Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/jovandyaz/knowtis-app/orientingnpx skills add jovandyaz/knowtis-app --skill orientinggit clone --depth 1 https://github.com/jovandyaz/knowtis-appWrote 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/skills/jovandyaz/knowtis-app/orienting)<a href="https://agentmods.dev/skills/jovandyaz/knowtis-app/orienting"><img src="https://agentmods.dev/badge/skills/jovandyaz/knowtis-app/orienting.svg" alt="Measured on agentmods" 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 | $0.00085 | $0.00771 |
| Opus 5 | $0.00043 | $0.00385 |
| Sonnet 5 | $0.00017 | $0.00154 |
| Haiku 4.5 | $0.00009 | $0.00077 |
Grade A, and why
orienting scanned grade A with 0 findings 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 4d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orienting in Knowtis
Knowtis is a real-time collaborative notes platform: Nx monorepo, pnpm, Node 22. React 19 + Vite frontend, NestJS 11 backend, PostgreSQL 16 + Drizzle, Redis, Yjs/Hocuspocus CRDT collaboration, Vercel AI SDK v6.
For the full layout and dependency rules load references/architecture-map.md. For Nx tags/boundaries and the dual alias namespaces load references/aliases-and-boundaries.md.
The five facts that prevent most wasted sessions
- There are TWO AI modules.
apps/api/src/modules/ai= single-shot AI features (inline assistant).apps/api/src/modules/agent= the conversational copilot (tool loop, HITL, threads). Both sit on the framework-free@knowtis/ai-gatewaypackage. Don't add copilot features toaior vice versa. - Two alias namespaces. 18 workspace entries import as
@knowtis/*; publishable auth/permissions/email packages import as@jovandyaz/*. There is no@knowtis/auth— that import will not resolve. - The
import typeDI footgun. Inapps/api/**,import typeon a constructor-injected class silently breaks NestJS DI (provider arrivesundefined). ESLint auto-fix is disabled there for this reason. - Migrations:
generate+migrate, neverpush. Schema lives inapps/api/src/database/schema/;pnpm db:generateproduces the migration; Railway's pre-deploy command is the only production migrator.drizzle-kit pushagainst shared DBs causes the schema drift that migrations were adopted to fix. - Deploys are CI-driven, not Git-integration-driven. Notes and backoffice deploy to separate Vercel projects; API and MCP deploy through
.github/scripts/railway-deploy.sh. Railway still applieswatchPatternsto uploaded snapshots;SKIPPEDmeans no new deployment became live and must be checked against Nx's affected set.
Working rules
- Everything runs through Nx:
pnpm nx affected -t lint test build,nx run <project> <target>. Alwayspnpm, never npm/yarn. - Module boundaries are ESLint-enforced via tags (
type:app → type:ui/data-access → type:util; scopesshared|notes|api). A new lib needs correct tags or imports will be rejected. - AI features are gated:
ANTHROPIC_API_KEYin env AND DB feature flags (ai_enabled,agent_byok, …) toggled on. A feature "not working" is often just a flag defaulting to off. - Repo docs are canonical:
docs/ARCHITECTURE.md,docs/AI.md,docs/MCP.md,docs/AUTH.md,docs/PERMISSIONS.md,docs/MIGRATIONS.md,docs/DEPLOYMENT.md. Verify behavior against those docs and the current code rather than relying on historical design notes.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 27 lines · 85 tokens per session scan A 682e1a8bd4e4
orienting is a skill published in the GitHub repository jovandyaz/knowtis-app (3 stars, last pushed yesterday), licensed MIT. It adds 85 tokens to every session and 771 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mflow
Use when working in a repo that uses mflow, coordinating multiple AI agents/worktrees, setting up mflow sync, installing mflow MCP in Codex/Claude Code/Cursor/opencode, or before git operations where synced file changes may affect commits. Applies to CLI, MCP, room secrets, pause/resume, locks, status checks, and safe…
collavre
Manage Collavre Creatives (hierarchical tasks/content blocks) via CLI. Use when creating, retrieving, updating, importing, or batch-operating on Creatives. Creatives are tree-structured items with automatic progress rollup — like a smart to-do list that doubles as a structured document.
escurel-platform
Use when building an application that consumes the Escurel knowledge-base service as its data store — designing a tenant's skill/instance data model, calling the agent tools…
writing-specs
Use when writing or editing a spec inside a Pairdown room — a document a team will read without you in the room. Covers where to think out loud versus what belongs in the document, and the rules that keep the document skimmable.
joining-a-room
Use when the user wants to join, open, create or leave a Pairdown room, when they mention a room id or a Pairdown link, when they ask what rooms exist, or when they ask why an agent is not showing up in a room. Covers attaching a session to a room, how being summoned works, and the two things that usually go wrong.
demo-video
Record Collavre demo / feature-intro videos from a declarative YAML scenario. Drives a local dev server with Playwright, animates the REAL AI streaming UI via a local fake OpenAI server, and post-processes to MP4 + poster per theme/size. Use when creating or updating product demo videos, feature walkthroughs, or…