 slash commands | 44 hooks | 12 specialist agents | 49 templates | 33+ feature flags | real-time 3D dashboard\n\n[![Tests](https://github.com/garethdaine/agentops/actions/workflows/tests.yml/badge.svg?branch=main)](https://github.com/garethdaine/agentops/actions/workflows/tests.yml)\n[![Lint](https://github.com/garethdaine/agentops/actions/workflows/lint.yml/badge.svg?branch=main)](https://github.com/garethdaine/agentops/actions/workflows/lint.yml)\n[![Security](https://github.com/garethdaine/agentops/actions/workflows/security.yml/badge.svg?branch=main)](https://github.com/garethdaine/agentops/actions/workflows/security.yml)\n[![npm version](https://img.shields.io/npm/v/@garethdaine/agentops)](https://www.npmjs.com/package/@garethdaine/agentops)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)\n\n---\n\n## Quick Start\n\n### Install via npm\n\n```bash\nnpm install -g @garethdaine/agentops\n\n# Run Claude Code with the plugin loaded\nclaude --plugin-dir $(npm root -g)/@garethdaine/agentops\n```\n\n### Or clone from GitHub\n\n```bash\ngit clone https://github.com/garethdaine/agentops.git agentops-plugin\n\nclaude --plugin-dir ./agentops-plugin\n```\n\nOn first session, the plugin auto-initializes `.agentops/` with default flags and budget.\n\n---\n\n## AgentOps vs GSD vs Superpowers\n\n| Dimension | AgentOps | GSD (~31K stars) | Superpowers (~50K stars) |\n|-----------|----------|-------------------|--------------------------|\n| **Core identity** | Enterprise guardrailing + full delivery lifecycle | Spec-driven meta-prompting to beat context rot | Skills-based methodology with TDD enforcement |\n| **Commands** | 40 | ~15 | ~10 (skill-based) |\n| **Hooks** | 44 shell scripts across 7 lifecycle events | None (prompts only) | None (prompts only) |\n| **Agents** | 12 specialist agents | 4 parallel researchers + planner | Code reviewer agent |\n| **Security** | 7 layers (injection, exfiltration, supply-chain, Unicode, credential, path, env) | Minimal | None |\n| **Self-evolution** | EvoSkill (failures → proposer → skill-builder → feedback loop) | KNOWLEDGE.md (manual) | Skill extraction (manual) |\n| **TDD enforcement** | Mandatory RED→GREEN→REFACTOR + Nyquist rule (``/``/`` on every task); auto-test hook in sessions | Nyquist rule (verify required) | Code without tests = deleted |\n| **Context strategy** | Fresh subagent per task (build_fresh_context) + session hooks | Fresh 200K context per subagent | Fresh context per subagent |\n| **Parallel execution** | Wave-based with dependency graphs + 4 parallel researchers | Wave-based parallel execution | N/A |\n| **Persuasion psychology** | 5 Cialdini techniques embedded in human gates | None | 5 Cialdini techniques |\n| **Plan format** | STAR markdown + XML with Nyquist compliance (//) | XML executable plans | Markdown plans |\n| **Git workflow** | Configurable strategy (worktree / feature-branch / trunk-based); atomic commits per task, conventional commit format | Atomic commits, worktrees | Worktrees, atomic commits |\n| **Review** | Two-stage: spec compliance (requirements mapping) + code quality (11 dimensions) | N/A | Two-stage review |\n| **Feature flags** | 32+ independently toggleable with presets | Minimal settings | None |\n| **Enterprise templates** | 49 templates (discovery → delivery → handover) | None | None |\n| **Observability** | Audit logs, OTLP telemetry, file provenance, cost budgets | None | None |\n| **Configurable autonomy** | guided / supervised / autonomous | N/A | N/A |\n| **Linear integration** | Task sync (create, status update, close) | None | None |\n| **Real-time dashboard** | 3D office scene (React Three Fiber) + 2D fallback, WebSocket relay | None | None |\n\n### What AgentOps does that neither competitor does\n\n1. **7-layer security system.** Injection scanning, exfiltration detection, Unicode/Glassworm defense, path traversal protection, credential redaction, env var guarding, and content trust — all running as hooks on every tool invocation.