Borrowing it
Nothing to install: this file belongs to kaltura/kaltura-agents-api-guides. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kaltura/kaltura-agents-api-guides/main/AGENTS.mdgit clone --depth 1 https://github.com/kaltura/kaltura-agents-api-guidesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/kaltura/kaltura-agents-api-guides/agents-md)<a href="https://agentmods.dev/instructions/kaltura/kaltura-agents-api-guides/agents-md"><img src="https://agentmods.dev/badge/instructions/kaltura/kaltura-agents-api-guides/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/kaltura/kaltura-agents-api-guides/agents-md"><img src="https://agentmods.dev/badge/instructions/kaltura/kaltura-agents-api-guides/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.06841 | $0.06841 |
| Opus 5 | $0.03420 | $0.03420 |
| Sonnet 5 | $0.01368 | $0.01368 |
| Haiku 4.5 | $0.00684 | $0.00684 |
Grade A, and why
kaltura-agents-api-guides AGENTS.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **Language-agnostic.** All API examples use `curl` with shell variables. Agents choose their own language. How it starts
The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kaltura API Guides — Project Standards
This project produces Kaltura API documentation for AI agents building applications on Kaltura. Every guide must be accurate, tested against the live API, and written so an agent can follow it to build integrations safely, securely, and efficiently.
Repository Structure
Kaltura API Guides/
├── AGENTS.md # This file
├── PLAN.md # Master roadmap and API landscape
├── GUIDE_MAP.md # Dependency graph, reading order, decision tree
├── KALTURA_API_GETTING_STARTED.md # API structure, first call, multirequest, errors
├── KALTURA_SESSION_GUIDE.md # KS generation and management
├── KALTURA_GETTING_CREDENTIALS.md # Obtain credentials, configure .env, verify access
├── KALTURA_APPTOKENS_API.md # Secure auth with AppTokens
├── KALTURA_ESEARCH_API.md # Unified search
├── KALTURA_UPLOAD_AND_INGESTION_API.md # Upload, ingest, entry CRUD, flavors, attachments
├── KALTURA_VIDEO_EDITING_API.md # Trim, clip, concat, overlay, chroma key, caption burn-in, effects
├── KALTURA_CONTENT_DELIVERY_API.md # playManifest, serve, download, delivery profiles, CDN, access control
├── KALTURA_THUMBNAIL_API.md # Dynamic thumbnail URL, thumbAsset, thumbParams
├── KALTURA_PLAYER_EMBED_GUIDE.md # Player v7 embed (iframe + JS)
├── KALTURA_REACH_API.md # Enrichment services marketplace: 23 service types, machine + human, 80+ languages
├── KALTURA_AGENTS_MANAGER_API.md # Automated content processing
├── KALTURA_AI_GENIE_API.md # Conversational AI search
├── KALTURA_EVENTS_PLATFORM_API.md # Virtual events
├── KALTURA_MULTI_STREAM_API.md # Dual/multi-screen entries
├── KALTURA_APP_REGISTRY_API.md # Application instance registry
├── KALTURA_USER_PROFILE_API.md # Per-app user profiles & attendance
├── KALTURA_MESSAGING_API.md # Template-based email messaging
├── KALTURA_EVENT_NOTIFICATIONS_WEBHOOK_AND_EMAIL_API.md # HTTP webhooks & email via Messaging Service
├── KALTURA_USER_MANAGEMENT_API.md # User CRUD, roles (RBAC), groups
├── KALTURA_AUTH_BROKER_API.md # SSO/SAML auth profiles, app subscriptions
├── KALTURA_ACCESS_CONTROL_API.md # Access control profiles, rules, conditions
├── KALTURA_CATEGORIES_AND_ENTITLEMENTS_API.md # Categories, membership, entitlements
├── KALTURA_CUSTOM_METADATA_API.md # XSD schemas, metadata profiles, XSLT transforms
├── KALTURA_CAPTIONS_AND_TRANSCRIPTS_API.md # Caption assets, transcripts, multi-language, REACH
├── KALTURA_ANALYTICS_REPORTS_API.md # Reports, CSV exports, live analytics, stream health
├── KALTURA_ANALYTICS_EVENTS_COLLECTION_API.md # Playback & engagement event collection
├── KALTURA_GAMIFICATION_API.md # Leaderboards, badges, certificates, lead scoring
├── KALTURA_DISTRIBUTION_API.md # Content distribution connectors (push to YouTube/FB/FTP)
├── KALTURA_SYNDICATION_API.md # Syndication feeds (RSS/MRSS/iTunes/Roku pull)
├── KALTURA_EXPERIENCE_COMPONENTS_API.md # Experience components index (links to standalone guides)
├── KALTURA_EXPRESS_RECORDER_API.md # Browser-based WebRTC recording
├── KALTURA_CAPTIONS_EDITOR_API.md # Interactive caption editing with video/waveform sync
├── KALTURA_CONVERSATIONAL_AVATAR_API.md # Agentic Avatars — AI-powered conversational video avatars (intelligent-agents-sdk)
├── KALTURA_CNC_API.md # Chat & Collaborate (real-time chat, Q&A, polls)
├── KALTURA_GENIE_WIDGET_API.md # Conversational AI search widget
├── KALTURA_MEDIA_MANAGER_API.md # Browsable media library (select, upload, manage entries)
├── KALTURA_CONTENT_LAB_WIDGET_API.md # AI content repurposing (summaries, chapters, clips, quizzes)
├── KALTURA_AGENTS_WIDGET_API.md # Automated content-processing agent management UI
├── KALTURA_VOD_AVATAR_API.md # Pre-recorded avatar video generation from scripts
├── KALTURA_ANALYTICS_EMBED_API.md # Embeddable analytics dashboards via iframe
├── KALTURA_UNISPHERE_FRAMEWORK_API.md # Unisphere micro-frontend framework (loader, workspace, services)
├── KALTURA_MULTI_ACCOUNT_MANAGEMENT_API.md # Multi-account management, cross-account analytics
├── KALTURA_MODERATION_API.md # Content moderation: flagging, approve/reject, AI moderation via REACH
├── KALTURA_CUE_POINTS_API.md # Cue points hub: temporal metadata concepts, base service, eSearch, protocols
├── KALTURA_QUIZ_API.md # Interactive video quizzes: questions, scoring, reports, IVQ plugin
├── KALTURA_CHAPTERS_AND_SLIDES_API.md # Chapters, slides, timedThumbAsset workflow, navigation plugin
├── KALTURA_ANNOTATIONS_API.md # Annotations, threaded replies, hotspots, searchableOnEntry
├── KALTURA_AD_CUE_POINTS_API.md # VAST/VPAID ad insertion: pre-roll, mid-roll, overlay
├── KALTURA_CODE_CUE_POINTS_API.md # Code markers, view-change, forceStop, event/session cue points
├── KALTURA_LTI_INTEGRATION_GUIDE.md # LTI integration: KAF modules, auth flows, deep linking, grade passback
├── version.txt # Current version (managed by release-please)
├── release-please-config.json # Release automation config
├── .release-please-manifest.json # Version tracking for release-please
└── tests/ # Companion test scripts
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 352 lines · 6,841 tokens per session scan A 9388f048fb13
kaltura-agents-api-guides AGENTS.md is an instructions file published in the GitHub repository kaltura/kaltura-agents-api-guides (4 stars, last pushed yesterday), licensed MIT. It adds 6,841 tokens to every session, about $0.0342 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).