\n2. **EvoSkill self-evolution.** The failure-collector → proposer → skill-builder → feedback-history pipeline auto-generates skills from failures. No manual intervention.\n3. **Full observability.** Structured audit logs, OTLP telemetry export, file provenance tracking, and cost budgets with session-level granularity.\n4. **8.5-phase build lifecycle.** From brainstorm to merged PR with state machine, resumability, human gates, parallel research, TDD enforcement, two-stage review, and Nyquist verification — all configurable via feature flags and autonomy levels.\n5. **Real-time 3D agent dashboard.** A Next.js 16 + React Three Fiber office scene that visualizes agent activity live via WebSocket relay from telemetry JSONL, with 2D fallback for non-GPU environments.\n\n---\n\n## Architecture\n\nThe plugin integrates through four extension points:\n\n| Extension Point | Location | Count | Purpose |\n|-----------------|----------|-------|---------|\n| **Hooks** | `hooks/hooks.json` | 44 | Intercept tool use at every lifecycle event |\n| **Commands** | `commands/*.md` | 40 | User-facing slash commands (`/agentops:*`) |\n| **Agents** | `agents/*.md` | 12 | Specialist subagents for analysis and execution |\n| **Templates** | `templates/**/*.md` | 49 | Standards, architecture patterns, delivery docs |\n\nRuntime state lives in `.agentops/` (auto-created, gitignored).\n\n---\n\n## The Build Command\n\n`/agentops:build` is the master lifecycle command — it orchestrates a project from raw vision to merged, verified code.\n\n### 8.5 Phases\n\n| Phase | Name | What happens | Human gate? |\n|-------|------|-------------|-------------|\n| 1 | **BRAINSTORM** | Vision capture → 3 alternative framings → brief | Yes |\n| 2 | **INTERROGATION** | 4 parallel researchers + exhaustive Q&A → requirements | Yes |\n| 3 | **PLANNING** | STAR analysis → XML plan → 8-dimension validation | Yes |\n| 4 | **TASK BREAKDOWN** | Parse XML → per-task TDD mini-plans → Linear sync | Yes |\n| 4.5 | **SCAFFOLD** | Auto-scaffold new projects (conditional) | — |\n| 5 | **EXECUTION** | Fresh subagent per task, wave-based parallelism, TDD enforced | Supervised only |\n| 6 | **REVIEW** | Stage 1: spec compliance → Stage 2: code quality → fix wave | Yes |\n| 7 | **VERIFICATION** | Nyquist audit + full test suite + E2E + compliance gates | Yes |\n| 8 | **APPROVAL** | Summary → PR creation → Linear cleanup → lesson capture | Yes |\n\n### Key features\n\n- **Resumable state machine** — state saved to `.agentops/build-state.json` after each phase\n- **Fresh context per task** — each execution task gets a fresh 200K-token subagent with full standards injection\n- **Mandatory TDD** — RED→GREEN→REFACTOR enforced; no code without a failing test first\n- **Nyquist compliance** — every task must have ``, ``, and `` in the XML plan\n- **4 parallel researchers** — stack, architecture, features, pitfalls research runs concurrently\n- **8-dimension plan validation** — completeness, dependency DAG, file ownership, task size, Nyquist, wave ordering, TDD ordering, commit quality\n- **Two-stage review** — spec compliance reviewer maps every requirement to implementation; code quality reviewer checks 11 dimensions\n- **Persuasion psychology** — Cialdini's 5 techniques (authority, commitment, scarcity, social proof, loss aversion) embedded in human gates\n- **Quick mode** — `--quick` for brainstorm → plan → execute → verify (no interrogation, no PR)\n\n---\n\n## Security (7 Layers)\n\n| Layer | Hook | What it blocks |\n|-------|------|---------------|\n| Command validation | `validate-command.sh` | `rm -rf /`, fork bombs, shell injection, destructive ops |\n| Path validation | `validate-path.sh` | Path traversal, system dirs, sensitive dotfiles |\n| Env protection | `validate-env.sh` | `PATH`/`HOME` reassignment, credential patterns |\n| Injection detection | `injection-scan.sh` | Role-switching, authority markers, delimiter attacks |\n| Exfiltration prevention | `exfiltration-check.sh` | `curl`/`wget` with sensitive files, base64+network combos |\n| Credential redaction | `credential-redact.sh` | `.env`, `.pem`, `.key` access → audit + alert |\n| Content trust | `content-trust.sh` | Flags external content as untrusted + optional LLM firewall |\n\nPlus supply-chain defense: Unicode/Glassworm detection (`unicode-firewall.sh`), integrity verification (`integrity-verify.sh`), and lockfile auditing (`lockfile-audit.sh`).\n\n---\n\n## Commands (40)\n\n### Core Commands\n\n| Command | Purpose |\n|---------|---------|\n| `/agentops:build` | Master 8.5-phase project lifecycle — vision to merged PR |\n| `/agentops:plan` | STAR-based implementation plan with checkable tasks |\n| `/agentops:star` | Quick STAR analysis (lighter than plan) |\n| `/agentops:interrogate` | Exhaustive requirements discovery — eliminates all assumptions |\n| `/agentops:workflow` | 8-phase workflow mapping with YAML schemas and Mermaid diagrams |\n| `/agentops:verify` | Verify task completion against STAR criteria |\n| `/agentops:evolve` | Run EvoSkill self-improvement loop |\n| `/agentops:code-field` | Code Field methodology (decompose, solve with confidence, verify) |\n| `/agentops:code-analysis` | Structured code analysis on current project |\n| `/agentops:lessons` | Display all captured lessons |\n| `/agentops:lesson` | Capture a single lesson learned |\n| `/agentops:compliance-check` | Run compliance gates manually |\n| `/agentops:cost-report` | Session cost tracking and budget status |\n| `/agentops:flags` | View or toggle feature flags |\n| `/agentops:configure` | Unified configuration interface with presets |\n| `/agentops:prune` | Clean up stale runtime state |\n| `/agentops:supply-chain-scan` | Scan dependencies for supply-chain threats |\n| `/agentops:unicode-scan` | Scan project for invisible Unicode characters |\n\n### Enterprise Commands\n\n| Command | Purpose |\n|---------|---------|\n| `/agentops:feature` | 6-phase structured feature build with configurable autonomy |\n| `/agentops:scaffold` | Interactive project scaffolding with tech stack selection |\n| `/agentops:review` | Unified code review (code-critic + security-reviewer agents) |\n| `/agentops:test-gen` | AI-generated test suites with quality validation |\n| `/agentops:reason` | Multi-step reasoning: Analyse → Design → Validate → Recommend |\n| `/agentops:design` | Solution design — architecture proposals, risk assessment |\n| `/agentops:adr` | Architecture Decision Records |\n| `/agentops:brainstorm` | Structured brainstorming sessions |\n| `/agentops:qa-check` | Pre-deployment QA: security, performance, accessibility |\n| `/agentops:handover` | Client handover documentation and runbooks |\n| `/agentops:onboard` | Generate onboarding guides from project structure |\n| `/agentops:knowledge` | Search project knowledge base |\n| `/agentops:status-report` | Client-facing status report from git history |\n| `/agentops:tech-catalog` | Technology catalog and stack documentation |\n| `/agentops:gap-analysis` | Gap analysis between current and desired state |\n| `/agentops:dev-setup` | Developer environment setup guide |\n| `/agentops:docker-dev` | Docker development environment configuration |\n| `/agentops:e2e` | End-to-end test planning and execution |\n| `/agentops:worklog` | Personal work log for tracking daily contributions |\n| `/agentops:idea` | Structured idea proposals with development and export |\n| `/agentops:search` | Unified search across work log, ideas, git history, and knowledge base |\n| `/agentops:herd` | Multi-agent coordination for complex tasks |\n\n---\n\n## Specialist Agents (12)\n\n### Core Agents\n\n| Agent | Tools | Purpose |\n|-------|-------|---------|\n| `code-critic` | Read, Grep, Glob, Bash | 11-dimension code quality review |\n| `security-reviewer` | Read, Grep, Glob, Bash, WebSearch | OWASP Top 10, CVE scanning, auth gaps |\n| `interrogator` | Read, Grep, Glob, WebSearch | Requirements discovery and plan generation |\n| `proposer` | Read, Grep, Glob | Failure analysis → skill proposals (EvoSkill) |\n| `skill-builder` | Read, Grep, Glob, Bash | Materialize skill proposals into SKILL.md files |\n| `delegation-router` | Read, Grep, Glob | Route tasks to appropriate specialist agents |\n\n### Build Agents (Phase-specific)\n\n| Agent | Phase | Tools | Purpose |\n|-------|-------|-------|---------|\n| `stack-researcher` | 2 | Read, Grep, Glob, WebSearch | Technology stack options with fit scores |\n| `architecture-researcher` | 2 | Read, Grep, Glob, WebSearch | Architectural patterns and ADRs |\n| `feature-researcher` | 2 | Read, Grep, Glob, WebSearch | MVP vs v2 scope, feature trade-offs |\n| `pitfalls-researcher` | 2 | Read, Grep, Glob, WebSearch | Anti-patterns, failure modes, security pitfalls |\n| `plan-validator` | 3 | Read, Grep, Glob | 8-dimension plan validation |\n| `spec-compliance-reviewer` | 6 | Read, Grep, Glob, Bash | Requirement mapping + standards compliance |\n\n---\n\n## Hook System (44 hooks)\n\nHooks fire at 7 lifecycle events:\n\n| Event | When | Example hooks |\n|-------|------|---------------|\n| `SessionStart` | Session begins | session-cleanup, star-preamble, code-field-preamble, lessons-check, budget-check, unicode-scan, integrity-verify, lockfile-audit |\n| `PreToolUse` | Before tool executes | validate-command, validate-path, validate-env, injection-scan, exfiltration-check, star-gate, auto-plan, runtime-mode |\n| `PostToolUse` | After tool completes | content-trust, unicode-firewall, integrity-verify, credential-redact, detect-test-run, standards-enforce, ai-guardrails, plan-gate, auto-test, auto-delegate, audit-log, telemetry |\n| `PostToolUseFailure` | After tool fails | failure-collector, auto-lesson, evolve-gate, telemetry |\n| `SubagentStart` | Subagent spawned | delegation-trust |\n| `Stop` | Session ending | auto-verify, auto-evolve, compliance-gate |\n| `SessionEnd` | Final cleanup | telemetry |\n\n---\n\n## EvoSkill Self-Evolution\n\n```\nTool Failure → failure-collector.sh → failures.jsonl\n ↓\n /agentops:evolve\n ↓\n proposer agent (analyze failures,\n check existing skills & feedback)\n ↓\n Skill Proposal\n ↓\n skill-builder agent (materialize SKILL.md)\n ↓\n feedback-history.jsonl (record outcome)\n```\n\nTriggered automatically at session stop (if 2+ unprocessed failures exist) or manually via `/agentops:evolve`.\n\n---\n\n## Engineering Standards\n\nThe build system injects comprehensive engineering standards into every execution subagent:\n\n- **SOLID** — all 5 principles with heuristics and code examples (SRP: ≤30 line functions, ≤200 line classes)\n- **Clean Code** — naming, functions (≤3 params, command-query separation), error handling (typed hierarchy, correlation IDs)\n- **DRY/KISS/YAGNI** — with clear thresholds (2+ locations = extract, 3+ uses before abstracting)\n- **Design Patterns** — creational, structural, behavioral with selection heuristic (\"name the problem it solves\")\n- **Action-Based Architecture** — single-purpose action classes for business logic\n- **DDD** — aggregates, entities, value objects, domain services, ubiquitous language\n- **Layered Architecture** — controller → service → domain → repository (no skipping, violations = CRITICAL)\n- **Security** — injection prevention, secrets management, auth, input validation, data protection (all CRITICAL)\n- **Testing** — Arrange-Act-Assert, red-first TDD, behaviour over implementation\n\nStandards are enforced via `templates/standards/standards-checklist.md` during Phase 6 review.\n\n---\n\n## Feature Flags (33+)\n\nAll flags default to sensible values and are toggleable via `/agentops:flags` or `.agentops/flags.json`.\n\n### Security flags\n`command_validation_enabled`, `path_validation_enabled`, `env_validation_enabled`, `injection_scan_enabled`, `content_trust_enabled`, `exfiltration_detection_enabled`, `credential_redaction_enabled`, `llm_content_firewall_enabled`\n\n### Workflow flags\n`star_preamble_enabled`, `code_field_rules_enabled`, `plan_gate_enabled`, `verification_gate_enabled`, `test_gate_enabled`, `lessons_enabled`\n\n### Automation flags\n`auto_plan_enabled`, `auto_test_enabled`, `auto_verify_enabled`, `auto_lesson_enabled`, `auto_evolve_enabled`, `auto_delegate_enabled`\n\n### Build lifecycle flags\n`build_tdd_enforced`, `build_parallel_research`, `build_xml_plans`, `build_linear_sync`, `build_fresh_context`, `build_wave_parallel`, `build_nyquist_enforce`, `build_persuasion`, `build_quick_mode`, `build_scaffold_auto`, `build_standards_inject`, `standards_enforcement_mode`\n\n### Dashboard flags\n`dashboard_enabled`\n\n### Enterprise flags\n`enterprise_scaffold`, `ai_workflows`, `unified_review`, `architecture_guardrails`, `delivery_lifecycle`, `team_governance`, `client_comms`\n\n### Autonomy levels\n- **guided** (default) — all human gates active\n- **supervised** — all human gates + step-level confirmation during execution\n- **autonomous** — skip soft gates, only hard security gates remain\n\n### Configuration presets\n```bash\n/agentops:configure preset minimal # Security only, no automation\n/agentops:configure preset standard # Security + core automation\n/agentops:configure preset enterprise # All features, guided autonomy\n/agentops:configure preset autonomous # All features, minimal gates\n```\n\n---\n\n## Observability\n\n| System | File | Purpose |\n|--------|------|---------|\n| Audit log | `.agentops/audit.jsonl` | Every tool invocation with timestamp, session, tool, input |\n| Telemetry | `.agentops/telemetry.jsonl` | Structured events with optional OTLP export |\n| File provenance | `.agentops/provenance.jsonl` | Source and trust level of every file interaction |\n| Cost tracking | `.agentops/budget.json` | Session budget with 80% warning threshold |\n| Build execution | `.agentops/build-execution.jsonl` | Per-task execution log with TDD phase tracking |\n| Failure log | `.agentops/failures.jsonl` | Tool failures for EvoSkill analysis |\n| Integrity | `.agentops/integrity.jsonl` | SHA-256 manifest of agent-written files |\n\n---\n\n## Agent Office Dashboard\n\nA real-time 3D visualization of agent activity, built with Next.js 16, React Three Fiber, and Shadcn UI.\n\n### Features\n\n| Feature | Description |\n|---------|-------------|\n| **3D office scene** | Workstations with lighting, agent avatars, and animations via React Three Fiber |\n| **Real-time state** | WebSocket relay server streams agent activity from JSONL telemetry files |\n| **2D fallback** | Activity table with WebGL detection for environments without GPU support |\n| **Session registry** | Auto-registers sessions from incoming telemetry with stale detection |\n| **Connection status** | Live indicator showing relay connection health |\n| **Lifecycle management** | Proper Three.js disposal and resource cleanup |\n\n### How it works\n\n```\nhooks/telemetry.sh → .agentops/telemetry.jsonl\n ↓\ndashboard/server/file-watcher.ts (byte-offset tracking)\n ↓\ndashboard/server/relay.ts (WebSocket with origin validation)\n ↓\ndashboard/src/ (Zustand store → 3D scene / 2D table)\n```\n\nThe dashboard launches automatically when `dashboard_enabled` is `true` in `.agentops/flags.json`. The `dashboard-launch.sh` hook starts the Next.js dev server and WebSocket relay on session start.\n\n---\n\n## Configuration\n\n### Environment Variables\n\n| Variable | Default | Purpose |\n|----------|---------|---------|\n| `AGENTOPS_MODE` | `standard` | Runtime mode (`safe`, `standard`, `full`, `unrestricted`) |\n| `AGENTOPS_BUDGET_USD` | `5` | Session cost budget in USD |\n| `OTLP_ENDPOINT` | _(none)_ | OpenTelemetry endpoint for telemetry forwarding |\n| `LINEAR_API_KEY` | _(none)_ | Linear API key for build task sync |\n\n### Key Files\n\n| File | Purpose |\n|------|---------|\n| `.claude-plugin/plugin.json` | Plugin metadata |\n| `hooks/hooks.json` | Master hook registry |\n| `settings.json` | Plugin permission defaults |\n| `.agentops/flags.json` | Feature flag toggles (auto-created) |\n| `.agentops/budget.json` | Cost tracking (auto-created) |\n\n---\n\n## Directory Structure\n\n```\nagentops-plugin/\n├── .claude-plugin/\n│ └── plugin.json # Plugin metadata\n├── hooks/ # 44 shell scripts + hooks.json\n│ ├── hooks.json # Master hook registry\n│ ├── feature-flags.sh # Shared flag library (facade)\n│ ├── flag-utils.sh # Core flag reading\n│ ├── enforcement-lib.sh # Enforcement actions\n│ ├── patterns-lib.sh # Shared patterns & thresholds\n│ ├── redact-lib.sh # Secret redaction\n│ ├── evolve-lib.sh # Failure tracking helpers\n│ ├── unicode-lib.sh # Unicode detection library\n│ └── *.sh # Security, automation, compliance hooks\n├── commands/ # 37 slash commands\n│ ├── build.md # /agentops:build (master lifecycle)\n│ ├── plan.md # /agentops:plan (STAR planning)\n│ ├── interrogate.md # /agentops:interrogate (requirements)\n│ ├── workflow.md # /agentops:workflow (process mapping)\n│ └── enterprise/ # 19 enterprise delivery commands\n├── agents/ # 12 specialist agents\n│ ├── code-critic.md # Code quality (11 dimensions)\n│ ├── security-reviewer.md # Security (OWASP, CVEs)\n│ ├── stack-researcher.md # Technology research (build Phase 2)\n│ ├── architecture-researcher.md # Architecture research (build Phase 2)\n│ ├── feature-researcher.md # Feature scoping (build Phase 2)\n│ ├── pitfalls-researcher.md # Failure modes (build Phase 2)\n│ ├── plan-validator.md # 8-dimension validation (build Phase 3)\n│ └── spec-compliance-reviewer.md # Spec + standards review (build Phase 6)\n├── templates/ # 49 templates\n│ ├── standards/ # Engineering standards + checklist\n│ ├── build/ # Brief, task-plan, summary templates\n│ ├── architecture/ # 8 architecture pattern templates\n│ ├── delivery/ # Discovery → deployment → handover\n│ ├── communication/ # Stakeholder comms templates\n│ ├── workflows/ # Feature, refactor, spike, bug workflows\n│ └── scaffolds/ # Error handling, logging, health checks\n├── dashboard/ # Agent Office Dashboard (Next.js 16)\n│ ├── src/ # React components, stores, types\n│ ├── server/ # WebSocket relay + JSONL file watcher\n│ └── tests/ # Dashboard unit tests (Vitest)\n├── tests/ # 20 BATS test files (security, automation, dashboard)\n├── docs/ # Architecture docs\n├── settings.json # Plugin permission defaults\n├── LICENSE # MIT\n└── .gitignore\n```\n\n---\n\n## Testing\n\nThe plugin includes 20 BATS test files covering security hooks, automation hooks, and dashboard integration:\n\n```bash\n# Run all tests\nbats tests/\n\n# Security hooks\nbats tests/validate-command.bats\nbats tests/validate-path.bats\nbats tests/validate-env.bats\nbats tests/injection-scan.bats\nbats tests/exfiltration-check.bats\nbats tests/credential-redact.bats\nbats tests/content-trust.bats\nbats tests/feature-flags.bats\n\n# Automation hooks\nbats tests/auto-test.bats\nbats tests/auto-plan.bats\nbats tests/auto-verify.bats\nbats tests/auto-lesson.bats\nbats tests/auto-evolve.bats\nbats tests/auto-delegate.bats\nbats tests/failure-collector.bats\nbats tests/evolve-gate.bats\n\n# Dashboard\nbats tests/dashboard-flag.bats\nbats tests/dashboard-launch.bats\nbats tests/session-registry.bats\nbats tests/telemetry-pretool.bats\n```\n\n---\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for how to report bugs, suggest features, and submit PRs.\n\nThis project follows the [Contributor Covenant Code of Conduct](CODE_OF_CONDUCT.md).\n\n## Security\n\nFound a vulnerability? See [.github/SECURITY.md](.github/SECURITY.md) for responsible disclosure instructions. Do not open a public issue.\n\n## License\n\nMIT License. See [LICENSE](LICENSE) for details.\n", "bytes": 24855, "sha": "aae052625ca60c89522584c7d63ee37b6d79e12c1381a3ba8b81e7ec73bc3b34", "repo_slug": "garethdaine/agentops", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/plg_garethdaine_agentops_agentops_979671a4/readme" }